Towards provable probabilistic safety for scalable embodied AI systems

• URL: http://arxiv.org/abs/2506.05171v1
• Date: Thu, 05 Jun 2025 15:46:25 GMT
• Title: Towards provable probabilistic safety for scalable embodied AI systems
• Authors: Linxuan He, Qing-Shan Jia, Ang Li, Hongyan Sang, Ling Wang, Jiwen Lu, Tao Zhang, Jie Zhou, Yi Zhang, Yisen Wang, Peng Wei, Zhongyuan Wang, Henry X. Liu, Shuo Feng,
• Abstract summary: Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>We introduce provable probabilistic safety, which aims to ensure that the residual risk of large-scale deployment remains below a predefined threshold.
• Score: 79.31011047593492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge, which severely hinders their large-scale deployment in safety-critical domains, such as autonomous vehicles, medical devices, and robotics. While achieving provable deterministic safety--verifying system safety across all possible scenarios--remains theoretically ideal, the rarity and complexity of corner cases make this approach impractical for scalable embodied AI systems. To address this challenge, we introduce provable probabilistic safety, which aims to ensure that the residual risk of large-scale deployment remains below a predefined threshold. Instead of attempting exhaustive safety proof across all corner cases, this paradigm establishes a probabilistic safety boundary on overall system performance, leveraging statistical methods to enhance feasibility and scalability. A well-defined probabilistic safety boundary enables embodied AI systems to be deployed at scale while allowing for continuous refinement of safety guarantees. Our work focuses on three core questions: what is provable probabilistic safety, how to prove the probabilistic safety, and how to achieve the provable probabilistic safety. By bridging the gap between theoretical safety assurance and practical deployment, our work offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.

Related papers

• Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures [7.0540936204654]
  We introduce an uncertainty-aware latent safety filter that proactively steers robots away from both known and unseen failures.<n>We show that our uncertainty-aware safety filter preemptively detects potential unsafe scenarios and reliably proposes safe, in-distribution actions.
  arXiv  Detail & Related papers  (2025-05-01T18:18:17Z)
• A Domain-Agnostic Scalable AI Safety Ensuring Framework [8.086635708001166]
  We propose a novel framework that guarantees AI systems satisfy user-defined safety constraints with specified probabilities.<n>Our approach combines any AI model with an optimization problem that ensures outputs meet safety requirements while maintaining performance.<n>We prove our method guarantees probabilistic safety under mild conditions and establish the first scaling law in AI safety.
  arXiv  Detail & Related papers  (2025-04-29T16:38:35Z)
• Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systems [0.0]
  AI has emerged as a key technology, driving advancements across a range of applications.<n>The challenge of assuring safety in systems that incorporate AI components is substantial.<n>We propose a novel methodology designed to support the creation of safety assurance cases for AI-based systems.
  arXiv  Detail & Related papers  (2024-12-18T16:38:16Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)
• Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model [73.8765529028288]
  We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment.<n>To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations.<n>Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-21T16:14:15Z)
• Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
  We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
  arXiv  Detail & Related papers  (2024-05-10T17:38:32Z)
• Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
  We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
  arXiv  Detail & Related papers  (2022-09-29T20:49:25Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• Safe AI -- How is this Possible? [0.45687771576879593]
  Traditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems acting in largely unpredictable operating contexts. We outline some of underlying challenges of safe AI and suggest a rigorous engineering framework for minimizing uncertainty, thereby increasing confidence, up to tolerable levels, in the safe behavior of AI systems.
  arXiv  Detail & Related papers  (2022-01-25T16:32:35Z)
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach [2.741266294612776]
  We propose a model-free safety specification method that learns the maximal probability of safe operation. Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage. It yields a sequence of safe policies that determine the range of safe operation, called the safe set.
  arXiv  Detail & Related papers  (2020-02-24T09:20:03Z)

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.