SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning

• URL: http://arxiv.org/abs/2503.03480v1
• Date: Wed, 05 Mar 2025 13:16:55 GMT
• Title: SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning
• Authors: Borong Zhang, Yuhao Zhang, Jiaming Ji, Yingshan Lei, Josef Dai, Yuanpei Chen, Yaodong Yang,
• Abstract summary: We propose SafeVLA, a novel algorithm designed to integrate safety into vision-language--action models (VLAs)<n>SafeVLA balances safety and task performance by employing large-scale constrained learning within simulated environments.<n>We demonstrate that SafeVLA outperforms the current state-of-the-art method in both safety and task performance.
• Score: 10.844235123282056
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision-language-action models (VLAs) have shown great potential as generalist robot policies. However, these models pose urgent safety challenges during deployment, including the risk of physical harm to the environment, the robot itself, and humans. How can safety be explicitly incorporated into VLAs? In this work, we propose SafeVLA, a novel algorithm designed to integrate safety into VLAs, ensuring the protection of the environment, robot hardware and humans in real-world settings. SafeVLA effectively balances safety and task performance by employing large-scale constrained learning within simulated environments. We demonstrate that SafeVLA outperforms the current state-of-the-art method in both safety and task performance, achieving average improvements of 83.58% and 3.85%, respectively, in simulation. By prioritizing safety, our approach eliminates high-risk behaviors and reduces the upper bound of unsafe behaviors to 1/35 of that in the current state-of-the-art, thereby significantly mitigating long-tail risks. Furthermore, the learned safety constraints generalize to diverse, unseen scenarios, including multiple out-of-distribution perturbations and tasks. Our data, models and newly proposed benchmark environment are available at https://sites.google.com/view/pku-safevla.

Related papers

• Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing [12.986006070964772]
  Safety alignment is an essential research topic for real-world AI applications.<n>Our study first identified the difficulty of eliminating such vulnerabilities without sacrificing the model's helpfulness.<n>Our method could enhance the model's helpfulness while maintaining safety, thus improving the trade-off-front.
  arXiv  Detail & Related papers  (2025-02-04T09:31:54Z)
• Defining and Evaluating Physical Safety for Large Language Models [62.4971588282174]
  Large Language Models (LLMs) are increasingly used to control robotic systems such as drones. Their risks of causing physical threats and harm in real-world applications remain unexplored. We classify the physical safety risks of drones into four categories: (1) human-targeted threats, (2) object-targeted threats, (3) infrastructure attacks, and (4) regulatory violations.
  arXiv  Detail & Related papers  (2024-11-04T17:41:25Z)
• ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning [48.536695794883826]
  We present ActSafe, a novel model-based RL algorithm for safe and efficient exploration.<n>We show that ActSafe guarantees safety during learning while also obtaining a near-optimal policy in finite time.<n>In addition, we propose a practical variant of ActSafe that builds on latest model-based RL advancements.
  arXiv  Detail & Related papers  (2024-10-12T10:46:02Z)
• How Does Vision-Language Adaptation Impact the Safety of Vision Language Models? [27.46416187893547]
  Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) Despite potential harmfulness due to weakened safety measures, in-depth analysis on the effects of VL adaptation on safety remains under-explored.
  arXiv  Detail & Related papers  (2024-10-10T03:12:03Z)
• SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models [65.06446825020578]
  Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. We aim to measure the risks in finetuning LLMs through navigating the LLM safety landscape.
  arXiv  Detail & Related papers  (2024-05-27T17:31:56Z)
• Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis [63.532413807686524]
  This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL) We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
  arXiv  Detail & Related papers  (2023-12-18T16:09:43Z)
• Safe Deep Policy Adaptation [7.2747306035142225]
  Policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. We provide theoretical safety guarantees of SafeDPA and show the robustness of SafeDPA against learning errors and extra perturbations.
  arXiv  Detail & Related papers  (2023-10-08T00:32:59Z)
• Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements [76.80453043969209]
  This survey presents a framework for safety research pertaining to large models. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models. We explore the strategies for enhancing large model safety from training to deployment.
  arXiv  Detail & Related papers  (2023-02-18T09:32:55Z)
• ISAACS: Iterative Soft Adversarial Actor-Critic for Safety [0.9217021281095907]
  This work introduces a novel approach enabling scalable synthesis of robust safety-preserving controllers for robotic systems. A safety-seeking fallback policy is co-trained with an adversarial "disturbance" agent that aims to invoke the worst-case realization of model error. While the learned control policy does not intrinsically guarantee safety, it is used to construct a real-time safety filter.
  arXiv  Detail & Related papers  (2022-12-06T18:53:34Z)

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.