- 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 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.
- TL;DR: We develop a freeway merging algorithm based on multipolicy decision making with a reinforcement learning algorithm.
- Keywords: Autonomous vehicle, Freeway merging, Reinforcement learning