C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving

• URL: http://arxiv.org/abs/2605.10744v1
• Date: Mon, 11 May 2026 15:45:00 GMT
• Title: C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
• Abstract summary: We propose a counterfactual chain-of-thought (C-CoT) framework to decompose driving decisions into five sequential stages.<n>Within the counterfactual reasoning stage, we introduce a structured meta-action evaluation tree to explicitly assess the potential consequences of alternative action combinations.<n>This self-reflective reasoning establishes causal links between action choices and safety outcomes, improving robustness in long-tail and out-of-distribution scenarios.
• Score: 5.963051368087439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to capture complex scene semantics, infer potential risks, and make reliable decisions in rare, high-risk situations. While vision-language models (VLMs) offer promising approaches for safe decision-making in these environments, most current approaches lack reflective and causal reasoning, thereby limiting their overall robustness. To address this, we propose a counterfactual chain-of-thought (C-CoT) framework that leverages VLMs to decompose driving decisions into five sequential stages: scene description, critical object identification, risk prediction, counterfactual risk reasoning, and final action planning. Within the counterfactual reasoning stage, we introduce a structured meta-action evaluation tree to explicitly assess the potential consequences of alternative action combinations. This self-reflective reasoning establishes causal links between action choices and safety outcomes, improving robustness in long-tail and out-of-distribution scenarios. To validate our approach, we construct the DeepAccident-CCoT dataset based on the DeepAccident benchmark and fine-tune a Qwen2.5-VL (7B) model using low-rank adaptation. Our model achieves a risk prediction recall of 81.9%, reduces the collision rate to 3.52%, and lowers L2 error to 1.98 m. Ablation studies further confirm the critical role of counterfactual reasoning and the meta-action evaluation tree in enhancing safety and interpretability.

Related papers

• Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving [46.91409391705346]
  Complex, dynamic, and interactive driving environments pose significant challenges for autonomous driving.<n>A fundamental bottleneck in current systems is the disconnect between highly expressive uncertainty modeling and interpretable, safe motion planning.<n>We propose a novel sample-conditioned differentiable planning framework that bridges this gap by explicitly incorporating diffusion-generated future trajectories into the optimization process.
  arXiv  Detail & Related papers  (2026-06-02T08:10:02Z)
• Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability [79.08785366532287]
  We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
  arXiv  Detail & Related papers  (2026-05-14T01:23:09Z)
• Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance [3.7098231493739764]
  This paper presents a scenario-centric framework for reproducible auditing of risk reasoning in urban driving contexts.<n>Findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.
  arXiv  Detail & Related papers  (2026-03-29T06:20:08Z)
• OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences [64.01706941950489]
  Current safety paradigms primarily target malicious intent or situational violations.<n>We propose shifting the safety frontier toward consequence-driven safety, a paradigm essential for the robust deployment of autonomous and embodied agents.<n>We develop the Consequence-Aware Safety Policy Optimization (CASPO) framework, which integrates the model's intrinsic reasoning as a dynamic reference for token-level self-distillation rewards.
  arXiv  Detail & Related papers  (2026-03-10T14:16:43Z)
• Multimodal Belief-Space Covariance Steering with Active Probing and Influence for Interactive Driving [14.159772216001954]
  We introduce a hierarchical belief model that structures human behavior across coarse discrete intents and fine motion modes.<n>We develop an active probing strategy that identifies when multimodal ambiguity in human predictions may compromise safety.<n>Finally, a runtime risk-evaluation layer based on Conditional Value-at-Risk ensures that all probing actions remain within human risk tolerance during influence.
  arXiv  Detail & Related papers  (2026-02-16T08:04:16Z)
• SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models [60.8821834954637]
  We present SafeRBench, the first benchmark that assesses LRM safety end-to-end.<n>We pioneer the incorporation of risk categories and levels into input design.<n>We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units.
  arXiv  Detail & Related papers  (2025-11-19T06:46:33Z)
• AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models [6.059681491089391]
  AURA provides comprehensive, step level evaluations across logical coherence and safety-awareness.<n>Our framework seamlessly combines introspective self-critique, fine-grained PRM assessments, and adaptive safety-aware decoding.<n>This research represents a pivotal step toward safer, more responsible, and contextually aware AI, setting a new benchmark for alignment-sensitive applications.
  arXiv  Detail & Related papers  (2025-08-08T08:43:24Z)
• RiskNet: Interaction-Aware Risk Forecasting for Autonomous Driving in Long-Tail Scenarios [6.024186631622774]
  RiskNet is an interaction-aware risk forecasting framework for autonomous vehicles.<n>It integrates deterministic risk modeling with probabilistic behavior prediction for comprehensive risk assessment.<n>It supports real-time, scenario-adaptive risk forecasting and demonstrates strong generalization across uncertain driving environments.
  arXiv  Detail & Related papers  (2025-04-22T02:36:54Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems.<n>We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics.<n>We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• Making Large Language Models Better Planners with Reasoning-Decision Alignment [70.5381163219608]
  We motivate an end-to-end decision-making model based on multimodality-augmented LLM. We propose a reasoning-decision alignment constraint between the paired CoTs and planning results. We dub our proposed large language planners with reasoning-decision alignment as RDA-Driver.
  arXiv  Detail & Related papers  (2024-08-25T16:43:47Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)

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.