Reinforcement Learning and Distributed Model Predictive Control for Conflict Resolution in Highly Constrained Spaces

TL;DR

This paper introduces a novel distributed approach combining reinforcement learning and model predictive control to resolve multi-vehicle conflicts in constrained spaces efficiently and safely.

Contribution

It presents a new distributed algorithm that integrates multi-agent reinforcement learning with MPC for conflict resolution in multi-vehicle systems.

Findings

The combined RL and MPC approach effectively resolves conflicts safely.

The method is less computationally demanding than centralized solutions.

Preliminary results show promising safety and efficiency improvements.

Abstract

This work presents a distributed algorithm for resolving cooperative multi-vehicle conflicts in highly constrained spaces. By formulating the conflict resolution problem as a Multi-Agent Reinforcement Learning (RL) problem, we can train a policy offline to drive the vehicles towards their destinations safely and efficiently in a simplified discrete environment. During the online execution, each vehicle first simulates the interaction among vehicles with the trained policy to obtain its strategy, which is used to guide the computation of a reference trajectory. A distributed Model Predictive Controller (MPC) is then proposed to track the reference while avoiding collisions. The preliminary results show that the combination of RL and distributed MPC has the potential to guide vehicles to resolve conflicts safely and smoothly while being less computationally demanding than the centralized approach.