Overview

Robot safety concerns preventing collisions, injury, unsafe contact, and unauthorized actions while robots operate in homes, workplaces, hospitals, and shared spaces. Common approaches include control barrier functions and reachability for formal safety constraints, runtime shields and backup controllers, and safe reinforcement learning that balances task reward with risk. As vision-language-action models and other learned policies enter robot control, researchers add perception-aware filters, rule-based authorization, adversarial testing, and benchmarks that measure safety throughout execution rather than task success alone. A central challenge is achieving useful performance under uncertain dynamics and imperfect sensing: guarantees depend on assumptions, interventions can be overly conservative, and success in simulation may not predict safe real-world behavior.

Latest papers

254 papers20 papers in the last four weeks, down 55% on the four weeks before. 0.2% of all new papers.

Feb 19, 2026

Distributed Virtual Model Control for Scalable Human-Robot Collaboration in Shared Workspace

We present a decentralized, agent agnostic, and safety-aware control framework for human-robot collaboration based on Virtual Model Control (VMC). In our approach, both humans and robots are embedded in the same virtual-component-shaped workspace, where motion is the result of the interaction with virtual springs and dampers rather than explicit trajectory planning. A decentralized, force-based stall detector identifies deadlocks, which are resolved through negotiation. This reduces the probability of robots getting stuck in the block placement task from up to 61.2% to zero in our experiments. The framework scales without structural changes thanks to the distributed implementation: in experiments we demonstrate safe collaboration with up to two robots and two humans, and in simulation up to four robots, maintaining inter-agent separation at around 20 cm. Results show that the method shapes robot behavior intuitively by adjusting control parameters and achieves deadlock-free operation across team sizes in all tested scenarios.
Feb 18, 2026

Unified Perceptive Fall Safety for Humanoids

Reliable fall recovery is critical for humanoids operating in cluttered environments. Unlike quadrupeds or wheeled robots, humanoids undergo high-energy impacts, complex whole-body contact, and large viewpoint changes during falls, making recovery essential. Prior work treats fall safety as separate problems (avoidance, impact mitigation, stand-up) or learns end-to-end policies without vision, typically on flat terrain. More fundamentally, it couples pose, dynamics, and terrain into a single data space, requiring exhaustive coverage and limiting generalization. We present a unified visually grounded fall-safety approach spanning all phases of recovery. It builds on two insights: (1) human fall-recovery poses are structured and transferable across terrains via alignment, and (2) effective recovery depends on interpreting the recovery goal in relation to the surrounding terrain. We train a privileged teacher using sparse human demonstrations and simulated terrains, and distill it into a deployable student that relies on egocentric depth and proprioception. The student predicts a goal-in-context latent representing the recovery target in relation to its surroundings, guiding coordinated whole-body reactions. Experiments in simulation and on a Unitree G1 demonstrate robust zero-shot fall safety across diverse terrains. Project page: https://vigor2026.github.io/.
Feb 3, 2026

Formal Evidence Generation for Assurance Cases for Robotic Software Models

Robotics and Autonomous Systems are increasingly deployed in safety-critical domains, so that demonstrating their safety is essential. Assurance Cases (ACs) provide structured arguments supported by evidence, but generating and maintaining this evidence is labour-intensive, error-prone, and difficult to keep consistent as systems evolve. We present a model-based approach to systematically generating AC evidence by embedding formal verification into the assurance workflow. The approach addresses three challenges: systematically deriving formal assertions from natural language requirements using templates, orchestrating multiple formal verification tools to handle diverse property types, and integrating formal evidence production into the workflow. Leveraging RoboChart, a domain-specific modelling language with formal semantics, we combine model checking and theorem proving in our approach. Structured requirements are automatically transformed into formal assertions using predefined templates, and verification results are automatically integrated as evidence. Case studies demonstrate the effectiveness of our approach.
Jan 27, 2026

Reversible Simplex Supervision with Post-Action Debt Accounting for Goal-Reaching RL

Deploying reinforcement learning (RL) on multi-tonne robots calls for supervisory mechanisms that address both operational safety and progress toward task completion. However, repeated switching need not preserve task progress when a learned action increases storage before recovery takes control. We introduce reversible Simplex supervision with post-action debt accounting for a frozen finite-state policy and robust-adaptive recovery. Under exact sampled-state information and stated model and certificate conditions, we prove that recovery repayment exceeding a uniform triggering-edge debt bound guarantees finite switching and finite-sample goal entry. We formulate reachability-based certificate constructions for establishing these sufficient conditions. In 20 matched simulations, goal-entry counts are 20 with debt gating and 18 without it; the two remaining runs terminate under the supervisor's admissibility stopping rule. On an experimental 6000 kg robot, 24 asphalt and soft-terrain trials evaluate 50 ms supervision above a 1 kHz actuator stack; all eight triggered recoveries complete debt-gated re-entry. The experiments demonstrate the supervisory mechanism in the tested trials.
Dec 9, 2025

