RADE: Learning Risk-Adjustable Driving Environment via Multi-Agent Conditional Diffusion
This work addresses the need for scalable and realistic simulation tools for autonomous vehicle safety evaluation, representing an incremental improvement over existing adversarial methods.
The paper tackles the problem of generating realistic and safety-critical driving scenarios for autonomous vehicle testing by proposing RADE, a multi-agent diffusion framework that conditions agent trajectories on a surrogate risk measure, resulting in statistically realistic traffic scenes with controllable risk levels validated on the rounD dataset.
Generating safety-critical scenarios in high-fidelity simulations offers a promising and cost-effective approach for efficient testing of autonomous vehicles. Existing methods typically rely on manipulating a single vehicle's trajectory through sophisticated designed objectives to induce adversarial interactions, often at the cost of realism and scalability. In this work, we propose the Risk-Adjustable Driving Environment (RADE), a simulation framework that generates statistically realistic and risk-adjustable traffic scenes. Built upon a multi-agent diffusion architecture, RADE jointly models the behavior of all agents in the environment and conditions their trajectories on a surrogate risk measure. Unlike traditional adversarial methods, RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels. To ensure physical plausibility, we incorporate a tokenized dynamics check module that efficiently filters generated trajectories using a motion vocabulary. We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels and naturally increases the likelihood of safety-critical events as the desired risk level grows up. Our results highlight RADE's potential as a scalable and realistic tool for AV safety evaluation.