Publications
Below you will find the full publications list authored by members of the research group. The most up-to-date list can be found here.
2024
Salimi, Salma; Salimpour, Sahar; Queralta, Jorge Peña; Bessa, Wallace Moreira; Westerlund, Tomi
Benchmarking ML Approaches to UWB-Based Range-Only Posture Recognition for Human–Robot Interaction Journal Article
In: IEEE Sensors Journal, 2024.
@article{salimiBenchmarkingMLApproaches2024,
title = {Benchmarking ML Approaches to UWB-Based Range-Only Posture Recognition for Human–Robot Interaction},
author = {Salma Salimi and Sahar Salimpour and Jorge Peña Queralta and Wallace Moreira Bessa and Tomi Westerlund},
url = {https://ieeexplore.ieee.org/document/10752843},
doi = {10.1109/JSEN.2024.3493256},
year = {2024},
date = {2024-11-13},
urldate = {2024-01-01},
journal = {IEEE Sensors Journal},
abstract = {Human pose estimation involves detecting and tracking the positions of various body parts using input data from sources such as images, videos, or motion and inertial sensors. This paper presents a novel approach to human pose estimation using machine learning algorithms to predict human posture and translate them into robot motion commands using ultra-wideband (UWB) nodes, as an alternative to motion sensors. The study utilizes five UWB sensors implemented on the human body to enable the classification of still poses and more robust posture recognition. This approach ensures effective posture recognition across a variety of subjects. These range measurements serve as input features for posture prediction models, which are implemented and compared for accuracy. For this purpose, machine learning algorithms including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and deep Multi-Layer Perceptron (MLP) neural network are employed and compared in predicting corresponding postures. We demonstrate the proposed approach for real-time control of different mobile/aerial robots with inference implemented in a ROS2 node. Experimental results demonstrate the efficacy of the approach, showcasing successful prediction of human posture and corresponding robot movements with high accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Human pose estimation involves detecting and tracking the positions of various body parts using input data from sources such as images, videos, or motion and inertial sensors. This paper presents a novel approach to human pose estimation using machine learning algorithms to predict human posture and translate them into robot motion commands using ultra-wideband (UWB) nodes, as an alternative to motion sensors. The study utilizes five UWB sensors implemented on the human body to enable the classification of still poses and more robust posture recognition. This approach ensures effective posture recognition across a variety of subjects. These range measurements serve as input features for posture prediction models, which are implemented and compared for accuracy. For this purpose, machine learning algorithms including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and deep Multi-Layer Perceptron (MLP) neural network are employed and compared in predicting corresponding postures. We demonstrate the proposed approach for real-time control of different mobile/aerial robots with inference implemented in a ROS2 node. Experimental results demonstrate the efficacy of the approach, showcasing successful prediction of human posture and corresponding robot movements with high accuracy.
Zhang, Jiaqiang; Yu, Xianjia; Ha, Sier; Queralta, Jorge Peña; Westerlund, Tomi
Comparison of Middlewares in Edge-to-Edge and Edge-to-Cloud Communication for Distributed ROS 2 Systems Journal Article
In: Journal of Intelligent & Robotic Systems, vol. 110, no. 4, pp. 162, 2024, ISSN: 1573-0409.
@article{zhangComparisonMiddlewaresEdgeEdge2024,
title = {Comparison of Middlewares in Edge-to-Edge and Edge-to-Cloud Communication for Distributed ROS 2 Systems},
author = {Jiaqiang Zhang and Xianjia Yu and Sier Ha and Jorge Peña Queralta and Tomi Westerlund},
url = {https://link.springer.com/10.1007/s10846-024-02187-z},
doi = {10.1007/s10846-024-02187-z},
issn = {1573-0409},
year = {2024},
date = {2024-11-01},
urldate = {2024-11-13},
journal = {Journal of Intelligent & Robotic Systems},
volume = {110},
number = {4},
pages = {162},
abstract = {Abstract
The increased data transmission and number of devices involved in communications among distributed systems make it challenging yet significantly necessary to have an efficient and reliable networking middleware. In robotics and autonomous systems, the wide application of ROS 2 brings the possibility of utilizing various networking middlewares together with DDS in ROS 2 for better communication among edge devices or between edge devices and the cloud. However, there is a lack of comprehensive communication performance comparison of integrating these networking middlewares with ROS 2. In this study, we provide a quantitative analysis for the communication performance of utilized networking middlewares including MQTT and Zenoh alongside DDS in ROS 2 among a multiple host system. For a complete and reliable comparison, we calculate the latency and throughput of these middlewares by sending distinct amounts and types of data through different network setups including Ethernet, Wi-Fi, and 4G. To further extend the evaluation to real-world application scenarios, we assess the drift error (the position changes) over time caused by these networking middlewares with the robot moving in an identical square-shaped path. Our results show that CycloneDDS performs better under Ethernet while Zenoh performs better under Wi-Fi and 4G. In the actual robot test, the robot moving trajectory drift error over time (96 s) via Zenoh is the smallest. It is worth noting we have a discussion of the CPU utilization of these networking middlewares and the perfosrmance impact caused by enabling the security feature in ROS 2 at the end of the paper.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abstract
The increased data transmission and number of devices involved in communications among distributed systems make it challenging yet significantly necessary to have an efficient and reliable networking middleware. In robotics and autonomous systems, the wide application of ROS 2 brings the possibility of utilizing various networking middlewares together with DDS in ROS 2 for better communication among edge devices or between edge devices and the cloud. However, there is a lack of comprehensive communication performance comparison of integrating these networking middlewares with ROS 2. In this study, we provide a quantitative analysis for the communication performance of utilized networking middlewares including MQTT and Zenoh alongside DDS in ROS 2 among a multiple host system. For a complete and reliable comparison, we calculate the latency and throughput of these middlewares by sending distinct amounts and types of data through different network setups including Ethernet, Wi-Fi, and 4G. To further extend the evaluation to real-world application scenarios, we assess the drift error (the position changes) over time caused by these networking middlewares with the robot moving in an identical square-shaped path. Our results show that CycloneDDS performs better under Ethernet while Zenoh performs better under Wi-Fi and 4G. In the actual robot test, the robot moving trajectory drift error over time (96 s) via Zenoh is the smallest. It is worth noting we have a discussion of the CPU utilization of these networking middlewares and the perfosrmance impact caused by enabling the security feature in ROS 2 at the end of the paper.
The increased data transmission and number of devices involved in communications among distributed systems make it challenging yet significantly necessary to have an efficient and reliable networking middleware. In robotics and autonomous systems, the wide application of ROS 2 brings the possibility of utilizing various networking middlewares together with DDS in ROS 2 for better communication among edge devices or between edge devices and the cloud. However, there is a lack of comprehensive communication performance comparison of integrating these networking middlewares with ROS 2. In this study, we provide a quantitative analysis for the communication performance of utilized networking middlewares including MQTT and Zenoh alongside DDS in ROS 2 among a multiple host system. For a complete and reliable comparison, we calculate the latency and throughput of these middlewares by sending distinct amounts and types of data through different network setups including Ethernet, Wi-Fi, and 4G. To further extend the evaluation to real-world application scenarios, we assess the drift error (the position changes) over time caused by these networking middlewares with the robot moving in an identical square-shaped path. Our results show that CycloneDDS performs better under Ethernet while Zenoh performs better under Wi-Fi and 4G. In the actual robot test, the robot moving trajectory drift error over time (96 s) via Zenoh is the smallest. It is worth noting we have a discussion of the CPU utilization of these networking middlewares and the perfosrmance impact caused by enabling the security feature in ROS 2 at the end of the paper.
Zhang, Jiaqiang; Yu, Xianjia; Sier, Ha; Zhang, Haizhou; Westerlund, Tomi
Event-based Sensor Fusion and Application on Odometry: A Survey Miscellaneous
2024, (arXiv:2410.15480 [cs]).
