SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving

• URL: http://arxiv.org/abs/2605.19524v1
• Date: Tue, 19 May 2026 08:26:43 GMT
• Title: SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
• Abstract summary: Vision-Language-Action (VLA) models are promising due to their strong reasoning capabilities.<n>We propose SafeAlign-VLA, a negative-enhanced safe alignment framework that incorporates negative data into supervised learning and reinforcement learning.<n>Experiments on NAVSIM and DeepAccident validate the proposed framework.
• Score: 5.963051368087439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end autonomous driving systems excel in common scenarios but struggle with safety-critical long-tail cases. Vision-Language-Action (VLA) models are promising due to their strong reasoning capabilities. However, most VLA-based approaches rely on positive expert demonstrations, rarely exploiting negative samples, leading to insufficient understanding of risky behaviors and safety boundaries. To address this limitation, we propose SafeAlign-VLA, a unified negative-enhanced safe alignment framework that incorporates negative data into supervised learning and reinforcement learning. First, we develop a counterfactual safety pairing paradigm to generate structured safety labels and counterfactual positive trajectories from risky scenarios via counterfactual reasoning. Then, a two-stage training strategy is adopted: negative-enhanced supervised fine-tuning for failure feedback and trajectory correction, followed by anchor-based group relative policy optimization that uses positive and negative trajectories as contrastive anchors to steer sampling and penalize high-risk behaviors via group-relative advantages. Experiments on NAVSIM and DeepAccident validate the proposed framework. SafeAlign-VLA achieves 89.1 PDMS on the NAVSIM v1 testset, improving over the baseline without negative data by 1.3%. On DeepAccident, it reduces the collision rate to 3.36%, while achieving 84.2% language accuracy and 85.8% risk prediction accuracy. These results demonstrate the effectiveness of the proposed negative-enhanced safe alignment framework for safe and robust autonomous driving.

Related papers

• Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation [13.151825012034886]
  We propose a framework that trains risk-sensitive policies through Conditional Value-at-Risk (CVaR) constrained optimization on an off-policy TD3 backbone.<n>During training, the policy is optimized under CVaR constraints on cumulative costs, promoting sensitivity to high-cost tail outcomes.<n>A key finding is that policies trained with CVaR constraints maintain larger safety margins from obstacles across evaluated states.
  arXiv  Detail & Related papers  (2026-05-13T22:53:47Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control [7.102251210849638]
  We propose a safety-oriented, consequence-aware evaluation framework tailored to Air Traffic Control (ATC) operations.<n>Our results reveal that while current LLMs achieve reasonable aggregate accuracy, their operational reliability is severely limited.<n>These findings highlight the necessity of consequence-aware evaluation protocols for the responsible deployment of AI-assisted ATC systems.
  arXiv  Detail & Related papers  (2026-05-12T08:39:54Z)
• 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)
• Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning [2.9184958249079975]
  Existing defenses offer limited protection or force a trade-off between safety and utility.<n>We introduce a training framework that adapts regularization in response to safety risk.<n>We empirically verify that harmful intent signals are predictable from pre-generation activations.
  arXiv  Detail & Related papers  (2026-02-19T16:59:54Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Learning Safe Autonomous Driving Policies Using Predictive Safety Representations [0.0]
  Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving.<n>The Safety Representations for Safer Policy Learning (SRPL) framework addresses this challenge by equipping agents with a predictive model of future violations.<n>This paper investigates whether SRPL extends to real-world autonomous driving scenarios.
  arXiv  Detail & Related papers  (2025-12-19T13:52:19Z)
• SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models [66.71948519280669]
  Multimodal Large Reasoning Models (MLRMs) demonstrate impressive crossmodal reasoning but often amplify safety risks under adversarial prompts.<n> Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models to implicit risks.<n>We propose SaFeR-VLM, which integrates four components and supports dynamic and interpretable safety decisions beyond surface-level filtering.
  arXiv  Detail & Related papers  (2025-10-08T10:39:12Z)
• Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling [74.41886258801209]
  We propose a two-stage trajectory planning framework that decouples principle alignment from behavior learning.<n>Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-23T09:22:19Z)
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning [30.037309138373754]
  Vision-language-action models (VLAs) show potential as generalist robot policies.<n>These models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans.<n>We address this by exploring an integrated safety approach (ISA), systematically modeling safety requirements, then actively eliciting diverse unsafe behaviors.
  arXiv  Detail & Related papers  (2025-03-05T13:16:55Z)
• SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior [56.10557932893919]
  We present SafetyAnalyst, a novel AI safety moderation framework.<n>Given an AI behavior, SafetyAnalyst uses chain-of-thought reasoning to analyze its potential consequences.<n>It aggregates effects into a harmfulness score using 28 fully interpretable weight parameters.
  arXiv  Detail & Related papers  (2024-10-22T03:38:37Z)
• A Counterfactual Safety Margin Perspective on the Scoring of Autonomous Vehicles' Riskiness [52.27309191283943]
  This paper presents a data-driven framework for assessing the risk of different AVs' behaviors. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision.
  arXiv  Detail & Related papers  (2023-08-02T09:48:08Z)

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.