R3Swarms - Robust, Resilient and Reconfigurable Swarms
For robots to become more ubiquitous and interoperable in tomorrow’s world of smart cities and the industrial internet of things (IIoT), novel wireless connectivity solutions, and the means to enable more resilient and flexible swarms deployable across multiple scenarios must be brought forward today. The swarm robotics domain has the potential for bringing decades of theoretical research into practice and impact the real world with novel solutions to swarming autonomous cars, swarming drones in the U-Space large-scale distributed swarms of industrial robots, and masses of service robots swarming our cities.
The R3Swarms project comprehensively addresses some of the key challenges in current technology by developing a framework that integrates (1) secure UWB-based mesh connectivity and collaborative localization; (2) DLT-powered trustable and transparent collaboration and consensus; (3) deep-learning-enhanced predictive situational awareness; and (4) multi-tier autonomy stack with cloud-fog-edge fallback mechanisms. In turn, these four tracks build together towards the design and development of robust, resilient and reconfigurable swarms with efficient fleet management and interfacing. Applications will be provided through a swarm-as-a-service, with abstraction of swarm capabilities and resources as a large- scale system of heterogeneous autonomous entities.
Funded by: Secure Systems Research Center (SSRC), Technology Innovation Institute (TII), Abu Dhabi Government’s Advanced Technology Research Council (ATRC)
 Yu Xianjia, Sahar Salimpour, Jorge Peña Queralta, Tomi Westerlund, "Analyzing General-Purpose Deep-Learning Detection and Segmentation Models with Images from a Lidar as a Camera Sensor", International Conference on Intelligent Systems Design and Engineering Applications (ISDEA), Lecture Notes in Electrical Engineering (to appear) , Springer (2022) . (View) (Download)
 Paola Torrico Morón, Jorge Peña Queralta, Tomi Westerlund, "Towards Large-Scale Relative Localization in Multi-Robot Systems with Dynamic UWB Role Allocation", arXiv preprint (2022) . (View) (Download) (arXiv)
 Jorge Peña Queralta, Li Qingqing, Eduardo Castelló Ferrer, Tomi Westerlund, "Secure Encoded Instruction Graphs for End-to-End Data Validation in Autonomous Robots", IEEE Internet of Things Journal (to appear) , IEEE (2022) . (View) (Download) (Researchgate) (arXiv)
 Jorge Peña Queralta, Li Qingqing, Fabrizio Schiano, Tomi Westerlund, "VIO-UWB-Based Collaborative Localization and Dense Scene Reconstruction within Heterogeneous Multi-Robot Systems", IEEE International Conference on Advanced Robotics and Mechatronics , IEEE (2022) . (View) (Download) (arXiv)