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

02/03/2023

∙

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.

READ FULL TEXT

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

Multi-vehicle Conflict Resolution in Highly Constrained Spaces by Merging Optimal Control and Reinforcement Learning

Centralized Conflict-free Cooperation for Connected and Automated Vehicles at Intersections by Proximal Policy Optimization

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage

Training Efficient Controllers via Analytic Policy Gradient

Learning to Operate an Electric Vehicle Charging Station Considering Vehicle-grid Integration

TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing – A Reinforcement Learning Approach

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

Related Research

Multi-vehicle Conflict Resolution in Highly Constrained Spaces by Merging Optimal Control and Reinforcement Learning

Centralized Conflict-free Cooperation for Connected and Automated Vehicles at Intersections by Proximal Policy Optimization

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage

Training Efficient Controllers via Analytic Policy Gradient

Learning to Operate an Electric Vehicle Charging Station Considering Vehicle-grid Integration

TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing – A Reinforcement Learning Approach