@misc{zhangEventbasedSensorFusion2024,
title = {Event-based Sensor Fusion and Application on Odometry: A Survey},
author = {Jiaqiang Zhang and Xianjia Yu and Ha Sier and Haizhou Zhang and Tomi Westerlund},
url = {http://arxiv.org/abs/2410.15480},
year = {2024},
date = {2024-10-01},
urldate = {2024-11-14},
publisher = {arXiv},
abstract = {Event cameras, inspired by biological vision, are asynchronous sensors that detect changes in brightness, offering notable advantages in environments characterized by high-speed motion, low lighting, or wide dynamic range. These distinctive properties render event cameras particularly effective for sensor fusion in robotics and computer vision, especially in enhancing traditional visual or LiDAR-inertial odometry. Conventional frame-based cameras suffer from limitations such as motion blur and drift, which can be mitigated by the continuous, low-latency data provided by event cameras. Similarly, LiDAR-based odometry encounters challenges related to the loss of geometric information in environments such as corridors. To address these limitations, unlike the existing event camera-related surveys, this paper presents a comprehensive overview of recent advancements in event-based sensor fusion for odometry applications particularly, investigating fusion strategies that incorporate frame-based cameras, inertial measurement units (IMUs), and LiDAR. The survey critically assesses the contributions of these fusion methods to improving odometry performance in complex environments, while highlighting key applications, and discussing the strengths, limitations, and unresolved challenges. Additionally, it offers insights into potential future research directions to advance event-based sensor fusion for next-generation odometry applications.},
note = {arXiv:2410.15480 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Event cameras, inspired by biological vision, are asynchronous sensors that detect changes in brightness, offering notable advantages in environments characterized by high-speed motion, low lighting, or wide dynamic range. These distinctive properties render event cameras particularly effective for sensor fusion in robotics and computer vision, especially in enhancing traditional visual or LiDAR-inertial odometry. Conventional frame-based cameras suffer from limitations such as motion blur and drift, which can be mitigated by the continuous, low-latency data provided by event cameras. Similarly, LiDAR-based odometry encounters challenges related to the loss of geometric information in environments such as corridors. To address these limitations, unlike the existing event camera-related surveys, this paper presents a comprehensive overview of recent advancements in event-based sensor fusion for odometry applications particularly, investigating fusion strategies that incorporate frame-based cameras, inertial measurement units (IMUs), and LiDAR. The survey critically assesses the contributions of these fusion methods to improving odometry performance in complex environments, while highlighting key applications, and discussing the strengths, limitations, and unresolved challenges. Additionally, it offers insights into potential future research directions to advance event-based sensor fusion for next-generation odometry applications.
Ha, Sier; Du, Honghao; Yu, Xianjia; Song, Jian; Westerlund, Tomi
2024, (arXiv:2409.11532 [cs]).
@misc{haEnhancingReliabilityLiDAR2024,
title = {Enhancing the Reliability of LiDAR Point Cloud Sampling: A Colorization and Super-Resolution Approach Based on LiDAR-Generated Images},
author = {Sier Ha and Honghao Du and Xianjia Yu and Jian Song and Tomi Westerlund},
url = {http://arxiv.org/abs/2409.11532},
year = {2024},
date = {2024-09-01},
urldate = {2024-11-14},
publisher = {arXiv},
abstract = {In recent years, Light Detection and Ranging (LiDAR) technology, a critical sensor in robotics and autonomous systems, has seen significant advancements. These improvements include enhanced resolution of point clouds and the capability to provide 360textbackslashdeg low-resolution images. These images encode various data such as depth, reflectivity, and near-infrared light within the pixels. However, an excessive density of points and conventional point cloud sampling can be counterproductive, particularly in applications such as LiDAR odometry, where misleading points and degraded geometry information may induce drift errors. Currently, extensive research efforts are being directed towards leveraging LiDAR-generated images to improve situational awareness. This paper presents a comprehensive review of current deep learning (DL) techniques, including colorization and super-resolution, which are traditionally utilized in conventional computer vision tasks. These techniques are applied to LiDAR-generated images and are analyzed qualitatively. Based on this analysis, we have developed a novel approach that selectively integrates the most suited colorization and super-resolution methods with LiDAR imagery to sample reliable points from the LiDAR point cloud. This approach aims to not only improve the accuracy of point cloud registration but also avoid mismatching caused by lacking geometry information, thereby augmenting the utility and precision of LiDAR systems in practical applications. In our evaluation, the proposed approach demonstrates superior performance compared to our previous work, achieving lower translation and rotation errors with a reduced number of points.},
note = {arXiv:2409.11532 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
In recent years, Light Detection and Ranging (LiDAR) technology, a critical sensor in robotics and autonomous systems, has seen significant advancements. These improvements include enhanced resolution of point clouds and the capability to provide 360textbackslashdeg low-resolution images. These images encode various data such as depth, reflectivity, and near-infrared light within the pixels. However, an excessive density of points and conventional point cloud sampling can be counterproductive, particularly in applications such as LiDAR odometry, where misleading points and degraded geometry information may induce drift errors. Currently, extensive research efforts are being directed towards leveraging LiDAR-generated images to improve situational awareness. This paper presents a comprehensive review of current deep learning (DL) techniques, including colorization and super-resolution, which are traditionally utilized in conventional computer vision tasks. These techniques are applied to LiDAR-generated images and are analyzed qualitatively. Based on this analysis, we have developed a novel approach that selectively integrates the most suited colorization and super-resolution methods with LiDAR imagery to sample reliable points from the LiDAR point cloud. This approach aims to not only improve the accuracy of point cloud registration but also avoid mismatching caused by lacking geometry information, thereby augmenting the utility and precision of LiDAR systems in practical applications. In our evaluation, the proposed approach demonstrates superior performance compared to our previous work, achieving lower translation and rotation errors with a reduced number of points.
Mwase, Christine; Jin, Yi; Westerlund, Tomi; Tenhunen, Hannu; Zou, Zhuo
DAI-NET: Toward communication-aware collaborative training for the industrial edge Journal Article
In: Future Generation Computer Systems, vol. 155, pp. 193–203, 2024, ISSN: 0167-739X.
@article{mwaseDAINETCommunicationawareCollaborative2024,
title = {DAI-NET: Toward communication-aware collaborative training for the industrial edge},
author = {Christine Mwase and Yi Jin and Tomi Westerlund and Hannu Tenhunen and Zhuo Zou},
url = {https://research.utu.fi/converis/portal/detail/Publication/381182419?lang=en_GB},
doi = {10.1016/j.future.2024.01.027},
issn = {0167-739X},
year = {2024},
date = {2024-06-01},
urldate = {2024-04-03},
journal = {Future Generation Computer Systems},
volume = {155},
pages = {193–203},
abstract = {The industrial edge generates an abundance of spatially distributed and dynamic data that needs to remain on-site for privacy and security reasons. Collaborative training at the edge can leverage this data to refine pre-trained models locally for specific industrial tasks and environments and have them adapt to local changes for enhanced performance, agility, and resilience. However, communication between the devices during training is a key bottleneck and is not modelled by existing frameworks such as MxNet, PyTorch and TensorFlow. This paper introduces DAI-NET, a co-simulation framework for examining communication and its associated costs, and provides results from an implementation using Python, OMNET++ and INET. To validate it and showcase its utility, the developed platform is applied in the analysis of (i) the performance and cost of collaboratively training a Multilayer Perceptron model, and (ii) the influence of computational heterogeneity. Communication costs generated during the training are captured at the device and system levels. In computationally heterogeneous clusters, the root cause of stragglers is exposed. In addition, the key performance contributors are identified to be a cluster’s computation capability and the variation in the relative computation capabilities of its devices. This study is particularly useful for Artificial Intelligence of Things (AIoT) systems, whose bandwidth and energy resources are limited. It lends the way for more practical research on communication-efficient algorithms, network protocols and architectures for the AIoT edge.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The industrial edge generates an abundance of spatially distributed and dynamic data that needs to remain on-site for privacy and security reasons. Collaborative training at the edge can leverage this data to refine pre-trained models locally for specific industrial tasks and environments and have them adapt to local changes for enhanced performance, agility, and resilience. However, communication between the devices during training is a key bottleneck and is not modelled by existing frameworks such as MxNet, PyTorch and TensorFlow. This paper introduces DAI-NET, a co-simulation framework for examining communication and its associated costs, and provides results from an implementation using Python, OMNET++ and INET. To validate it and showcase its utility, the developed platform is applied in the analysis of (i) the performance and cost of collaboratively training a Multilayer Perceptron model, and (ii) the influence of computational heterogeneity. Communication costs generated during the training are captured at the device and system levels. In computationally heterogeneous clusters, the root cause of stragglers is exposed. In addition, the key performance contributors are identified to be a cluster’s computation capability and the variation in the relative computation capabilities of its devices. This study is particularly useful for Artificial Intelligence of Things (AIoT) systems, whose bandwidth and energy resources are limited. It lends the way for more practical research on communication-efficient algorithms, network protocols and architectures for the AIoT edge.
Nawaz, Anum; Wang, Liguan; Irfan, Muhammad; Westerlund, Tomi
Hyperledger sawtooth based supplychain traceability system for counterfeit drugs Journal Article
In: Computers & Industrial Engineering, vol. 190, pp. 110021, 2024, ISSN: 0360-8352.
