Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments
Summary
Proposes a unified risk map modeling framework for autonomous driving that integrates traffic flow and collision risks in partially observable environments, using spatiotemporal modeling and diffusion-based scenario generation. Outperforms state-of-the-art occlusion-aware baselines on the Waymo Open Motion Dataset.
View Cached Full Text
Cached at: 05/29/26, 07:01 AM
Paper page - Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments
Source: https://huggingface.co/papers/2605.22189
Abstract
A unified risk map modeling framework addresses occlusion challenges in autonomous driving by integrating traffic flow and collision risks through spatiotemporal modeling and diffusion-based scenario generation.
Occlusion-aware predictionremains 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 unifiedrisk map modelingand learning framework forpartially observable environments. Our method integrates traffic flow risk and collision risk throughspatiotemporal modeling, enabling fine-grained assessment of occlusion-induced hazards. To address the scarcity of scenarios involving occluded interactions, we introduce adiffusion-based scenario generationframework that produces realistic yet adversarial scenarios. We integrate the modeling and learning of a unified risk map into a framework that supportsrisk-aware planningunder 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 forrisk-aware planninginpartially observable environments.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.22189
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.22189 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.22189 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.22189 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
This paper proposes a multi-agent reinforcement learning framework that co-trains an autonomous vehicle and pedestrians with personality-driven jaywalking behavior, achieving a 30% reduction in collisions compared to single-agent approaches and demonstrating more realistic interaction scenarios.
Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving
This paper proposes an uncertainty-aware reinforcement learning framework for autonomous driving that uses expert advice guided by adaptive uncertainty thresholds and a commitment-cooldown strategy to improve safety and efficiency. Experiments in the CARLA simulator show a 5-7% success improvement over the IQN baseline.
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
This paper introduces HERMES++, a unified driving world model that integrates 3D scene understanding and future geometry prediction using BEV representation, LLM-enhanced queries, and joint geometric optimization.
ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
ScenePilot proposes a feasibility-guided, boundary-driven framework for generating safety-critical scenarios for autonomous driving, using constrained multi-objective reinforcement learning to produce physically valid yet failure-inducing scenarios.
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 presents a unified generator-discriminator framework for autonomous driving that combines diffusion-based trajectory generation with RL-optimized reranking, achieving 56% collision rate reduction compared to diffusion-based planners. The approach introduces techniques like Temporally Consistent Group Relative Policy Optimization and BEV-Warp simulation environment for efficient large-scale training.