Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving

• URL: http://arxiv.org/abs/2605.06264v1
• Date: Thu, 07 May 2026 13:38:18 GMT
• Title: Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving
• Abstract summary: 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.
• Score: 51.726472686971896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and hard-to-localize risks. Existing methods either rely on auxiliary monitoring models or generate textual explanations, but are decoupled from the planning process and fail to reveal the visual evidence underlying trajectory generation. While attribution offers a direct alternative, planning differs from image classification by taking six-view camera images as input and predicting continuous multi-step trajectories, requiring attribution to capture both critical views and regions and their influence on outputs. Moreover, whether attribution maps can support risk identification remains underexplored. To address this, we propose a hierarchical attribution framework for end-to-end planning. Specifically, using L2 consistency with the original trajectory as the objective, we design a coarse-to-fine region attribution strategy that searches candidate regions across the full six-view input and refines attribution within them. We further extract three attribution statistics as predictive signals for planning risk, including attribution entropy to measure how concentrated the planner's reliance is over the joint visual space, within-camera spatial variance to characterize how spread out the attribution is within each view, and cross-camera Gini coefficient to quantify how unevenly attribution is distributed across the six cameras. Experiments on BridgeAD, UniAD, and GenAD show that these statistics correlate with planning risk, achieving Spearman correlations of $0.30 \pm 0.07$ with trajectory error and AUROC of $0.77 \pm 0.04$ for collision detection. The signal generalizes to held-out scenes with negligible degradation and remains stable under an alternative attribution baseline.

Related papers

• READ: Learning Risk-Informed Fields for End-to-End Autonomous Driving [24.54780591783853]
  We introduce READ, a framework that learns an explicit, planning-aligned risk representation from complementary geometric and behavioral constraints.<n> READ instantiates this representation as a continuoustemporal field, enabling differentiable queries along candidate trajectories.<n> Experiments on NAVSIM show consistent gains across matched end-to-end backbones and strong performance in a VLA setting.
  arXiv  Detail & Related papers  (2026-09-11T02:40:51Z)
• Orthogonal JEPA: Factorized Predictive States for Latent World Models [95.20158869896393]
  We introduce method, a latent world-modeling framework based on predictive factorization.<n>We show that method can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure.<n>Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.
  arXiv  Detail & Related papers  (2026-08-20T13:59:57Z)
• Multi-Agent Next-Best-View Optimization for Risk-Averse Planning [1.1246921651379473]
  Multi-agent Next-Best-View (NBV) selection for safe path planning in uncertain and unknown environments requires informative, safety-aware, and efficient coordination.<n>We propose a distributed, risk-aware NBV framework in which each robot maintains a private local 3D Gaussian map.<n>Experiments in Gibson environments at multiple team sizes show that the distributed formulation approaches the centralized baseline in mapping quality and trajectory safety.
  arXiv  Detail & Related papers  (2026-06-02T19:23:23Z)
• Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments [15.293238760957722]
  We propose a unified map modeling and learning framework for partially observable environments.<n>The proposed framework offers a comprehensive and practical solution for risk-aware planning in partially observable environments.
  arXiv  Detail & Related papers  (2026-05-21T08:56:38Z)
• Multi-Agent Off-World Exploration for Sparse Evidence Discovery via Gaussian Belief Mapping and Dual-Domain Coverage [15.524614683513834]
  We propose a multi-agent informative path planning framework for sparse evidence discovery based on Gaussian belief mapping and dual-domain coverage.<n> Experimental results in simulated lunar environments show that the proposed method consistently outperforms sampling-based and greedy baselines under different budgets and communication ranges.
  arXiv  Detail & Related papers  (2026-03-08T14:27:41Z)
• LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks [0.5653106385738822]
  Disruptions at critical logistics nodes pose severe risks to global supply chains.<n>This paper proposes an evidence-grounded framework that jointly performs bottleneck prediction and faithful natural-language risk explanation.
  arXiv  Detail & Related papers  (2026-03-05T05:07:40Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• The Decoupled Risk Landscape in Performative Prediction [3.904855396113132]
  Performative Prediction addresses scenarios where deploying a model induces a distribution shift in the input data.<n>We introduce a simple decoupled risk visualization method inspired in the two-step process that performative prediction is.<n>We introduce a novel setting - extended Performative Prediction - which captures scenarios where the distribution reacts to a model different from the decision-making one.
  arXiv  Detail & Related papers  (2025-06-10T17:58:39Z)
• An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks [12.08908327186123]
  We propose a Graph OOD Membership Inference Attack (GOOD-MIA) to achieve cross-domain graph attacks.<n>Specifically, we construct shadow subgraphs with distributions from different domains to model the diversity of real-world data.<n> Experimental results demonstrate that GOOD-MIA achieves superior attack performance in datasets designed for multiple domains.
  arXiv  Detail & Related papers  (2025-05-26T14:52:52Z)
• Urban Traffic Accident Risk Prediction Revisited: Regionality, Proximity, Similarity and Sparsity [18.566139471849844]
  Traffic accidents pose a significant risk to human health and property safety. To prevent traffic accidents, predicting their risks has garnered growing interest. We argue that a desired prediction solution should demonstrate resilience to the complexity of traffic accidents.
  arXiv  Detail & Related papers  (2024-07-29T03:10:15Z)
• LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference [66.45326873274908]
  We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately. Compared to MINE, our approach has an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5%.
  arXiv  Detail & Related papers  (2023-07-23T03:38:55Z)
• Handling Distribution Shifts on Graphs: An Invariance Perspective [78.31180235269035]
  We formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM) EERM resorts to multiple context explorers that are adversarially trained to maximize the variance of risks from multiple virtual environments. We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution.
  arXiv  Detail & Related papers  (2022-02-05T02:31:01Z)
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles [103.87351701138554]
  In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. We introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. We show competitive detection and attribute recognition results, as well as a more stable MTL training.
  arXiv  Detail & Related papers  (2020-12-04T15:10:12Z)

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.