@article{nawaz_hyperledger_2024,
title = {Hyperledger sawtooth based supplychain traceability system for counterfeit drugs},
author = {Anum Nawaz and Liguan Wang and Muhammad Irfan and Tomi Westerlund},
url = {https://www.sciencedirect.com/science/article/pii/S0360835224001426},
doi = {10.1016/j.cie.2024.110021},
issn = {0360-8352},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-03},
journal = {Computers & Industrial Engineering},
volume = {190},
pages = {110021},
abstract = {Drug supply chains have been facing severe issues as counterfeit product cases are increasing exponentially. A supply chain management system that ensures transparency, reliability, and provenance of drugs would increase the trustworthiness of the whole industry. One solution to all three needs is utilizing blockchain-based distributed ledger technologies (DLTs). Even though DLTs are emerging as an ideal infrastructure for multi-stakeholder supply chain applications, they still need to be more mature to address the specific challenges specific to each use case. In this article, we propose a distributed blockchain-based framework, PHTrack, leveraging hyperledger sawtooth as a drug supply chain traceability system. Hyperledger sawtooth addresses scalability issues by offering a robust foundation to support large-scale drug supply chain operations in a modular way for it’s each participating stakeholder. Furthermore, it simplifies the integration process with existing systems, even those employing different technologies, thereby facilitating a smoother transition to DLTs. The design of PHTrack is oriented towards minimizing resource consumption throughout the process, particularly within hyperledger sawtooth nodes. Additionally, it incorporates quantum secure off-chain communication for peer-to-peer (P2P) communication. A set of experiments was conducted to validate the proposed framework. Experiments have shown that PHTrack provides reliable and comprehensive drug provenance as well as real-time drug supply chain tracking.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Drug supply chains have been facing severe issues as counterfeit product cases are increasing exponentially. A supply chain management system that ensures transparency, reliability, and provenance of drugs would increase the trustworthiness of the whole industry. One solution to all three needs is utilizing blockchain-based distributed ledger technologies (DLTs). Even though DLTs are emerging as an ideal infrastructure for multi-stakeholder supply chain applications, they still need to be more mature to address the specific challenges specific to each use case. In this article, we propose a distributed blockchain-based framework, PHTrack, leveraging hyperledger sawtooth as a drug supply chain traceability system. Hyperledger sawtooth addresses scalability issues by offering a robust foundation to support large-scale drug supply chain operations in a modular way for it’s each participating stakeholder. Furthermore, it simplifies the integration process with existing systems, even those employing different technologies, thereby facilitating a smoother transition to DLTs. The design of PHTrack is oriented towards minimizing resource consumption throughout the process, particularly within hyperledger sawtooth nodes. Additionally, it incorporates quantum secure off-chain communication for peer-to-peer (P2P) communication. A set of experiments was conducted to validate the proposed framework. Experiments have shown that PHTrack provides reliable and comprehensive drug provenance as well as real-time drug supply chain tracking.
Catalano, Iacopo; Queralta, Jorge Peña; Westerlund, Tomi
Evaluating the Performance of Multi-scan Integration for UAV LiDAR-Based Tracking Proceedings Article
In: Westerlund, Tomi; Queralta, Jorge Peña (Ed.): New Developments and Environmental Applications of Drones, pp. 85–95, Springer Nature Switzerland, Cham, 2024, ISBN: 9783031446078.
@inproceedings{catalano_evaluating_2024,
title = {Evaluating the Performance of Multi-scan Integration for UAV LiDAR-Based Tracking},
author = {Iacopo Catalano and Jorge Peña Queralta and Tomi Westerlund},
editor = {Tomi Westerlund and Jorge Peña Queralta},
doi = {10.1007/978-3-031-44607-8_6},
isbn = {9783031446078},
year = {2024},
date = {2024-01-01},
booktitle = {New Developments and Environmental Applications of Drones},
pages = {85–95},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Drones have become essential tools in a wide range of industries, including agriculture, surveying, and transportation. However, tracking unmanned aerial vehicles (UAVs) in challenging environments, such as cluttered or GNSS-denied environments, remains a critical issue. Additionally, UAVs are being deployed as part of multi-robot systems, where tracking their position can be essential for relative state estimation. In this chapter, we evaluate the performance of a multi-scan integration method for tracking UAVs in GNSS-denied environments using a solid-state LiDAR and a Kalman Filter (KF). We evaluate the algorithm’s ability to track a UAV in a large open area at various distances and speeds. Our quantitative analysis shows that while “tracking by detection” using a constant-velocity model is the only method that consistently tracks the target, integrating multiple scan frequencies using a KF achieves lower position errors and represents a viable option for tracking UAVs in similar scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Drones have become essential tools in a wide range of industries, including agriculture, surveying, and transportation. However, tracking unmanned aerial vehicles (UAVs) in challenging environments, such as cluttered or GNSS-denied environments, remains a critical issue. Additionally, UAVs are being deployed as part of multi-robot systems, where tracking their position can be essential for relative state estimation. In this chapter, we evaluate the performance of a multi-scan integration method for tracking UAVs in GNSS-denied environments using a solid-state LiDAR and a Kalman Filter (KF). We evaluate the algorithm’s ability to track a UAV in a large open area at various distances and speeds. Our quantitative analysis shows that while “tracking by detection” using a constant-velocity model is the only method that consistently tracks the target, integrating multiple scan frequencies using a KF achieves lower position errors and represents a viable option for tracking UAVs in similar scenarios.
Thuan, Phuoc Nguyen; Queralta, Jorge Peña; Westerlund, Tomi
Simulation Analysis of Exploration Strategies and UAV Planning for Search and Rescue Proceedings Article
In: Westerlund, Tomi; Queralta, Jorge Peña (Ed.): New Developments and Environmental Applications of Drones, pp. 75–84, Springer Nature Switzerland, Cham, 2024, ISBN: 9783031446078.
@inproceedings{thuan_simulation_2024,
title = {Simulation Analysis of Exploration Strategies and UAV Planning for Search and Rescue},
author = {Phuoc Nguyen Thuan and Jorge Peña Queralta and Tomi Westerlund},
editor = {Tomi Westerlund and Jorge Peña Queralta},
doi = {10.1007/978-3-031-44607-8_5},
isbn = {9783031446078},
year = {2024},
date = {2024-01-01},
booktitle = {New Developments and Environmental Applications of Drones},
pages = {75–84},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Aerial scans with unmanned aerial vehicles (UAVs) are becoming more widely adopted across industries, from smart farming to urban mapping. An application area that can leverage the strength of such systems is search and rescue (SAR) operations. However, with a vast variability in strategies and topology of application scenarios, as well as the difficulties in setting up real-world UAV-aided SAR operations for testing, designing an optimal flight pattern to search for and detect all victims can be a challenging problem. Specifically, the deployed UAV should be able to scan the area in the shortest amount of time while maintaining high victim detection recall rates. Therefore, low probability of false negatives (i.e., high recall) is more important than precision in this case. To address the issues mentioned above, we have developed a simulation environment that emulates different SAR scenarios and allows experimentation with flight missions to provide insight into their efficiency. The solution was developed with the open-source ROS framework and Gazebo simulator, with PX4 as the autopilot system for flight control, and YOLO as the object detector.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Aerial scans with unmanned aerial vehicles (UAVs) are becoming more widely adopted across industries, from smart farming to urban mapping. An application area that can leverage the strength of such systems is search and rescue (SAR) operations. However, with a vast variability in strategies and topology of application scenarios, as well as the difficulties in setting up real-world UAV-aided SAR operations for testing, designing an optimal flight pattern to search for and detect all victims can be a challenging problem. Specifically, the deployed UAV should be able to scan the area in the shortest amount of time while maintaining high victim detection recall rates. Therefore, low probability of false negatives (i.e., high recall) is more important than precision in this case. To address the issues mentioned above, we have developed a simulation environment that emulates different SAR scenarios and allows experimentation with flight missions to provide insight into their efficiency. The solution was developed with the open-source ROS framework and Gazebo simulator, with PX4 as the autopilot system for flight control, and YOLO as the object detector.
Fu, Lei; Morón, Paola Torrico; Queralta, Jorge Peña; Hästbacka, David; Edelman, Harry; Westerlund, Tomi
Is Alice Really in Wonderland? UWB-Based Proof of Location for UAVs with Hyperledger Fabric Blockchain Proceedings Article
In: Westerlund, Tomi; Queralta, Jorge Peña (Ed.): New Developments and Environmental Applications of Drones, pp. 43–56, Springer Nature Switzerland, Cham, 2024, ISBN: 9783031446078.