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves over 50% improvement in obstacle avoidance rate while substantially increasing the task success rate by nearly 10%. All benchmark datasets, code, and supplementary materials are publicly available at https://vlsa-aegis.github.io/.
Oct 20, 2025

HumanHalo: Safe and Efficient 3D Navigation Among Humans via Minimally Conservative MPC

Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on simplified 2D crowd navigation and fail to account for the full complexity of human body dynamics beyond root motion. We present HumanHalo, an MPC framework for 3D MAV navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel reachability-based safety formulation that constrains only the initial control input for safety while modeling its effects over the entire planning horizon, enabling safe yet efficient navigation. We validate HumanHalo in both simulated experiments using real human trajectories and in the real world, demonstrating its effectiveness across tasks ranging from goal-directed navigation to visual servoing for human tracking. While we apply our method to MAV in this work, it is generic and can be adapted to other platforms. Our results show that the method preserves safety without excessive conservatism, even under imperfect human prediction and in constrained workspaces, while remaining efficient enough for real-time onboard execution.
Oct 7, 2025

How Well Do Latent World Models Understand Partially Observable Safety Constraints?

Latent world models are a promising approach for learning state representations and dynamics directly from high-dimensional observations, enabling robot control in hard-to-model settings. However, control performance ultimately depends on the latent representation encoding the required information for the task. In this work, we study latent-space safe control problems and show how partial observability can induce control failures when safety-relevant information is not preserved in the latent state. Specifically, we identify two world model failure modes: estimation gaps, where current observations do not reveal safety-critical quantities (e.g., temperature in a cooking task), and prediction gaps, where failures are observable once they occur but cannot be reliably anticipated from available observations. We introduce two diagnostics for these gaps: a mutual-information-based measure of safety observability and a rollout-based measure of future safety predictability. Finally, we present mitigation strategies for each failure mode: privileged multimodal supervision for estimation gaps and conformal risk calibration for prediction gaps. Across two hardware case studies -- using unimodal RGB world models and multimodal RGB+Tactile and RGB+Thermal variants -- we show that these mitigation strategies improve the safety of a Franka Research 3 manipulator on challenging cooking tasks under partial observability, albeit with increased conservativeness. More broadly, our work raises the question of when world model state representations are sufficient for reliable robot control
Sep 27, 2025

GUARD: Sensitivity-aware Uncertainty Attribution for Safe Traditional and Learning-based Robot Control

This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines a technique from probabilistic state estimation with an uncertainty identification method to derive critical thresholds for robot control algorithms. The first part focuses on complementing a method for probabilistic kernel optimization (PKO) by a sensitivity-aware uncertainty attribution technique. Next, the estimated uncertainties and their sources are forwarded to the robot controllers to adapt safety margins and trigger the initialization of safe backup trajectories. To validate GUARD's applicability and performance, experiments are conducted on a traditional model predictive control (MPC) algorithm and a reinforcement learning (RL) based controller. The results demonstrate that GUARD reduces collision rates by 44-67% in the RL-based evaluation, while decreasing backup policy activation by 50-75% in the medium- and high-uncertainty profiles. In the MPC simulation, GUARD successfully avoids collisions. By unifying the probabilistic kernel optimization algorithm from robot state estimation with the uncertainty estimation method for learning-based control, GUARD brings together traditional techniques and learning for safe and efficient robot applications.
Jul 21, 2025

The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents

Ensuring reliable and rule-compliant behavior of autonomous agents in uncertain environments remains a fundamental challenge in modern robotics. Our work shows how neuro-symbolic systems, which integrate probabilistic, symbolic white-box reasoning models with deep learning methods, offer a powerful solution to this challenge. They enable the simultaneous consideration of explicit rules and neural models trained on noisy data, combining the strengths of structured reasoning with flexible representations. To this end, we introduce the Constitutional Controller (CoCo), a novel framework designed to enhance the safety and reliability of agents by reasoning over deep probabilistic logic programs that represent constraints, such as those found in shared traffic spaces. Furthermore, we propose the concept of self-doubt, implemented as a probability density conditioned on doubt features such as travel velocity, employed sensors, or health factors. In a real-world aerial mobility study, we demonstrate CoCo's advantages for intelligent autonomous systems to learn appropriate doubts and navigate complex, uncertain environments safely and compliantly.
Jun 2, 2025

Captivity-Escape Games as a Means for Safety in Online Motion Generation

This paper addresses conservatism, limited numerical accuracy, and high computational effort in existing methods ensuring safety by design in online model-based motion generation. The presented method employs a novel captivity-escape zero-sum differential game to adapt the planning model's performance so that resulting reference trajectories are trackable within a prescribed safety margin by a jointly synthesized safety controller. A numerical example demonstrates orders-of-magnitude faster computation and improved numerical accuracy compared to the state of the art.
May 16, 2025

SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics

Robot learning has produced remarkably effective ``black-box'' controllers for complex tasks such as dynamic locomotion on humanoids. Yet ensuring dynamic safety, i.e., constraint satisfaction, remains challenging for such policies. Reinforcement learning (RL) embeds constraints heuristically through reward engineering, and adding or modifying constraints requires retraining. Model-based approaches, like control barrier functions (CBFs), enable runtime constraint specification with formal guarantees but require accurate dynamics models. This paper presents SHIELD, a layered safety framework that bridges this gap by: (1) training a generative, stochastic dynamics residual model using real-world data from hardware rollouts of the nominal controller, capturing system behavior and uncertainties; and (2) adding a safety layer on top of the nominal (learned locomotion) controller that leverages this model via a stochastic discrete-time CBF formulation enforcing safety constraints in probability. The result is a minimally-invasive safety layer that can be added to the existing autonomy stack to give probabilistic guarantees of safety that balance risk and performance. In hardware experiments on an Unitree G1 humanoid, SHIELD enables safe navigation (obstacle avoidance) through varied indoor and outdoor environments using a nominal (unknown) RL controller and onboard perception.
Mar 1, 2025

Passivity-Centric Safe Reinforcement Learning for Contact-Rich Robotic Tasks

Reinforcement learning (RL) has achieved remarkable success in various robotic tasks; however, its deployment in real-world scenarios, particularly in contact-rich environments, often overlooks critical safety and stability aspects. Policies without passivity guarantees can result in system instability, posing risks to robots, their environments, and human operators. In this work, we investigate the limitations of traditional RL policies when deployed in contact-rich tasks and explore the combination of energy-based passive control with safe RL in both training and deployment to answer these challenges. Firstly, we reveal the discovery that standard RL policy does not satisfy stability in contact-rich scenarios. Secondly, we introduce a passivity-aware RL policy training with energy-based constraints in our safe RL formulation. Lastly, a passivity filter is exerted on the policy output for passivity-ensured control during deployment. We conduct comparative studies on a contact-rich robotic maze exploration task, evaluating the effects of learning passivity-aware policies and the importance of passivity-ensured control. The experiments demonstrate that a passivity-agnostic RL policy easily violates energy constraints in deployment, even though it achieves high task completion in training. The results show that our proposed approach guarantees control stability through passivity filtering and improves the energy efficiency through passivity-aware training. A video of real-world experiments is available as supplementary material. We also release the checkpoint model and offline data for pre-training at Hugging Face.
Dec 21, 2024

Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots

LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), and open_gripper(). Jailbreak attacks on these robots extend the threat from generating malicious content to executing harmful behaviors. However, we find that existing jailbreak attempts against LLM-based robots that produce malicious-looking policies (intent jailbreaks) often fail to induce harmful physical actions by robots (behavior jailbreaks), due to robot-specific constraints, such as logical errors and hallucinated control APIs. In this paper, we demystify the intent-behavior gap and investigate its root causes to inform effective defenses. Our measurement study finds that current LLM jailbreak methods overlook robot-specific syntax constraints (e.g., executable control APIs) and physical feasibility (e.g., ordering of policies and hardware/kinematic constraints). To bridge the gap, we introduce POEF (POlicy EFfective Jailbreak), an automated red-teaming framework that takes into account the robot-specific constraints during both the optimization and evaluation processes. Specifically, POEF employs the hidden-layer gradients from an unaligned LLM to guide the jailbreak prompt optimization and uses a multi-agent evaluator to assess the feasibility of the generated policies. Experiments on commercial robots, including the Unitree G1, the Franka robotic arm, and simulators, show that POEF achieves an 80% behavior jailbreak success rate and transfers across various LLMs. In addition, we propose two defense strategies that mitigate the behavior jailbreak risks. Our findings indicate an urgent need for stronger countermeasures before LLM-based robots are deployed at scale. The homepage is available at https://zjushine.github.io/poef.github.io/.
Sep 30, 2024

Adaptive Collision Sensitivity for Efficient and Safe Human-Robot Collaboration

What is considered safe for a robot operator during physical human-robot collaboration (HRC) is specified in corresponding HRC standards (e.g., ISO 10218-2:2025). The regime that allows collisions between the moving robot and the operator, called Power and Force Limiting (PFL), restricts the permissible contact forces. Using the same fixed contact thresholds on the entire robot surface results unnecessary productivity losses, as the robot needs to stop even when impact forces are within limits. Here we present a framework that decides whether the robot should interrupt motion based on estimated collision force computed individually for different parts of the robot body and dynamically on the fly, based on the Effective Mass (EM) of each robot link. We performed experiments on a simulated and real collaborative robot arm (UR10e) with sensitive skin (AIRSKIN) for collision detection and isolation. To demonstrate the generality of our method, we added experiments on simulated KUKA LBR iiwa robot, where collision sensing draws on joint torque sensing. On a mock pick-and-place scenario with both transient and quasi-static collisions, we show an increase in productivity over 45% from using the standard approach. The method is applicable to any robot for which the EF can be calculated.