Learning Realistic Traffic Agents in Closed-loop

Chris Zhang, James Tu, Lunjun Zhang, Kelvin Wong, Simon Suo, Raquel Urtasun

Keywords: Traffic simulation, Imitation learning, Reinforcement learning

TL;DR: We learn realistic traffic simulation agents in closed-loop using a joint IL + RL approach that exploits nominal offline-collected data and simulated long-tail scenarios.

Abstract: Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is used to learn human-like traffic agents directly from real-world observations collected offline, but without explicit specification of traffic rules, agents trained from IL alone frequently display unrealistic infractions like collisions and driving off the road. This problem is exacerbated in out-of-distribution and long-tail scenarios. On the other hand, reinforcement learning (RL) can train traffic agents to avoid infractions, but using RL alone results in unhuman-like driving behaviors. We propose Reinforcing Traffic Rules (RTR), a holistic closed-loop learning objective to match expert demonstrations under a traffic compliance constraint, which naturally gives rise to a joint IL + RL approach, obtaining the best of both worlds. Our method learns in closed-loop simulations of both nominal scenarios from real-world datasets as well as procedurally generated long-tail scenarios. Our experiments show that RTR learns more realistic and generalizable traffic simulation policies, achieving significantly better tradeoffs between human-like driving and traffic compliance in both nominal and long-tail scenarios. Moreover, when used as a data generation tool for training prediction models, our learned traffic policy leads to considerably improved downstream prediction metrics compared to baseline traffic agents.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)