Safety-Critical Traffic Simulation with Adversarial Transfer of Driving Intentions

2025-03-07

AI Summary

Evaluating and generating long-tail accident scenarios for autonomous driving systems remains challenging. To address this, we propose IntSim—the first intent-motion disentangled traffic simulation framework. IntSim automatically mines and transfers adversarial driving intents from routine driving logs, formulating intent adaptation as an optimization problem that enables environment-aware intent refinement. Conditioned on these optimized intents, IntSim drives high-fidelity motion planning to synthesize safety-critical interactive scenarios. Technically, it integrates optimization-driven adversarial intent transfer, intent-conditioned deep motion modeling, and large-scale real-world data supervision. Evaluated on nuScenes and Waymo, IntSim achieves state-of-the-art performance in both open-loop and closed-loop simulation. It significantly enhances the robustness and generalization of decision-and-planning modules under high-risk scenarios, demonstrating superior capability in uncovering and stress-testing edge cases.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Adversarial Agents
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Traffic simulation, complementing real-world data with a long-tail distribution, allows for effective evaluation and enhancement of the ability of autonomous vehicles to handle accident-prone scenarios. Simulating such safety-critical scenarios is nontrivial, however, from log data that are typically regular scenarios, especially in consideration of dynamic adversarial interactions between the future motions of autonomous vehicles and surrounding traffic participants. To address it, this paper proposes an innovative and efficient strategy, termed IntSim, that explicitly decouples the driving intentions of surrounding actors from their motion planning for realistic and efficient safety-critical simulation. We formulate the adversarial transfer of driving intention as an optimization problem, facilitating extensive exploration of diverse attack behaviors and efficient solution convergence. Simultaneously, intention-conditioned motion planning benefits from powerful deep models and large-scale real-world data, permitting the simulation of realistic motion behaviors for actors. Specially, through adapting driving intentions based on environments, IntSim facilitates the flexible realization of dynamic adversarial interactions with autonomous vehicles. Finally, extensive open-loop and closed-loop experiments on real-world datasets, including nuScenes and Waymo, demonstrate that the proposed IntSim achieves state-of-the-art performance in simulating realistic safety-critical scenarios and further improves planners in handling such scenarios.

Problem

• Simulating safety-critical traffic scenarios for autonomous vehicles
• Decoupling driving intentions from motion planning for realistic simulation
• Enhancing autonomous vehicle planners with adversarial intention transfer

Innovation

• Decouples driving intentions from motion planning
• Formulates adversarial transfer as optimization problem
• Uses deep models for realistic motion simulation