Decentralized Cooperative Planning for Automated Vehicles with Continuous Monte Carlo Tree Search

TL;DR

This paper introduces a decentralized cooperative planning algorithm for automated vehicles using continuous Monte Carlo Tree Search, enabling implicit cooperation in complex traffic scenarios with continuous trajectories.

Contribution

It extends cooperative planning to continuous action spaces with novel MCTS enhancements, allowing automated vehicles to better cooperate in heterogeneous environments.

Findings

Effective cooperative planning achieved in various scenarios.

Outperforms egocentric planning approaches.

Handles continuous trajectories for wider applicability.

Abstract

Urban traffic scenarios often require a high degree of cooperation between traffic participants to ensure safety and efficiency. Observing the behavior of others, humans infer whether or not others are cooperating. This work aims to extend the capabilities of automated vehicles, enabling them to cooperate implicitly in heterogeneous environments. Continuous actions allow for arbitrary trajectories and hence are applicable to a much wider class of problems than existing cooperative approaches with discrete action spaces. Based on cooperative modeling of other agents, Monte Carlo Tree Search (MCTS) in conjunction with Decoupled-UCT evaluates the action-values of each agent in a cooperative and decentralized way, respecting the interdependence of actions among traffic participants. The extension to continuous action spaces is addressed by incorporating novel MCTS-specific enhancements for efficient search space exploration. The proposed algorithm is evaluated under different scenarios, showing that the algorithm is able to achieve effective cooperative planning and generate solutions egocentric planning fails to identify.