Comparison of Market-based and DQN methods for Multi-Robot processing Task Allocation (MRpTA)

Paul Gautier (1) , Laurent D. Johann (1) , Jean-Philippe Diguet (1)

1 Lab-STICC_UBS_CACS_MOCS

Multi-robot task allocation (MRTA) problems require that robots take complex choices based on their understanding of a dynamic and uncertain environment. As a distributed computing system, the Multi-Robot System (MRS) must handle and distribute processing tasks (MRpTA). Each robot must contribute to the overall efficiency of the system based solely on a limited knowledge of its environment. Market-based methods are a natural candidate to deal processing tasks over a MRS but recent and numerous developments in reinforcement learning and especially Deep Q-Networks (DQN) provide new opportunities to solve the problem. In this paper we propose a new DQN-based method so that robots can learn directly from experience, and compare it with Market-based approaches as well with centralized and purely local solutions. Our study shows the relevancy of learning-based methods and also highlight research challenges to solve the processing load-balancing problem in MRS.

Mots clés: Index Terms-Multi-robot tasks allocation; distributed system; reinforcement learning; deep Q-learning

Domaines: Calcul parallèle, distribué et partagé [cs.DC]

Paul Gautier, Laurent D. Johann, Jean-Philippe Diguet. Comparison of Market-based and DQN methods for Multi-Robot processing Task Allocation (MRpTA). IEEE International Conference on Robotic Computing (IRC), Nov 2020, Taichung, Taiwan. ⟨hal-02510990⟩