@inproceedings{fu_is_2024,
title = {Is Alice Really in Wonderland? UWB-Based Proof of Location for UAVs with Hyperledger Fabric Blockchain},
author = {Lei Fu and Paola Torrico Morón and Jorge Peña Queralta and David Hästbacka and Harry Edelman and Tomi Westerlund},
editor = {Tomi Westerlund and Jorge Peña Queralta},
doi = {10.1007/978-3-031-44607-8_3},
isbn = {9783031446078},
year = {2024},
date = {2024-01-01},
booktitle = {New Developments and Environmental Applications of Drones},
pages = {43–56},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Remote identification of Unmanned Aerial Vehicles (UAVs) is becoming increasingly important since more UAVs are being widely used for different needs in urban areas. For example, in the US and in the EU, identification and position broadcasting is already a requirement for the use of drones. However, the current solutions do not validate the position of the UAV but its identity, while trusting the given position. Therefore, a more advanced solution enabling the proof of location is needed to avoid spoofing. We propose the combination of a permissioned blockchain managed by public authorities together with UWB-based communication to approach this. Specifically, we leverage the identity management tools from Hyperledger Fabric, an open-source permissioned blockchain framework, and ultra-wideband (UWB) ranging, leading to situated communication (i.e., simultaneous communication and localization). This approach allows us to prove both the UAV identity and also the location it broadcasts through interaction with ground infrastructure in known locations. Our initial experiments show that the proposed approach is viable and UWB transceivers can be used for UAVs to validate both their identity and position with ground infrastructure deployed in known locations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Remote identification of Unmanned Aerial Vehicles (UAVs) is becoming increasingly important since more UAVs are being widely used for different needs in urban areas. For example, in the US and in the EU, identification and position broadcasting is already a requirement for the use of drones. However, the current solutions do not validate the position of the UAV but its identity, while trusting the given position. Therefore, a more advanced solution enabling the proof of location is needed to avoid spoofing. We propose the combination of a permissioned blockchain managed by public authorities together with UWB-based communication to approach this. Specifically, we leverage the identity management tools from Hyperledger Fabric, an open-source permissioned blockchain framework, and ultra-wideband (UWB) ranging, leading to situated communication (i.e., simultaneous communication and localization). This approach allows us to prove both the UAV identity and also the location it broadcasts through interaction with ground infrastructure in known locations. Our initial experiments show that the proposed approach is viable and UWB transceivers can be used for UAVs to validate both their identity and position with ground infrastructure deployed in known locations.
Taipalmaa, Jussi; Raitoharju, Jenni; Queralta, Jorge Peña; Westerlund, Tomi; Gabbouj, Moncef
On Automatic Person-in-Water Detection for Marine Search and Rescue Operations Journal Article
In: IEEE Access, vol. 12, pp. 52428–52438, 2024, ISSN: 2169-3536.
@article{taipalmaaAutomaticPersonWaterDetection2024,
title = {On Automatic Person-in-Water Detection for Marine Search and Rescue Operations},
author = {Jussi Taipalmaa and Jenni Raitoharju and Jorge Peña Queralta and Tomi Westerlund and Moncef Gabbouj},
url = {https://research.utu.fi/converis/portal/detail/Publication/387653781?lang=fi_FI},
doi = {10.1109/ACCESS.2024.3386640},
issn = {2169-3536},
year = {2024},
date = {2024-01-01},
urldate = {2024-11-13},
journal = {IEEE Access},
volume = {12},
pages = {52428–52438},
abstract = {In marine search and rescue missions, the objective is to find a missing person in the water. Time is a critical factor in the identification of the missing person, as any delay in locating them can have life-threatening consequences. Autonomous unmanned aerial vehicles (UAVs) possess the potential to help in the search task by providing a bird’s-eye view helping to cover larger areas faster. Therefore, it is very important that UAVs can efficiently and accurately detect persons in the water. This work studies automatic person detection in the water from a UAV. We performed experiments on both lakes and sea near Turku, Finland, and captured videos of people in the water from various altitudes and different viewing angles. Our person-in-water detection tests focus on important factors that have not received sufficient attention in prior studies: evaluation metrics and detection thresholds, the impact and use of different bounding box sizes, multi-frame detection and performance in unseen environments. We provide analysis of the suitability of different approaches for the person detection task and we also publish our training and testing data that includes over 72000 frames. To the best of our knowledge, this is the largest publicly available person-in-water detection dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In marine search and rescue missions, the objective is to find a missing person in the water. Time is a critical factor in the identification of the missing person, as any delay in locating them can have life-threatening consequences. Autonomous unmanned aerial vehicles (UAVs) possess the potential to help in the search task by providing a bird’s-eye view helping to cover larger areas faster. Therefore, it is very important that UAVs can efficiently and accurately detect persons in the water. This work studies automatic person detection in the water from a UAV. We performed experiments on both lakes and sea near Turku, Finland, and captured videos of people in the water from various altitudes and different viewing angles. Our person-in-water detection tests focus on important factors that have not received sufficient attention in prior studies: evaluation metrics and detection thresholds, the impact and use of different bounding box sizes, multi-frame detection and performance in unseen environments. We provide analysis of the suitability of different approaches for the person detection task and we also publish our training and testing data that includes over 72000 frames. To the best of our knowledge, this is the largest publicly available person-in-water detection dataset.
Zhang, Haizhou; Yu, Xianjia; Westerlund, Tomi
Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality Miscellaneous
2024, (Version Number: 1).
@misc{zhangDualCriterionModelAggregation2024,
title = {Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality},
author = {Haizhou Zhang and Xianjia Yu and Tomi Westerlund},
url = {https://arxiv.org/abs/2411.07816},
doi = {10.48550/ARXIV.2411.07816},
year = {2024},
date = {2024-01-01},
urldate = {2024-11-13},
publisher = {arXiv},
abstract = {Federated learning (FL) has become one of the key methods for privacy-preserving collaborative learning, as it enables the transfer of models without requiring local data exchange. Within the FL framework, an aggregation algorithm is recognized as one of the most crucial components for ensuring the efficacy and security of the system. Existing average aggregation algorithms typically assume that all client-trained data holds equal value or that weights are based solely on the quantity of data contributed by each client. In contrast, alternative approaches involve training the model locally after aggregation to enhance adaptability. However, these approaches fundamentally ignore the inherent heterogeneity between different clients' data and the complexity of variations in data at the aggregation stage, which may lead to a suboptimal global model.
To address these issues, this study proposes a novel dual-criterion weighted aggregation algorithm involving the quantity and quality of data from the client node. Specifically, we quantify the data used for training and perform multiple rounds of local model inference accuracy evaluation on a specialized dataset to assess the data quality of each client. These two factors are utilized as weights within the aggregation process, applied through a dynamically weighted summation of these two factors. This approach allows the algorithm to adaptively adjust the weights, ensuring that every client can contribute to the global model, regardless of their data's size or initial quality. Our experiments show that the proposed algorithm outperforms several existing state-of-the-art aggregation approaches on both a general-purpose open-source dataset, CIFAR-10, and a dataset specific to visual obstacle avoidance.},
note = {Version Number: 1},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Federated learning (FL) has become one of the key methods for privacy-preserving collaborative learning, as it enables the transfer of models without requiring local data exchange. Within the FL framework, an aggregation algorithm is recognized as one of the most crucial components for ensuring the efficacy and security of the system. Existing average aggregation algorithms typically assume that all client-trained data holds equal value or that weights are based solely on the quantity of data contributed by each client. In contrast, alternative approaches involve training the model locally after aggregation to enhance adaptability. However, these approaches fundamentally ignore the inherent heterogeneity between different clients’ data and the complexity of variations in data at the aggregation stage, which may lead to a suboptimal global model.
To address these issues, this study proposes a novel dual-criterion weighted aggregation algorithm involving the quantity and quality of data from the client node. Specifically, we quantify the data used for training and perform multiple rounds of local model inference accuracy evaluation on a specialized dataset to assess the data quality of each client. These two factors are utilized as weights within the aggregation process, applied through a dynamically weighted summation of these two factors. This approach allows the algorithm to adaptively adjust the weights, ensuring that every client can contribute to the global model, regardless of their data’s size or initial quality. Our experiments show that the proposed algorithm outperforms several existing state-of-the-art aggregation approaches on both a general-purpose open-source dataset, CIFAR-10, and a dataset specific to visual obstacle avoidance.
To address these issues, this study proposes a novel dual-criterion weighted aggregation algorithm involving the quantity and quality of data from the client node. Specifically, we quantify the data used for training and perform multiple rounds of local model inference accuracy evaluation on a specialized dataset to assess the data quality of each client. These two factors are utilized as weights within the aggregation process, applied through a dynamically weighted summation of these two factors. This approach allows the algorithm to adaptively adjust the weights, ensuring that every client can contribute to the global model, regardless of their data’s size or initial quality. Our experiments show that the proposed algorithm outperforms several existing state-of-the-art aggregation approaches on both a general-purpose open-source dataset, CIFAR-10, and a dataset specific to visual obstacle avoidance.
