# CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning

arXiv: https://arxiv.org/abs/2609.16724 · HTML: https://mlsanity.com/paper/2609.16724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)

## Builds on (most cited first, 4 of 4)

- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025)
- [UniFuture: A 4D Driving World Model for Future Generation and Perception](https://mlsanity.com/paper/2503.13587/) (2025)
- [RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification](https://mlsanity.com/paper/2608.21414/) (2026)

## Abstract (arXiv)

Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose different risks to different ego trajectories. We present CorrRisk-WM, a planning-oriented partial world model coupling environment evolution with supervised intrusion and near-miss prediction over bounded candidate-trajectory corridors. A latent environment model recursively predicts agent states and updates agent-agent and agent-map interactions. Each candidate queries the evolving environment through footprint- aware geometry and learned agent-corridor representations. A lightweight recurrent risk module uses temporal context to estimate per-slice hazards; survival aggregation yields first-entry and horizon-level event probabilities. On 29,176 scenarios from 100 Waymo validation shards, CorrRisk-WM achieves intrusion average precision (AP) of 0.8567 and 1-m near-miss first-entry AP of 0.8671. In baseline comparisons, it attains the highest near-miss AP at all three distance thresholds and the lowest observed open-loop collision rate (4.88%), with route progress of 15.35 m. Across three seeds, removing dynamic environment modeling or candidate-conditioned geometric interaction reduces mean intrusion AP from 0.8590 to 0.7624 and 0.7252, respectively. These results support coupling environment evolution with candidate-conditioned geometric reasoning for risk prediction and safety-oriented candidate selection.