Verifiable Foundation Models for Robot Safety

• URL: http://arxiv.org/abs/2606.23754v1
• Date: Mon, 22 Jun 2026 03:10:51 GMT
• Title: Verifiable Foundation Models for Robot Safety
• Abstract summary: We present FEARL (Foundation-Enabled Assured Robot Learning), a framework that addresses this tension through a modular architectural decomposition.<n>FEARL separates the policy into a large Controller (C) responsible for high-dimensional perception and task reasoning, and a small Safety module (S) that receives low-dimensional observations from dedicated safety sensors.<n>This makes formal analysis tractable with existing tools while preserving the Controller's expressive power for task reasoning.
• Score: 9.839166424557009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes these models opaque and difficult to analyze formally, rendering them intractable for existing verification tools. In this paper, we present FEARL (Foundation-Enabled Assured Robot Learning), a framework that addresses this tension through a modular architectural decomposition. FEARL separates the policy into a large Controller (C) responsible for high-dimensional perception and task reasoning, and a small Safety module (S) that receives low-dimensional observations from dedicated safety sensors together with a bounded context embedding from C and produces the final action. Since many robot safety requirements, such as collision avoidance and workspace boundary constraints, can be expressed over these safety sensor observations, formal verification can be applied to S rather than to the full foundation-model backbone. This makes formal analysis tractable with existing tools while preserving the Controller's expressive power for task reasoning. To show that the decomposed policy remains capable of solving diverse tasks, we evaluate FEARL on three simulated robotic domains using multiple Controller backbones and training procedures, including pretrained off-the-shelf vision-language-action models. We further transfer the learned policy from one of our simulated tasks to a physical robot, suggesting that the low-dimensional safety interface supports practical sim-to-real transfer.

Related papers

• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World [42.7330476721001]
  We argue that existing approaches, including static verification, monolithic controllers, and end-to-end learned policies, are insufficient in settings where tasks, environments, and human expectations are open-ended, long-tailed, and subject to adaptation over time.<n>We propose modular safety guardrails, consisting of monitoring (evaluation) and intervention layers, as an architectural foundation for comprehensive safety across the autonomy stack.
  arXiv  Detail & Related papers  (2026-02-03T22:41:51Z)
• Vision-based Goal-Reaching Control for Mobile Robots Using a Hierarchical Learning Framework [4.014524824655106]
  This paper decomposes the whole system into a set of tightly coupled functional modules.<n>The proposed framework guarantees uniform exponential stability of the actuation system and safety of the whole operation.
  arXiv  Detail & Related papers  (2026-01-02T08:41:47Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• Constrained Decoding for Robotics Foundation Models [12.916330118607918]
  We introduce SafeDec, a constrained decoding framework for autoregressive robot foundation models.<n>Task-specific safety rules are expressed as Signal Temporal Logic (STL) formulas and are enforced at inference time with minimal overhead.<n>Our method ensures that generated actions provably satisfy STL specifications under assumed dynamics at runtime without retraining.
  arXiv  Detail & Related papers  (2025-09-01T19:17:40Z)
• 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)
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics [68.36528819227641]
  This paper systematically evaluates the robustness of Vision-Language-Action (VLA) models.<n>We introduce two untargeted attack objectives that leverage spatial foundations to destabilize robotic actions, and a targeted attack objective that manipulates the robotic trajectory.<n>We design an adversarial patch generation approach that places a small, colorful patch within the camera's view, effectively executing the attack in both digital and physical environments.
  arXiv  Detail & Related papers  (2024-11-18T01:52:20Z)
• Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System [55.94648383147838]
  We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects. Our framework consists of five core modules: (i) an object state estimator that learns object trajectory prediction, (ii) a catching pose quality network that learns to score and rank object poses for catching, (iii) a reaching control policy trained to move the robot hand to pre-catch poses, and (iv) a grasping control policy trained to perform soft catching motions. We conduct extensive evaluations of our framework in simulation for each module and the integrated system, to demonstrate high success rates of in-flight
  arXiv  Detail & Related papers  (2023-12-21T16:20:12Z)
• Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot [19.789369416528604]
  grasp force control aims to manipulate objects safely by limiting the amount of force exerted on the object. Prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim-to-real transfer. We propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning.
  arXiv  Detail & Related papers  (2023-11-13T11:29:06Z)
• Robotic Handling of Compliant Food Objects by Robust Learning from Demonstration [79.76009817889397]
  We propose a robust learning policy based on Learning from Demonstration (LfD) for robotic grasping of food compliant objects. We present an LfD learning policy that automatically removes inconsistent demonstrations, and estimates the teacher's intended policy. The proposed approach has a vast range of potential applications in the aforementioned industry sectors.
  arXiv  Detail & Related papers  (2023-09-22T13:30:26Z)

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.