Probability Collectives Algorithm applied to Decentralized Intersection Coordination for Connected Autonomous Vehicles

Charles Philippe (1) , Lounis Adouane (1) , Antonios Tsourdos (2) , Hyo-Sang Shin (2) , Benoit Thuilot (1)

1 IP - Institut Pascal
2 Cranfield University

In this paper, a multi-agent probabilistic optimization algorithm is applied to the problem of multi-vehicle coordination. The algorithm is known as "Probability Collectives" (PC) and has roots in Game Theory and Optimization theory. It is traditionally used for finding optimal solutions of NPhard problems such as the travelling salesman problem. On the other end, the proposed PC formulation presented in this paper focuses on a minimal complexity implementation for solving the coordination problem in a time of the order of magnitude of 0.1. Besides time constraints, the emphasis in the design is put on ensuring that the algorithm always comes up with a feasible solution. Simulations show that both objectives are reached while having a decentralized algorithm, and flexible with respect to the type of situations it can deal with. Additional benefits of the PC algorithm include robustness to agent failure and the possibility to accommodate non-collaborative vehicles (market penetration of autonomous vehicles < 100%).

Mots clés: multi-robot systems; probability; travelling salesman problems; computational complexity; mobile robots

Domaines: Automatique; Robotique [cs.RO]; Automatique / Robotique

Charles Philippe, Lounis Adouane, Antonios Tsourdos, Hyo-Sang Shin, Benoit Thuilot. Probability Collectives Algorithm applied to Decentralized Intersection Coordination for Connected Autonomous Vehicles. 2019 IEEE Intelligent Vehicles Symposium (IV), Jun 2019, Paris, France. pp.1928-1934, ⟨10.1109/IVS.2019.8813827⟩. ⟨hal-03620798⟩