D2CoPlan: A Differentiable Decentralized Planner for Multi-Robot Coverage

摘要

Centralized approaches for multi-robot coverage planning problems suffer from the lack of scalability. Learning-based distributed algorithms provide a scalable avenue in addition to bringing data-oriented feature generation capabilities to the table, allowing integration with other learning-based approaches. To this end, we present a learning-based, differentiable distributed coverage planner (D2CoP <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LAN</inf> ) which scales efficiently in runtime and number of agents compared to the expert algorithm, and performs on par with the classical distributed algorithm. In addition, we show that D2CoP <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LAN</inf> can be seamlessly combined with other learning methods to learn end-to-end, resulting in a better solution than the individually trained modules, opening doors to further research for tasks that remain elusive with classical methods.