2023
Catalano, Iacopo; Sier, Ha; Yu, Xianjia; Westerlund, Tomi; Queralta, Jorge Peña
UAV Tracking with Solid-State Lidars: Dynamic Multi-Frequency Scan Integration Proceedings Article
In: 2023 21st International Conference on Advanced Robotics (ICAR), pp. 417–424, IEEE, 2023, ISBN: 9798350342291.
@inproceedings{catalanoUAVTrackingSolidState2023,
title = {UAV Tracking with Solid-State Lidars: Dynamic Multi-Frequency Scan Integration},
author = {Iacopo Catalano and Ha Sier and Xianjia Yu and Tomi Westerlund and Jorge Peña Queralta},
url = {https://research.utu.fi/converis/portal/detail/Publication/182011763?lang=en_GB},
doi = {10.1109/ICAR58858.2023.10406884},
isbn = {9798350342291},
year = {2023},
date = {2023-12-01},
urldate = {2023-12-01},
booktitle = {2023 21st International Conference on Advanced Robotics (ICAR)},
pages = {417–424},
publisher = {IEEE},
abstract = {With the increasing use of drones across various industries, the navigation and tracking of these unmanned aerial vehicles (UAVs) in challenging environments (such as GNSS-denied environments) have become critical issues. In this paper, we propose a novel method for a ground-based UAV tracking system using a solid-state LiDAR, which dynamically adjusts the LiDAR frame integration time based on the distance to the UAV and its speed. Our method fuses two simultaneous scan integration frequencies for high accuracy and persistent tracking, enabling reliable estimates of the UAV state even in challenging scenarios. The use of the Inverse Covariance Intersection method and Kalman filters allow for better tracking accuracy and can handle challenging tracking scenarios. We have performed a number of experiments for evaluating the performance of the proposed tracking system and identifying its limitations. Our experimental results demonstrate that the proposed method achieves comparable tracking performance to the established baseline method, while also providing more reliable and accurate tracking when only one of the frequencies is available or unreliable},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With the increasing use of drones across various industries, the navigation and tracking of these unmanned aerial vehicles (UAVs) in challenging environments (such as GNSS-denied environments) have become critical issues. In this paper, we propose a novel method for a ground-based UAV tracking system using a solid-state LiDAR, which dynamically adjusts the LiDAR frame integration time based on the distance to the UAV and its speed. Our method fuses two simultaneous scan integration frequencies for high accuracy and persistent tracking, enabling reliable estimates of the UAV state even in challenging scenarios. The use of the Inverse Covariance Intersection method and Kalman filters allow for better tracking accuracy and can handle challenging tracking scenarios. We have performed a number of experiments for evaluating the performance of the proposed tracking system and identifying its limitations. Our experimental results demonstrate that the proposed method achieves comparable tracking performance to the established baseline method, while also providing more reliable and accurate tracking when only one of the frequencies is available or unreliable
Yu, Xianjia; Catalano, Iacopo; Morón, Paola Torrico; Salimpour, Sahar; Westerlund, Tomi; Queralta, Jorge Peña
Fusing Odometry, UWB Ranging, and Spatial Detections for Relative Multi-Robot Localization Miscellaneous
2023, (arXiv:2304.06264 [cs]).
@misc{yu_fusing_2023,
title = {Fusing Odometry, UWB Ranging, and Spatial Detections for Relative Multi-Robot Localization},
author = {Xianjia Yu and Iacopo Catalano and Paola Torrico Morón and Sahar Salimpour and Tomi Westerlund and Jorge Peña Queralta},
url = {http://arxiv.org/abs/2304.06264},
year = {2023},
date = {2023-09-01},
urldate = {2024-04-03},
publisher = {arXiv},
abstract = {This letter presents a cooperative relative multi-robot localization design and experimental study. We propose a flexible Monte Carlo approach leveraging a particle filter to estimate relative states. The estimation can be based on inter-robot Ultra-Wideband (UWB) ranging and onboard odometry alone or dynamically integrated with cooperative spatial object detections from stereo cameras mounted on each robot. The main contributions of this work are as follows. First, we show that a single UWB range is enough to estimate the accurate relative states of two robots when fusing odometry measurements. Second, our experiments also demonstrate that our approach surpasses traditional methods, namely, multilateration, in terms of accuracy. Third, to further increase accuracy, we allow for the integration of cooperative spatial detections. Finally, we show how ROS 2 and Zenoh can be integrated to build a scalable wireless communication solution for multi-robot systems. The experimental validation includes real-time deployment and autonomous navigation based on the relative positioning method. It is worth mentioning that we also address the challenges for UWB-ranging error mitigation for mobile transceivers. The code is available at https://github.com/TIERS/uwb-cooperative-mrs-localization.},
note = {arXiv:2304.06264 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
This letter presents a cooperative relative multi-robot localization design and experimental study. We propose a flexible Monte Carlo approach leveraging a particle filter to estimate relative states. The estimation can be based on inter-robot Ultra-Wideband (UWB) ranging and onboard odometry alone or dynamically integrated with cooperative spatial object detections from stereo cameras mounted on each robot. The main contributions of this work are as follows. First, we show that a single UWB range is enough to estimate the accurate relative states of two robots when fusing odometry measurements. Second, our experiments also demonstrate that our approach surpasses traditional methods, namely, multilateration, in terms of accuracy. Third, to further increase accuracy, we allow for the integration of cooperative spatial detections. Finally, we show how ROS 2 and Zenoh can be integrated to build a scalable wireless communication solution for multi-robot systems. The experimental validation includes real-time deployment and autonomous navigation based on the relative positioning method. It is worth mentioning that we also address the challenges for UWB-ranging error mitigation for mobile transceivers. The code is available at https://github.com/TIERS/uwb-cooperative-mrs-localization.
Keramat, Farhad; Queralta, Jorge Pena; Westerlund, Tomi
Partition-tolerant and byzantine-tolerant decision-making for distributed robotic systems with iota and ROS 2 Journal Article
In: IEEE Internet of Things Journal, 2023.
@article{keramat2023partition,
title = {Partition-tolerant and byzantine-tolerant decision-making for distributed robotic systems with iota and ROS 2},
author = {Farhad Keramat and Jorge Pena Queralta and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
journal = {IEEE Internet of Things Journal},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sier, Ha; Li, Qingqing; Yu, Xianjia; Queralta, Jorge Peña; Zou, Zhuo; Westerlund, Tomi
A benchmark for multi-modal lidar slam with ground truth in gnss-denied environments Journal Article
In: Remote Sensing, vol. 15, no. 13, pp. 3314, 2023.
@article{sier2023benchmark,
title = {A benchmark for multi-modal lidar slam with ground truth in gnss-denied environments},
author = {Ha Sier and Qingqing Li and Xianjia Yu and Jorge Peña Queralta and Zhuo Zou and Tomi Westerlund},
url = {https://research.utu.fi/converis/portal/detail/Publication/180820026?lang=en_GB},
doi = {https://doi.org/10.3390/rs15133314},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Remote Sensing},
volume = {15},
number = {13},
pages = {3314},
publisher = {MDPI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sier, Ha; Yu, Xianjia; Catalano, Iacopo; Queralta, Jorge Pena; Zou, Zhuo; Westerlund, Tomi
UAV Tracking with Lidar as a Camera Sensor in GNSS-Denied Environments Proceedings Article
In: 2023 International Conference on Localization and GNSS (ICL-GNSS), pp. 1–7, IEEE 2023.
@inproceedings{sier2023uav,
title = {UAV Tracking with Lidar as a Camera Sensor in GNSS-Denied Environments},
author = {Ha Sier and Xianjia Yu and Iacopo Catalano and Jorge Pena Queralta and Zhuo Zou and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
booktitle = {2023 International Conference on Localization and GNSS (ICL-GNSS)},
pages = {1–7},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Queralta, Jorge Pena; Keramat, Farhad; Salimi, Salma; Fu, Lei; Yu, Xianjia; Westerlund, Tomi
Blockchain and emerging distributed ledger technologies for decentralized multi-robot systems Journal Article
In: Current Robotics Reports, vol. 4, no. 3, pp. 43–54, 2023.
@article{queralta2023blockchain,
title = {Blockchain and emerging distributed ledger technologies for decentralized multi-robot systems},
author = {Jorge Pena Queralta and Farhad Keramat and Salma Salimi and Lei Fu and Xianjia Yu and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
journal = {Current Robotics Reports},
volume = {4},
number = {3},
pages = {43–54},
publisher = {Springer International Publishing Cham},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Yu, Xianjia; Salimpour, Sahar; Queralta, Jorge Peña; Westerlund, Tomi
General-Purpose Deep Learning Detection and Segmentation Models for Images from a Lidar-Based Camera Sensor Journal Article
In: Sensors, vol. 23, no. 6, pp. 2936, 2023.
