BITS: Bi-level Imitation for Traffic Simulation

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 devising first principle models for human-like behaviors is generally infeasible. In this work, we take a data-driven approach 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 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 with scenarios from two large-scale driving datasets and show our method 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 video results and code release, see https://bit.ly/3L9uzj3.

Authors

• Danfei Xu
• Yuxiao Chen 0008
• Boris Ivanovic
• Marco Pavone 0001

Keywords

• Roads
• Transforms
• Traffic control
• Robot sensing systems
• Data models
• Stability analysis
• Behavioral sciences
• Traffic Simulation
• High Diversity
• First-principles
• Autonomous Vehicles
• Sampling Efficiency
• Diverse Behaviors
• Real Behavior
• Road Users
• Verification And Validation
• Core Contribution
• Traffic Behavior
• Pedestrian
• Types Of Agents
• Realistic Simulation
• Spatial Network
• Short-term Goals
• Metric Learning
• Likelihood Score
• Semantic Map
• Trajectory Prediction
• Traffic Model
• Stable Simulation
• Imitation Learning
• Wasserstein Distance
• Trajectory Generation
• Ground Truth Trajectory
• Future Time Steps
• Simulated Trials
• Lower Failure Rate
• Raster Map