# Context-aware Risk Assessment and Its Application in Autonomous Driving

arXiv: https://arxiv.org/abs/2508.02919 · HTML: https://mlsanity.com/paper/2508.02919/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving.
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Placed in

- End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/)

## Builds on (most cited first, 6 of 6)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024)
- [On a Formal Model of Safe and Scalable Self-driving Cars](https://mlsanity.com/paper/1708.06374/) (2017)
- [Hidden Biases of End-to-End Driving Models](https://mlsanity.com/paper/2306.07957/) (2023)
- [FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling](https://mlsanity.com/paper/2306.05381/) (2023)
- [Risk-Based Safety Envelopes for Autonomous Vehicles Under Perception Uncertainty](https://mlsanity.com/paper/2107.09918/) (2021)

## Abstract (arXiv)

Ensuring safety in autonomous driving requires precise, real-time risk assessment and adaptive behavior. Prior work on risk estimation either outputs coarse, global scene-level metrics lacking interpretability, proposes indicators without concrete integration into autonomous systems, or focuses narrowly on specific driving scenarios. We introduce the Context-aware Risk Index (CRI), a light-weight modular framework that quantifies directional risks based on object kinematics and spatial relationships, dynamically adjusting control commands in real time. CRI employs direction-aware spatial partitioning within a dynamic safety envelope using Responsibility-Sensitive Safety (RSS) principles, a hybrid probabilistic-max fusion strategy for risk aggregation, and an adaptive control policy for real-time behavior modulation. We evaluate CRI on the Bench2Drive benchmark comprising 220 safety-critical scenarios using a state-of-the-art end-to-end model Transfuser++ on challenging routes. Our collision-rate metrics show a 19% reduction (p = 0.003) in vehicle collisions per failed route, a 20% reduction (p = 0.004) in collisions per kilometer, a 17% increase (p = 0.016) in composed driving score, and a statistically significant reduction in penalty scores (p = 0.013) with very low overhead (3.6 ms per decision cycle). These results demonstrate that CRI substantially improves safety and robustness in complex, risk-intensive environments while maintaining modularity and low runtime overhead.