@article{yu2023general,
title = {General-Purpose Deep Learning Detection and Segmentation Models for Images from a Lidar-Based Camera Sensor},
author = {Xianjia Yu and Sahar Salimpour and Jorge Peña Queralta and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
journal = {Sensors},
volume = {23},
number = {6},
pages = {2936},
publisher = {MDPI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Irfan, Muhammad; Shun, Peng; Felix, Barkoum Betra; Mustafa, Noman; Abbasi, Saadullah Farooq; Nahli, Abdelwahed; Subasi, Abdulhamit; Westerlund, Tomi; Chen, Wei
An IoT-Based Non-Contact ECG System: Sole of the Feet/Hands Palm Journal Article
In: IEEE Internet of Things Journal, 2023.
@article{irfan2023iot,
title = {An IoT-Based Non-Contact ECG System: Sole of the Feet/Hands Palm},
author = {Muhammad Irfan and Peng Shun and Barkoum Betra Felix and Noman Mustafa and Saadullah Farooq Abbasi and Abdelwahed Nahli and Abdulhamit Subasi and Tomi Westerlund and Wei Chen},
year = {2023},
date = {2023-01-01},
journal = {IEEE Internet of Things Journal},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Westerlund, Tomi
Decentralized Vision-Based Byzantine Agent Detection in Multi-robot Systems with IOTA Smart Contracts Proceedings Article
In: Foundations and Practice of Security: 15th International Symposium, FPS 2022, Ottawa, ON, Canada, December 12–14, 2022, Revised Selected Papers, pp. 322, Springer Nature 2023.
@inproceedings{westerlund2023decentralized,
title = {Decentralized Vision-Based Byzantine Agent Detection in Multi-robot Systems with IOTA Smart Contracts},
author = {Tomi Westerlund},
year = {2023},
date = {2023-01-01},
booktitle = {Foundations and Practice of Security: 15th International Symposium, FPS 2022, Ottawa, ON, Canada, December 12–14, 2022, Revised Selected Papers},
volume = {13877},
pages = {322},
organization = {Springer Nature},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Edelman, Harry; Stenroos, Joel; Queralta, Jorge Peña; Hästbacka, David; Oksanen, Jani; Westerlund, Tomi; Röning, Juha
Analysis of airport design for introducing infrastructure for autonomous drones Journal Article
In: Facilities, vol. 41, no. 15/16, pp. 85–100, 2023.
@article{edelman2023analysis,
title = {Analysis of airport design for introducing infrastructure for autonomous drones},
author = {Harry Edelman and Joel Stenroos and Jorge Peña Queralta and David Hästbacka and Jani Oksanen and Tomi Westerlund and Juha Röning},
year = {2023},
date = {2023-01-01},
journal = {Facilities},
volume = {41},
number = {15/16},
pages = {85–100},
publisher = {Emerald Publishing Limited},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Haizhou; Yu, Xianjia; Ha, Sier; Westerlund, Tomi
LiDAR-Generated Images Derived Keypoints Assisted Point Cloud Registration Scheme in Odometry Estimation Journal Article
In: Remote Sensing, vol. 15, no. 20, pp. 5074, 2023.
@article{zhang2023lidar,
title = {LiDAR-Generated Images Derived Keypoints Assisted Point Cloud Registration Scheme in Odometry Estimation},
author = {Haizhou Zhang and Xianjia Yu and Sier Ha and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
journal = {Remote Sensing},
volume = {15},
number = {20},
pages = {5074},
publisher = {MDPI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nguyen, Phuoc Thuan; Westerlund, Tomi; Queralta, Jorge Peña
Vision-based safe autonomous UAV docking with panoramic sensors Journal Article
In: Frontiers in Robotics and AI, vol. 10, 2023.
@article{nguyen2023vision,
title = {Vision-based safe autonomous UAV docking with panoramic sensors},
author = {Phuoc Thuan Nguyen and Tomi Westerlund and Jorge Peña Queralta},
year = {2023},
date = {2023-01-01},
journal = {Frontiers in Robotics and AI},
volume = {10},
publisher = {Frontiers Media SA},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nawaz, Anum; Irfan, Muhammad; Westerlund, Tomi
Optical Character Recognition Using Optimized Convolutional Networks Proceedings Article
In: 2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC), pp. 107–114, IEEE 2023.
@inproceedings{nawaz2023optical,
title = {Optical Character Recognition Using Optimized Convolutional Networks},
author = {Anum Nawaz and Muhammad Irfan and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
booktitle = {2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC)},
pages = {107–114},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Irfan, Muhammad; Siddiqa, Hafza Ayesha; Nahli, Abdelwahed; Chen, Chen; Xu, Yan; Wang, Laishuan; Nawaz, Anum; Subasi, Abdulhamit; Westerlund, Tomi; Chen, Wei
An Ensemble Voting Approach with Innovative Multi-Domain Feature Fusion for Neonatal Sleep Stratification Journal Article
In: IEEE Access, 2023.
@article{irfan2023ensemble,
title = {An Ensemble Voting Approach with Innovative Multi-Domain Feature Fusion for Neonatal Sleep Stratification},
author = {Muhammad Irfan and Hafza Ayesha Siddiqa and Abdelwahed Nahli and Chen Chen and Yan Xu and Laishuan Wang and Anum Nawaz and Abdulhamit Subasi and Tomi Westerlund and Wei Chen},
year = {2023},
date = {2023-01-01},
journal = {IEEE Access},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nawaz, Anum; Irfan, Muhammad; Sadiqa, Hafza Ayesha; Westerlund, Tomi
Edge Based Skin Cancer Decision Support System Using Machine Learning Algorithms Proceedings Article
In: 2023 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), pp. 0292–0297, IEEE 2023.
@inproceedings{nawaz2023edge,
title = {Edge Based Skin Cancer Decision Support System Using Machine Learning Algorithms},
author = {Anum Nawaz and Muhammad Irfan and Hafza Ayesha Sadiqa and Tomi Westerlund},
year = {2023},
date = {2023-01-01},
booktitle = {2023 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)},
pages = {0292–0297},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2022
Dhaou, Imed Saad Ben; Kondoro, Aron; Kakakhel, Syed Rameez Ullah; Westerlund, Tomi; Tenhunen, Hannu
Internet of Things technologies for smart grid Book Section
In: Research Anthology on Smart Grid and Microgrid Development, pp. 805–832, IGI Global, 2022.
@incollection{dhaou2022internet,
title = {Internet of Things technologies for smart grid},
author = {Imed Saad Ben Dhaou and Aron Kondoro and Syed Rameez Ullah Kakakhel and Tomi Westerlund and Hannu Tenhunen},
year = {2022},
date = {2022-01-01},
booktitle = {Research Anthology on Smart Grid and Microgrid Development},
pages = {805–832},
publisher = {IGI Global},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Nevalainen, Paavo; Movahedi, Parisa; Queralta, Jorge Peña; Westerlund, Tomi; Heikkonen, Jukka
Long-term autonomy in forest environment using self-corrective slam Proceedings Article
In: New Developments and Environmental Applications of Drones: Proceedings of FinDrones 2020, pp. 83–107, Springer International Publishing 2022.
@inproceedings{nevalainen2022long,
title = {Long-term autonomy in forest environment using self-corrective slam},
author = {Paavo Nevalainen and Parisa Movahedi and Jorge Peña Queralta and Tomi Westerlund and Jukka Heikkonen},
year = {2022},
date = {2022-01-01},
booktitle = {New Developments and Environmental Applications of Drones: Proceedings of FinDrones 2020},
pages = {83–107},
organization = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mwase, Christine; Jin, Yi; Westerlund, Tomi; Tenhunen, Hannu; Zou, Zhuo
Communication-efficient distributed AI strategies for the IoT edge Journal Article
In: Future Generation Computer Systems, vol. 131, pp. 292–308, 2022.
@article{mwase2022communication,
title = {Communication-efficient distributed AI strategies for the IoT edge},
author = {Christine Mwase and Yi Jin and Tomi Westerlund and Hannu Tenhunen and Zhuo Zou},
year = {2022},
date = {2022-01-01},
journal = {Future Generation Computer Systems},
volume = {131},
pages = {292–308},
publisher = {North-Holland},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Morón, Paola Torrico; Queralta, Jorge Peña; Westerlund, Tomi
Towards large-scale relative localization in multi-robot systems with dynamic uwb role allocation Proceedings Article
In: 2022 7th International Conference on Robotics and Automation Engineering (ICRAE), pp. 239–246, IEEE 2022.
