RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation

• URL: http://arxiv.org/abs/2603.27165v1
• Date: Sat, 28 Mar 2026 07:04:16 GMT
• Title: RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation
• Abstract summary: Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts.<n>Existing methods rely on binary supervision with manually annotated "anomaly onset" frames.<n>We propose RiskProp, a novel collision-anchored self-supervised risk propagation paradigm for early accident anticipation.
• Score: 16.390547433087185
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts. Existing methods rely on binary supervision with manually annotated "anomaly onset" frames, which are subjective and inconsistent, leading to inaccurate risk estimation. In contrast, we propose RiskProp, a novel collision-anchored self-supervised risk propagation paradigm for early accident anticipation, which removes the need for anomaly onset annotations and leverages only the reliably annotated collision frame. RiskProp models temporal risk evolution through two observation-driven losses: first, since future frames contain more definitive evidence of an impending accident, we introduce a future-frame regularization loss that uses the model's next-frame prediction as a soft target to supervise the current frame, enabling backward propagation of risk signals; second, inspired by the empirical trend of rising risk before accidents, we design an adaptive monotonic constraint to encourage a non-decreasing progression over time. Experiments on CAP and Nexar demonstrate that RiskProp achieves state-of-the-art performance and produces smoother, more discriminative risk curves, improving both early anticipation and interpretability.

Related papers

• Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions [13.366980144986707]
  We propose Recast, a safety risk forecasting framework for large language models (LLMs)<n>Recast predicts 88.3% of future safety failures with an average lead time of 2.41 turns, while maintaining a false alarm rate of 12.3%.
  arXiv  Detail & Related papers  (2026-07-29T12:14:23Z)
• CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation [4.201387349435027]
  We propose CARA (Concept-Aware Attention Attention), an intrinsically interpretable dynamic framework for collision anticipation.<n>By treating semantic risk factors as dynamic intermediate evidence rather than auxiliary post-hoc explanations, CARA couples interpretability with the process.
  arXiv  Detail & Related papers  (2026-07-24T17:06:05Z)
• Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving [51.726472686971896]
  End-to-end autonomous driving models generate future trajectories from multi-view inputs.<n> Existing methods fail to reveal the visual evidence underlying trajectory generation.<n>We propose a hierarchical attribution framework for end-to-end planning.
  arXiv  Detail & Related papers  (2026-05-07T13:38:18Z)
• Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving [82.69496624372944]
  "Only driving like the expert" suffers from limited generalization.<n>Can an E2E-AD system make reliable decisions without any expert action supervision?<n>We propose a unified framework named Risk-aware World Model Predictive Control.
  arXiv  Detail & Related papers  (2026-02-26T17:32:30Z)
• Uncertainty-aware Generative Recommendation [52.0751022792023]
  Uncertainty-aware Generative Recommendation (UGR) is a unified framework that leverages uncertainty as a critical signal for adaptive optimization.<n>UGR not only yields superior recommendation performance but also fundamentally stabilizes training, preventing the performance degradation often observed in standard methods.
  arXiv  Detail & Related papers  (2026-02-12T08:48:51Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• Accident Anticipation via Temporal Occurrence Prediction [15.813749445439292]
  Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety.<n>Existing methods typically predict frame-level risk scores as indicators of hazard.<n>We propose a novel paradigm that shifts the prediction target from current-frame risk scoring to directly estimating accident scores at multiple future time steps.
  arXiv  Detail & Related papers  (2025-10-25T11:57:22Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• STRAP: Spatial-Temporal Risk-Attentive Vehicle Trajectory Prediction for Autonomous Driving [0.968535561940627]
  We propose a novel spatial-temporal risk-attentive trajectory prediction framework that incorporates a risk potential field.<n>The proposed framework provides interpretable, risk-aware predictions, contributing to more robust decision-making for autonomous driving systems.
  arXiv  Detail & Related papers  (2025-07-11T13:05:35Z)
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction [6.570852598591727]
  We introduce the Stemporal Zero-Inflated Tweedie Graph Neural Network STZITZTDGNN -- the first uncertainty-aware graph deep learning model in road traffic accident prediction for multisteps. Our study demonstrates that STIDGNN can effectively inform targeted road monitoring, thereby improving urban road safety strategies.
  arXiv  Detail & Related papers  (2023-09-10T16:35:47Z)
• AdvDO: Realistic Adversarial Attacks for Trajectory Prediction [87.96767885419423]
  Trajectory prediction is essential for autonomous vehicles to plan correct and safe driving behaviors. We devise an optimization-based adversarial attack framework to generate realistic adversarial trajectories. Our attack can lead an AV to drive off road or collide into other vehicles in simulation.
  arXiv  Detail & Related papers  (2022-09-19T03:34:59Z)
• Mitigating multiple descents: A model-agnostic framework for risk monotonization [84.6382406922369]
  We develop a general framework for risk monotonization based on cross-validation. We propose two data-driven methodologies, namely zero- and one-step, that are akin to bagging and boosting.
  arXiv  Detail & Related papers  (2022-05-25T17:41:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.