Communication Algorithms for Spatio-Temporal Cooperation in Multi-Robot Systems

Majcherczyk, Nathalie

Etd

Communication Algorithms for Spatio-Temporal Cooperation in Multi-Robot Systems

Pubblico

Swarm robotics has the potential to offer key solutions for large-scale, time-sensitive and dangerous applications, such as wildfire fighting and disaster response. Teams of robots promise capabilities beyond the reach of single-robot solutions by distributing intelligence, sensing and actuation at a large scale. This opportunity comes with the challenge of dealing with large amounts of data which are physically distributed across robots. Therefore, a key precondition for the swarm to coordinate successfully is the ability of the robots to store and exchange information efficiently. This dissertation proposes a novel modular framework for organizing communication in highly mobile robotic swarms. Its first part addresses how to maintain continuous connectivity between robots via distributed motion coordination. This ensures that there are communication paths between any two robots to exchange information. The second part presents the design of a distributed data structure for low-memory, low-bandwidth, highly mobile swarms. The final part leverages previous insights and contributions to tackle distributed learning and collective perception applications. The outcomes of this work include: (i) scalable connectivity maintenance algorithms tested extensively in realistic simulation and with real robots, (ii) a general and reusable platform for storing quantities of data that exceed the memory of individual robots, while maintaining near-perfect data retention in high-load conditions, and (iii) algorithms for collectively learning a machine learning model and improving accuracy of predictions through cooperation.

Creator