@inproceedings{moron2022towards,
title = {Towards large-scale relative localization in multi-robot systems with dynamic uwb role allocation},
author = {Paola Torrico Morón and Jorge Peña Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 7th International Conference on Robotics and Automation Engineering (ICRAE)},
pages = {239–246},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Katila, Risto; Gia, Tuan Nguyen; Westerlund, Tomi
Analysis of mobility support approaches for edge-based IoT systems using high data rate Bluetooth Low Energy 5 Journal Article
In: Computer Networks, vol. 209, pp. 108925, 2022.
@article{katila2022analysis,
title = {Analysis of mobility support approaches for edge-based IoT systems using high data rate Bluetooth Low Energy 5},
author = {Risto Katila and Tuan Nguyen Gia and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
journal = {Computer Networks},
volume = {209},
pages = {108925},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Yu, Xianjia; Queralta, Jorge Pena; Westerlund, Tomi
Federated learning for vision-based obstacle avoidance in the internet of robotic things Proceedings Article
In: 2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC), pp. 1–6, IEEE 2022.
@inproceedings{yu2022federated,
title = {Federated learning for vision-based obstacle avoidance in the internet of robotic things},
author = {Xianjia Yu and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC)},
pages = {1–6},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Yu, Xianjia; Queralta, Jorge Pena; Westerlund, Tomi
Towards lifelong federated learning in autonomous mobile robots with continuous sim-to-real transfer Journal Article
In: Procedia Computer Science, vol. 210, pp. 86–93, 2022.
@article{yu2022towards,
title = {Towards lifelong federated learning in autonomous mobile robots with continuous sim-to-real transfer},
author = {Xianjia Yu and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
journal = {Procedia Computer Science},
volume = {210},
pages = {86–93},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Salimi, Salma; Morón, Paola Torrico; Queralta, Jorge Peña; Westerlund, Tomi
Secure heterogeneous multi-robot collaboration and docking with hyperledger fabric blockchain Proceedings Article
In: 2022 IEEE 8th World Forum on Internet of Things (WF-IoT), pp. 1–7, IEEE 2022.
@inproceedings{salimi2022secure,
title = {Secure heterogeneous multi-robot collaboration and docking with hyperledger fabric blockchain},
author = {Salma Salimi and Paola Torrico Morón and Jorge Peña Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 IEEE 8th World Forum on Internet of Things (WF-IoT)},
pages = {1–7},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Salimpour, Sahar; Queralta, Jorge Pena; Westerlund, Tomi
Self-calibrating anomaly and change detection for autonomous inspection robots Proceedings Article
In: 2022 Sixth IEEE International Conference on Robotic Computing (IRC), pp. 207–214, IEEE 2022.
@inproceedings{salimpour2022self,
title = {Self-calibrating anomaly and change detection for autonomous inspection robots},
author = {Sahar Salimpour and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 Sixth IEEE International Conference on Robotic Computing (IRC)},
pages = {207–214},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Morón, Paola Torrico; Salimi, Salma; Queralta, Jorge Peña; Westerlund, Tomi
UWB role allocation with distributed ledger technologies for scalable relative localization in multi-robot systems Proceedings Article
In: 2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE), pp. 1–8, IEEE 2022.
@inproceedings{moron2022uwb,
title = {UWB role allocation with distributed ledger technologies for scalable relative localization in multi-robot systems},
author = {Paola Torrico Morón and Salma Salimi and Jorge Peña Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)},
pages = {1–8},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Salimpour, Sahar; Keramat, Farhad; Queralta, Jorge Pena; Westerlund, Tomi
Decentralized vision-based byzantine agent detection in multi-robot systems with iota smart contracts Proceedings Article
In: International Symposium on Foundations and Practice of Security, pp. 322–337, Springer Nature Switzerland Cham 2022.
@inproceedings{salimpour2022decentralized,
title = {Decentralized vision-based byzantine agent detection in multi-robot systems with iota smart contracts},
author = {Sahar Salimpour and Farhad Keramat and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {International Symposium on Foundations and Practice of Security},
pages = {322–337},
organization = {Springer Nature Switzerland Cham},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gurgu, Marius-Mihail; Queralta, Jorge Peña; Westerlund, Tomi
Vision-Based GNSS-Free Localization for UAVs in the Wild Proceedings Article
In: 2022 7th International Conference on Mechanical Engineering and Robotics Research (ICMERR), pp. 7–12, IEEE 2022.
@inproceedings{gurgu2022vision,
title = {Vision-Based GNSS-Free Localization for UAVs in the Wild},
author = {Marius-Mihail Gurgu and Jorge Peña Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 7th International Conference on Mechanical Engineering and Robotics Research (ICMERR)},
pages = {7–12},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hernández, Daniel Montero; Queralta, Jorge Peña; Westerlund, Tomi
Distributed Ledger Technologies for Managing Heterogenous Computing Systems at the Edge Proceedings Article
In: 2022 9th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), pp. 1–8, IEEE 2022.
@inproceedings{hernandez2022distributed,
title = {Distributed Ledger Technologies for Managing Heterogenous Computing Systems at the Edge},
author = {Daniel Montero Hernández and Jorge Peña Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 9th International Conference on Internet of Things: Systems, Management and Security (IOTSMS)},
pages = {1–8},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhang, Jiaqiang; Keramat, Farhad; Yu, Xianjia; Hernández, Daniel Montero; Queralta, Jorge Pena; Westerlund, Tomi
Distributed robotic systems in the edge-cloud continuum with ros 2: a review on novel architectures and technology readiness Proceedings Article
In: 2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC), pp. 1–8, IEEE 2022.
@inproceedings{zhang2022distributed,
title = {Distributed robotic systems in the edge-cloud continuum with ros 2: a review on novel architectures and technology readiness},
author = {Jiaqiang Zhang and Farhad Keramat and Xianjia Yu and Daniel Montero Hernández and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC)},
pages = {1–8},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Qingqing, Li; Xianjia, Yu; Queralta, Jorge Pena; Westerlund, Tomi
Multi-modal lidar dataset for benchmarking general-purpose localization and mapping algorithms Proceedings Article
In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3837–3844, IEEE 2022.
@inproceedings{qingqing2022multi,
title = {Multi-modal lidar dataset for benchmarking general-purpose localization and mapping algorithms},
author = {Li Qingqing and Yu Xianjia and Jorge Pena Queralta and Tomi Westerlund},
year = {2022},
date = {2022-01-01},
booktitle = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages = {3837–3844},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Queralta, Jorge Peña; Li, Qingqing; Schiano, Fabrizio; Westerlund, Tomi
VIO-UWB-based collaborative localization and dense scene reconstruction within heterogeneous multi-robot systems Proceedings Article
In: 2022 International Conference on Advanced Robotics and Mechatronics (ICARM), pp. 87–94, IEEE, 2022.
@inproceedings{queraltaVIOUWBbasedCollaborativeLocalization2022,
title = {VIO-UWB-based collaborative localization and dense scene reconstruction within heterogeneous multi-robot systems},
author = {Jorge Peña Queralta and Qingqing Li and Fabrizio Schiano and Tomi Westerlund},
url = {https://research.utu.fi/converis/portal/detail/Publication/177071818?lang=fi_FI},
doi = {10.1109/ICARM54641.2022.9959470},
year = {2022},
date = {2022-01-01},
booktitle = {2022 International Conference on Advanced Robotics and Mechatronics (ICARM)},
pages = {87–94},
publisher = {IEEE},
abstract = {Effective collaboration in multi-robot systems requires accurate and robust estimation of relative localization: from cooperative manipulation to collaborative sensing, and including cooperative exploration or cooperative transportation. This paper introduces a novel approach to collaborative localization for dense scene reconstruction in heterogeneous multi-robot systems comprising ground robots and micro-aerial vehicles (MAVs). We solve the problem of full relative pose estimation without sliding time windows by relying on UWB-based ranging and Visual Inertial Odometry (VIO)-based egomotion estimation for localization, while exploiting lidars onboard the ground robots for full relative pose estimation in a single reference frame. During operation, the rigidity eigenvalue provides feedback to the system. To tackle the challenge of path planning and obstacle avoidance of MAVs in GNSS-denied environments, we maintain line-of-sight between ground robots and MAVs. Because lidars capable of dense reconstruction have limited FoV, this introduces new constraints to the system. Therefore, we propose a novel formulation with a variant of the Dubins multiple traveling salesman problem with neighborhoods (DMTSPN) where we include constraints related to the limited FoV of the ground robots. Our approach is validated with simulations and experiments with real robots for the different parts of the system.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Effective collaboration in multi-robot systems requires accurate and robust estimation of relative localization: from cooperative manipulation to collaborative sensing, and including cooperative exploration or cooperative transportation. This paper introduces a novel approach to collaborative localization for dense scene reconstruction in heterogeneous multi-robot systems comprising ground robots and micro-aerial vehicles (MAVs). We solve the problem of full relative pose estimation without sliding time windows by relying on UWB-based ranging and Visual Inertial Odometry (VIO)-based egomotion estimation for localization, while exploiting lidars onboard the ground robots for full relative pose estimation in a single reference frame. During operation, the rigidity eigenvalue provides feedback to the system. To tackle the challenge of path planning and obstacle avoidance of MAVs in GNSS-denied environments, we maintain line-of-sight between ground robots and MAVs. Because lidars capable of dense reconstruction have limited FoV, this introduces new constraints to the system. Therefore, we propose a novel formulation with a variant of the Dubins multiple traveling salesman problem with neighborhoods (DMTSPN) where we include constraints related to the limited FoV of the ground robots. Our approach is validated with simulations and experiments with real robots for the different parts of the system.
