Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic

TL;DR

This paper introduces a reinforcement learning approach called passive actor-critic for freeway merging, enabling automated vehicles to decide where and how to merge in congested traffic with high success rates.

Contribution

The paper presents a novel multi-policy decision making method using passive actor-critic reinforcement learning for freeway merging, reducing system knowledge requirements and avoiding active exploration.

Findings

Achieves 92% success rate in freeway merging tasks

Comparable to human decision-making in real traffic data

Demonstrates effectiveness of pAC in congested traffic scenarios

Abstract

Freeway merging in congested traffic is a significant challenge toward fully automated driving. Merging vehicles need to decide not only how to merge into a spot, but also where to merge. We present a method for the freeway merging based on multi-policy decision making with a reinforcement learning method called {\em passive actor-critic} (pAC), which learns with less knowledge of the system and without active exploration. The method selects a merging spot candidate by using the state value learned with pAC. We evaluate our method using real traffic data. Our experiments show that pAC achieves 92\% success rate to merge into a freeway, which is comparable to human decision making.