Research Area:  Machine Learning
The recent advancement of Deep Reinforcement Learning (DRL) contributed to robotics by allowing automatic controller design. The automatic controller design is a crucial approach for designing swarm robotic systems, which require more complex controllers than a single robot system to lead a desired collective behaviour. Although the DRL-based controller design method showed its effectiveness for swarm robotic systems, the reliance on the central training server is a critical problem in real-world environments where robot-server communication is unstable or limited. We propose a novel Federated Learning (FL) based DRL training strategy (FLDDPG) for use in swarm robotic applications. Through the comparison with baseline strategies under a limited communication bandwidth scenario, it is shown that the FLDDPG method resulted in higher robustness and generalisation ability into a different environment and real robots, while the baseline strategies suffer from the limitation of communication bandwidth. This result suggests that the proposed method can benefit swarm robotic systems operating in environments with limited communication bandwidth, e.g., in high-radiation, underwater, or subterranean environments.
Keywords:  
Training
Robots
Swarm robotics
Servers
Robot kinematics
Design methodology
Collision avoidance
Author(s) Name:  Seongin Na,Tomas Roucek,Jan Pikman
Journal name:  IEEE Transactions on Cognitive and Developmental Systems
Conferrence name:  
Publisher name:  IEEE
DOI:  10.1109/TCDS.2023.3239815
Volume Information:  
Paper Link:   https://ieeexplore.ieee.org/abstract/document/10025836