Queralta, Jorge Peña; Li, Qingqing; Ferrer, Eduardo Castelló; Westerlund, Tomi
Secure encoded instruction graphs for end-to-end data validation in autonomous robots Journal Article
In: IEEE Internet of Things Journal, vol. 9, no. 18, pp. 18028–18040, 2022, (Publisher: IEEE).
@article{queraltaSecureEncodedInstruction2022,
title = {Secure encoded instruction graphs for end-to-end data validation in autonomous robots},
author = {Jorge Peña Queralta and Qingqing Li and Eduardo Castelló Ferrer and Tomi Westerlund},
url = {https://research.utu.fi/converis/portal/detail/Publication/174636470?lang=fi_FI},
doi = {10.1109/JIOT.2022.3164545},
year = {2022},
date = {2022-01-01},
journal = {IEEE Internet of Things Journal},
volume = {9},
number = {18},
pages = {18028–18040},
abstract = {As autonomous robots are becoming more widespread, more attention is being paid to the security of robotic operation. Autonomous robots can be seen as cyberphysical systems: they can operate in virtual, physical, and human realms. Therefore, securing the operations of autonomous robots requires not only securing their data (e.g., sensor inputs and mission instructions) but securing their interactions with their environment. There is currently a deficiency of methods that would allow robots to securely ensure their sensors and actuators are operating correctly without external feedback. This paper introduces an encoding method and end-to-end validation framework for the missions of autonomous robots. In particular, we present a proof of concept of a map encoding method, which allows robots to navigate realistic environments and validate operational instructions with almost zero a priori knowledge. We demonstrate our framework using two different encoded maps in experiments with simulated and real robots. Our encoded maps have the same advantages as typical landmark-based navigation, but with the added benefit of cryptographic hashes that enable end-to-end information validation. Our method is applicable to any aspect of robotic operation in which there is a predefined set of actions or instructions given to the robot.},
note = {Publisher: IEEE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
As autonomous robots are becoming more widespread, more attention is being paid to the security of robotic operation. Autonomous robots can be seen as cyberphysical systems: they can operate in virtual, physical, and human realms. Therefore, securing the operations of autonomous robots requires not only securing their data (e.g., sensor inputs and mission instructions) but securing their interactions with their environment. There is currently a deficiency of methods that would allow robots to securely ensure their sensors and actuators are operating correctly without external feedback. This paper introduces an encoding method and end-to-end validation framework for the missions of autonomous robots. In particular, we present a proof of concept of a map encoding method, which allows robots to navigate realistic environments and validate operational instructions with almost zero a priori knowledge. We demonstrate our framework using two different encoded maps in experiments with simulated and real robots. Our encoded maps have the same advantages as typical landmark-based navigation, but with the added benefit of cryptographic hashes that enable end-to-end information validation. Our method is applicable to any aspect of robotic operation in which there is a predefined set of actions or instructions given to the robot.
2021
Qingqing, Li; Xianjia, Yu; Queralta, Jorge Pena; Westerlund, Tomi
Adaptive lidar scan frame integration: Tracking known mavs in 3d point clouds Proceedings Article
In: 2021 20th International Conference on Advanced Robotics (ICAR), pp. 1079–1086, IEEE 2021.
@inproceedings{qingqing2021adaptive,
title = {Adaptive lidar scan frame integration: Tracking known mavs in 3d point clouds},
author = {Li Qingqing and Yu Xianjia and Jorge Pena Queralta and Tomi Westerlund},
year = {2021},
date = {2021-01-01},
booktitle = {2021 20th International Conference on Advanced Robotics (ICAR)},
pages = {1079–1086},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xianjia, Yu; Qingqing, Li; Queralta, Jorge Peña; Heikkonen, Jukka; Westerlund, Tomi
Applications of uwb networks and positioning to autonomous robots and industrial systems Proceedings Article
In: 2021 10th Mediterranean Conference on Embedded Computing (MECO), pp. 1–6, IEEE 2021.
@inproceedings{xianjia2021applications,
title = {Applications of uwb networks and positioning to autonomous robots and industrial systems},
author = {Yu Xianjia and Li Qingqing and Jorge Peña Queralta and Jukka Heikkonen and Tomi Westerlund},
year = {2021},
date = {2021-01-01},
booktitle = {2021 10th Mediterranean Conference on Embedded Computing (MECO)},
pages = {1–6},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xianjia, Yu; Qingqing, Li; Queralta, Jorge Pena; Heikkonen, Jukka; Westerlund, Tomi
Cooperative uwb-based localization for outdoors positioning and navigation of uavs aided by ground robots Proceedings Article
In: 2021 IEEE International Conference on Autonomous Systems (ICAS), pp. 1–5, IEEE 2021.
@inproceedings{xianjia2021cooperative,
title = {Cooperative uwb-based localization for outdoors positioning and navigation of uavs aided by ground robots},
author = {Yu Xianjia and Li Qingqing and Jorge Pena Queralta and Jukka Heikkonen and Tomi Westerlund},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Conference on Autonomous Systems (ICAS)},
pages = {1–5},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xianjia, Yu; Queralta, Jorge Peña; Heikkonen, Jukka; Westerlund, Tomi
Federated learning in robotic and autonomous systems Journal Article
In: Procedia Computer Science, vol. 191, pp. 135–142, 2021.
@article{xianjia2021federated,
title = {Federated learning in robotic and autonomous systems},
author = {Yu Xianjia and Jorge Peña Queralta and Jukka Heikkonen and Tomi Westerlund},
year = {2021},
date = {2021-01-01},
journal = {Procedia Computer Science},
volume = {191},
pages = {135–142},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nguyen, Minh; Gia, Tuan Nguyen; Westerlund, Tomi
EMG-based IoT system using hand gestures for remote control applications Proceedings Article
In: 2021 IEEE 7th World Forum on Internet of Things (WF-IoT), pp. 911–912, IEEE 2021.
@inproceedings{nguyen2021emg,
title = {EMG-based IoT system using hand gestures for remote control applications},
author = {Minh Nguyen and Tuan Nguyen Gia and Tomi Westerlund},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE 7th World Forum on Internet of Things (WF-IoT)},
pages = {911–912},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Irfan, Muhammad; Jawad, Husnain; Felix, Barkoum Betra; Abbasi, Saadullah Farooq; Nawaz, Anum; Akbarzadeh, Saeed; Awais, Muhammad; Chen, Lin; Westerlund, Tomi; Chen, Wei
Non-wearable IoT-based smart ambient behavior observation system Journal Article
In: IEEE Sensors Journal, vol. 21, no. 18, pp. 20857–20869, 2021.
@article{irfan2021non,
title = {Non-wearable IoT-based smart ambient behavior observation system},
author = {Muhammad Irfan and Husnain Jawad and Barkoum Betra Felix and Saadullah Farooq Abbasi and Anum Nawaz and Saeed Akbarzadeh and Muhammad Awais and Lin Chen and Tomi Westerlund and Wei Chen},
year = {2021},
date = {2021-01-01},
journal = {IEEE Sensors Journal},
volume = {21},
number = {18},
pages = {20857–20869},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Kramar, Vadim; Kanth, Rajeev; Toppinen, Arto; Rabah, Mohammed; Immonen, Eero; Koskela, Marjut; Erkkilä, Juha; Westerlund, Tomi; Tenhunen, Hannu; Isoaho, Jouni; others,
Unmanned Aircraft Systems-Education Activities in Finland, UCNDrone Perspective Proceedings Article
In: Proceeding of the 30th Conference of Fruct Association, Fruct oy 2021.
@inproceedings{kramar2021unmanned,
title = {Unmanned Aircraft Systems-Education Activities in Finland, UCNDrone Perspective},
author = {Vadim Kramar and Rajeev Kanth and Arto Toppinen and Mohammed Rabah and Eero Immonen and Marjut Koskela and Juha Erkkilä and Tomi Westerlund and Hannu Tenhunen and Jouni Isoaho and others},
year = {2021},
date = {2021-01-01},
booktitle = {Proceeding of the 30th Conference of Fruct Association},
organization = {Fruct oy},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}