BITS: Bi-level Imitation for Traffic Simulation

TL;DR

The paper introduces BITS, a data-driven bi-level imitation method for realistic, diverse, and stable traffic simulation using real-world driving logs, addressing the challenge of human-like behavior modeling.

Contribution

It proposes a novel bi-level hierarchy approach for traffic behavior imitation, combining intent inference and behavior imitation, with a planning module for long-term stability, and provides an open-source simulation tool.

Findings

Achieves high realism and diversity in traffic behaviors

Demonstrates stable long-horizon traffic simulation

Provides a new evaluation suite for traffic behavior realism

Abstract

Simulation is the key to scaling up validation and verification for robotic systems such as autonomous vehicles. Despite advances in high-fidelity physics and sensor simulation, a critical gap remains in simulating realistic behaviors of road users. This is because, unlike simulating physics and graphics, devising first principle models for human-like behaviors is generally infeasible. In this work, we take a data-driven approach and propose a method that can learn to generate traffic behaviors from real-world driving logs. The method achieves high sample efficiency and behavior diversity by exploiting the bi-level hierarchy of driving behaviors by decoupling the traffic simulation problem into high-level intent inference and low-level driving behavior imitation. The method also incorporates a planning module to obtain stable long-horizon behaviors. We empirically validate our method, named Bi-level Imitation for Traffic Simulation (BITS), with scenarios from two large-scale driving datasets and show that BITS achieves balanced traffic simulation performance in realism, diversity, and long-horizon stability. We also explore ways to evaluate behavior realism and introduce a suite of evaluation metrics for traffic simulation. Finally, as part of our core contributions, we develop and open source a software tool that unifies data formats across different driving datasets and converts scenes from existing datasets into interactive simulation environments. For additional information and videos, see https://sites.google.com/view/nvr-bits2022/home