InterSim: Interactive Traffic Simulation via Explicit Relation Modeling

TL;DR

InterSim is an interactive traffic simulation framework that models agent relations to generate realistic, consistent multi-agent behaviors, improving the testing of autonomous driving systems.

Contribution

We introduce InterSim, a novel interactive traffic simulator that explicitly models agent relations to produce diverse, realistic behaviors for autonomous driving testing.

Findings

InterSim outperforms existing simulators in realism and reactivity.

It generates consistent multi-agent trajectories based on relation reasoning.

Validated on a large-scale interactive driving dataset.

Abstract

Interactive traffic simulation is crucial to autonomous driving systems by enabling testing for planners in a more scalable and safe way compared to real-world road testing. Existing approaches learn an agent model from large-scale driving data to simulate realistic traffic scenarios, yet it remains an open question to produce consistent and diverse multi-agent interactive behaviors in crowded scenes. In this work, we present InterSim, an interactive traffic simulator for testing autonomous driving planners. Given a test plan trajectory from the ego agent, InterSim reasons about the interaction relations between the agents in the scene and generates realistic trajectories for each environment agent that are consistent with the relations. We train and validate our model on a large-scale interactive driving dataset. Experiment results show that InterSim achieves better simulation realism and reactivity in two simulation tasks compared to a state-of-the-art learning-based traffic simulator.