CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

Luke Rowe, Roger Girgis, Anthony Gosselin, Bruno Carrez, Florian Golemo, Felix Heide, Liam Paull, Christopher Pal

Keywords: offline reinforcement learning, autonomous driving, simulation

TL;DR: We propose reactive and controllable agents in a driving simulator using offline reinforcement learning.

Abstract: Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However, agents replayed from offline data are not reactive and hard to intuitively control. Existing approaches address these challenges by proposing methods that rely on heuristics or generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through a physics-enhanced Nocturne simulator to generate a diverse offline reinforcement learning dataset, annotated with various reward terms. We then train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including adversarial behaviours. We demonstrate that CtRL-Sim can generate diverse and realistic safety-critical scenarios while providing fine-grained control over agent behaviours.

Video: https://www.youtube.com/watch?v=oH99fd_462Q

Website: https://montrealrobotics.ca/ctrlsim/

Code: https://github.com/montrealrobotics/ctrl-sim/

Student Paper: yes

Submission Number: 27