Learning Safe-Stoppability Monitors for Humanoid Robots

• URL: http://arxiv.org/abs/2603.22703v1
• Date: Tue, 24 Mar 2026 01:51:32 GMT
• Title: Learning Safe-Stoppability Monitors for Humanoid Robots
• Abstract summary: We formalize emergency stopping for humanoids as a policy-dependent safe-stoppability problem.<n>We introduce PRISM, a simulation-driven framework that learns a neural predictor for state-level stoppability.<n>Results show that modeling safety as policy-dependent stoppability enables proactive safety monitoring and supports scalable certification of fail-safe behaviors for humanoid robots.
• Score: 11.850318870435265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emergency stop (E-stop) mechanisms are the de facto standard for robot safety. However, for humanoid robots, abruptly cutting power can itself cause catastrophic failures; instead, an emergency stop must execute a predefined fallback controller that preserves balance and drives the robot toward a minimum-risk condition. This raises a critical question: from which states can a humanoid robot safely execute such a stop? In this work, we formalize emergency stopping for humanoids as a policy-dependent safe-stoppability problem and use data-driven approaches to characterize the safe-stoppable envelope. We introduce PRISM (Proactive Refinement of Importance-sampled Stoppability Monitor), a simulation-driven framework that learns a neural predictor for state-level stoppability. PRISM iteratively refines the decision boundary using importance sampling, enabling targeted exploration of rare but safety-critical states. This targeted exploration significantly improves data efficiency while reducing false-safe predictions under a fixed simulation budget. We further demonstrate sim-to-real transfer by deploying the pretrained monitor on a real humanoid platform. Results show that modeling safety as policy-dependent stoppability enables proactive safety monitoring and supports scalable certification of fail-safe behaviors for humanoid robots.

Related papers

• ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models [5.812025441769613]
  Embodied Foundation Models (EFMs) integrate multimodal understanding, future-state reasoning, and executable robot actions.<n>To address this challenge, we propose a safety-critical data construction pipeline for human-injury prevention in EFMs.<n>We construct ROBOSHACKLES, a 10,000-clip robotic video dataset derived from real DROID observations.<n>Results show that all evaluated models produce unsafe actions in the tested safety-critical scenarios, yielding a 100% unsafe action generation rate.
  arXiv  Detail & Related papers  (2026-06-17T03:03:16Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails [12.84192844049763]
  Most AI guardrails rely on output classification based on labeled datasets and human-specified criteria.<n>We build predictive guardrails that monitor an AI system's outputs in real time and proactively correct risky outputs to safe ones.<n>Our experiments in simulated driving and e-commerce settings demonstrate that control-theoretic guardrails can reliably steer agents clear of catastrophic outcomes.
  arXiv  Detail & Related papers  (2025-10-15T16:30:57Z)
• ANNIE: Be Careful of Your Robots [48.89876809734855]
  We present the first systematic study of adversarial safety attacks on embodied AI systems.<n>We show attack success rates exceeding 50% across all safety categories.<n>Results expose a previously underexplored but highly consequential attack surface in embodied AI systems.
  arXiv  Detail & Related papers  (2025-09-03T15:00:28Z)
• Uncertainty Aware-Predictive Control Barrier Functions: Safer Human Robot Interaction through Probabilistic Motion Forecasting [13.020006323600251]
  Uncertainty-Aware Predictive Control Barrier Functions fuses probabilistic human hand motion forecasting with the formal safety guarantees of Control Barrier Functions.<n> UA-PCBFs empower collaborative robots with a deeper understanding of future human states.<n>Relative to state-of-the-art HRI architectures, UA-PCBFs show better performance in task-critical metrics.
  arXiv  Detail & Related papers  (2025-08-28T14:11:26Z)
• Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation [55.02966123945644]
  We propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms.<n>Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer.<n>These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior.
  arXiv  Detail & Related papers  (2025-04-30T13:47:25Z)
• Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis [6.267574471145217]
  Hamilton-Jacobi (H) reachability is a rigorous framework that enables robots to simultaneously detect unsafe states and generate actions.<n>We propose La Safety Filters, a latent-space reachability that operates directly on raw observation data.
  arXiv  Detail & Related papers  (2025-02-02T22:00:20Z)
• Ensuring Force Safety in Vision-Guided Robotic Manipulation via Implicit Tactile Calibration [18.183151257773886]
  This paper introduces a novel state diffusion framework termed SafeDiff.<n>It generates a prospective state sequence from the current robot state and visual context observation.<n>It incorporates real-time tactile feedback to refine the sequence.<n>In experiments, our visual-tactile model substantially mitigates the risk of harmful forces in the door opening.
  arXiv  Detail & Related papers  (2024-12-13T18:45:26Z)
• ABNet: Attention BarrierNet for Safe and Scalable Robot Learning [58.4951884593569]
  Barrier-based method is one of the dominant approaches for safe robot learning. We propose Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving.
  arXiv  Detail & Related papers  (2024-06-18T19:37:44Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)
• SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction [5.804727815849655]
  " Shielding" control scheme overrides the robot's nominal plan with a safety fallback strategy when a safety-critical event is imminent. We propose a new shielding-based planning approach that allows the robot to plan efficiently by explicitly accounting for possible future shielding events.
  arXiv  Detail & Related papers  (2021-10-02T17:01:59Z)
• SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots [112.2491765424719]
  We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal. We use model predictive control (SMPC) to calculate control inputs that satisfy robot dynamics, and consider uncertainty during obstacle avoidance with chance constraints. recurrent neural networks are used to provide a quick estimate of future state uncertainty considered in the SMPC finite-time horizon solution. A Deep Q-learning agent is employed to serve as a high-level path planner, providing the SMPC with target positions that move the robots towards a desired global goal.
  arXiv  Detail & Related papers  (2021-08-03T02:56:21Z)

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.