Learning a Unified Risk Map for Autonomous Driving in Partially Observable Environments
- 19 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4457-4464
Abstract
Occlusion-aware prediction remains a critical challenge in autonomous driving due to the inherent uncertainty of unobserved regions. Existing approaches either overestimate risk based on reachable states or struggle to predict accurate trajectories under high occlusion uncertainty. To address these limitations, we propose a unified risk map modeling and learning framework for partially observable environments. Our method integrates traffic flow risk and collision risk through spatiotemporal modeling, enabling fine-grained assessment of occlusion-induced hazards. To address the scarcity of scenarios involving occluded interactions, we introduce a diffusion-based scenario generation framework that produces realistic yet adversarial scenarios. We integrate the modeling and learning of a unified risk map into a framework that supports risk-aware planning under partial observability. Experiments on the Waymo Open Motion Dataset show that our method significantly outperforms the state-of-the-art occlusion-aware baseline, improving minimum time-to-collision by 0.78 times and average time-to-collision by 1.67 times. The proposed framework offers a comprehensive and practical solution for risk-aware planning in partially observable environments.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62403142)
- Science and Technology Commission of Shanghai Municipality (24511103100)
This publication has 30 references indexed in Scilit:
- Query-Centric Trajectory Prediction2023
- MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion2023
- AdvDO: Realistic Adversarial Attacks for Trajectory Prediction2022
- KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients2022
- Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior2022
- Multi-Agent Variational Occlusion Inference Using People as Sensors2022
- Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation2022
- Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset2021
- Risk Assessment and Planning with Bidirectional Reachability for Autonomous Driving2020
- Congested traffic states in empirical observations and microscopic simulationsPhysical Review E, 2000