English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present a decentralized sensor-level collision avoidancepolicy for multi-robot systems, which shows promising results in practicalapplications. In particular, our policy directly maps raw sensor measurementsto an agent's steering commands in terms of the movement velocity. As a firststep toward reducing the performance gap between decentralized and centralizedmethods, we present a multi-scenario multi-stage training framework to learn anoptimal policy. The policy is trained over a large number of robots in rich,complex environments simultaneously using a policy gradient based reinforcementlearning algorithm. The learning algorithm is also integrated into a hybridcontrol framework to further improve the policy's robustness and effectiveness.  We validate the learned sensor-level collision avoidance policy in a varietyof simulated and real-world scenarios with thorough performance evaluations forlarge-scale multi-robot systems. The generalization of the learned policy isverified in a set of unseen scenarios including the navigation of a group ofheterogeneous robots and a large-scale scenario with 100 robots. Although thepolicy is trained using simulation data only, we have successfully deployed iton physical robots with shapes and dynamics characteristics that are differentfrom the simulated agents, in order to demonstrate the controller's robustnessagainst the sim-to-real modeling error. Finally, we show that thecollision-avoidance policy learned from multi-robot navigation tasks providesan excellent solution to the safe and effective autonomous navigation for asingle robot working in a dense real human crowd. Our learned policy enables arobot to make effective progress in a crowd without getting stuck. Videos areavailable at https://sites.google.com/view/hybridmrca

Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios