Over the last years collaborative robots have gained great success in manufacturing applications where human and robot work together in close proximity. However, current ISO/TS-15066-compliant implementations often limit the efficiency of collaborative tasks due to conservative speed restrictions. For this reason, this paper introduces a deep-learning-based human-robot-safety framework (HRSF) that aims at a dynamical adaptation of robot velocities depending on the separation distance between human and robot while respecting maximum biomechanical force and pressure limits. The applicability of the framework was investigated for four different deep learning approaches that can be used for human body extraction: human body recognition, human body segmentation, human pose estimation, and human body part segmentation. Unlike conventional industrial safety systems, the proposed HRSF differentiates individual human body parts from other objects, enabling optimized robot process execution. Experiments demonstrated a quantitative reduction in cycle time of up to 15% compared to conventional safety technology.

The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security risks: a compromised VLA model can directly translate adversarial perturbations on sensory input into unsafe physical actions. Traditional safety definitions and methodologies from the machine learning community are no longer sufficient. EAI systems raise new questions, such as what constitutes safety, how to measure it, and how to design effective attack and defense mechanisms in physically grounded, interactive settings. In this work, we present the first systematic study of adversarial safety attacks on embodied AI systems, grounded in ISO standards for human-robot interactions. We (1) formalize a principled taxonomy of safety violations (critical, dangerous, risky) based on physical constraints such as separation distance, velocity, and collision boundaries; (2) introduce ANNIEBench, a benchmark of nine safety-critical scenarios with 2,400 video-action sequences for evaluating embodied safety; and (3) ANNIE-Attack, a task-aware adversarial framework with an attack leader model that decomposes long-horizon goals into frame-level perturbations. Our evaluation across representative EAI models shows attack success rates exceeding 50% across all safety categories. We further demonstrate sparse and adaptive attack strategies and validate the real-world impact through physical robot experiments. These results expose a previously underexplored but highly consequential attack surface in embodied AI systems, highlighting the urgent need for security-driven defenses in the physical AI era. Code is available at https://github.com/RLCLab/Annie.

A Safety-A ware Kinodynamic Architecture for Human-Robot Collaboration Andrea Pupa 1, Mohammad Arrfou 2, Gildo Andreoni 2 and Cristian Secchi 1 Abstract -- The new paradigm of human-robot collaboration has led to the creation of shared work environments in which humans and robots work in close contact with each other . Consequently, the safety regulations have been updated addressing these new scenarios. The mere application of these regulations may lead to a very inefficient behavior of the robot. In order to preserve safety for the human operators and allow the robot to reach a desired configuration in a safe and efficient way, a two layers architecture for trajectory planning and scaling is proposed. The first layer calculates the nominal trajectory and continuously adapts it based on the human behavior . The second layer, which explicitly considers the safety regulations, scales the robot velocity and requests for a new trajectory if the robot speed drops. The proposed architecture is experimentally validated on a Pilz PRBT manipulator . I. I NTRODUCTION The introduction and diffusion of collaborative robotics within the industrial environments has allowed to create shared workspace where humans and robots can work closely. While this new paradigm has led to an increase in the flexibility of production lines, the lack of physical barriers requires to pay more attention on how to guarantee human safety.

This paper addresses motion replanning in human-robot collaborative scenarios, emphasizing reactivity and safety-compliant efficiency. While existing human-aware motion planners are effective in structured environments, they often struggle with unpredictable human behavior, leading to safety measures that limit robot performance and throughput. In this study, we combine reactive path replanning and a safety-aware cost function, allowing the robot to adjust its path to changes in the human state. This solution reduces the execution time and the need for trajectory slowdowns without sacrificing safety. Simulations and real-world experiments show the method's effectiveness compared to standard human-robot cooperation approaches, with efficiency enhancements of up to 60\%.

What is considered safe for a robot operator during physical human-robot collaboration (HRC) is specified in corresponding HRC standards (e.g., the European ISO/TS 15066). 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 in significant and unnecessary productivity losses, as the robot needs to stop even when impact forces are within limits. Here we present a framework for setting the protective skin thresholds individually for different parts of the robot body and dynamically on the fly, based on the effective mass of each robot link and the link velocity. We perform experiments on a 6-axis collaborative robot arm (UR10e) completely covered with a sensitive skin (AIRSKIN) consisting of eleven individual pads. On a mock pick-and-place scenario with both transient and quasi-static collisions, we demonstrate how skin sensitivity influences the task performance and exerted force. We show an increase in productivity of almost 50% from the most conservative setting of collision thresholds to the most adaptive setting, while ensuring safety for human operators. The method is applicable to any robot for which the effective mass can be calculated.

Artificial electronic skins covering complete robot bodies can make physical human-robot collaboration safe and hence possible. Standards for collaborative robots (e.g., ISO/TS 15066) prescribe permissible forces and pressures during contacts with the human body. These characteristics of the collision depend on the speed of the colliding robot link but also on its effective mass. Thus, to warrant contacts complying with the Power and Force Limiting (PFL) collaborative regime but at the same time maximizing productivity, protective skin thresholds should be set individually for different parts of the robot bodies and dynamically on the run. Here we present and empirically evaluate four scenarios: (a) static and uniform - fixed thresholds for the whole skin, (b) static but different settings for robot body parts, (c) dynamically set based on every link velocity, (d) dynamically set based on effective mass of every robot link. We perform experiments in simulation and on a real 6-axis collaborative robot arm (UR10e) completely covered with sensitive skin (AIRSKIN) comprising eleven individual pads. On a mock pick-and-place scenario with transient collisions with the robot body parts and two collision reactions (stop and avoid), we demonstrate the boost in productivity in going from the most conservative setting of the skin thresholds (a) to the most adaptive setting (d). The threshold settings for every skin pad are adapted with a frequency of 25 Hz. This work can be easily extended for platforms with more degrees of freedom and larger skin coverage (humanoids) and to social human-robot interaction scenarios where contacts with the robot will be used for communication.

Safety for physical human-robot interaction (pHRI) is a major concern for all application domains. While current standardization for industrial robot applications provide safety constraints that address the onset of pain in blunt impacts, these impact thresholds are difficult to use on edged or pointed impactors. The most severe injuries occur in constrained contact scenarios, where crushing is possible. Nevertheless, situations potentially resulting in constrained contact only occur in certain areas of a workspace and design or organisational approaches can be used to avoid them. What remains are risks to the human physical integrity caused by unconstrained accidental contacts, which are difficult to avoid while maintaining robot motion efficiency. Nevertheless, the probability and severity of injuries occurring with edged or pointed impacting objects in unconstrained collisions is hardly researched. In this paper, we propose an experimental setup and procedure using two pendulums modeling human hands and arms and robots to understand the injury potential of unconstrained collisions of human hands with edged objects. Pig feet are used as ex vivo surrogate samples - as these closely resemble the physiological characteristics of human hands - to create an initial injury database on the severity of injuries caused by unconstrained edged or pointed impacts. For the effective mass range of typical lightweight robots, the data obtained show low probabilities of injuries such as skin cuts or bone/tendon injuries in unconstrained collisions when the velocity is reduced to < 0.5 m/s. The proposed experimental setups and procedures should be complemented by sufficient human modeling and will eventually lead to a complete understanding of the biomechanical injury potential in pHRI.

The successful implementation of Physical Human-Robot Interaction in industrial environments depends on ensuring safe collaboration between human operators and robotic devices. This necessitates the adoption of measures that guarantee the safety of human operators in close proximity to robots, without constraining the speed and motion of the robotic systems. This paper proposes a novel variable impedance-based controller for cobots that ensures safe collaboration by adhering to the ISO/TS 15066 safety standard, namely power and force limiting mode, while achieving higher operational speeds. The effectiveness of the proposed controller has been compared with conventional methods and implemented on two different robotic platforms. The results demonstrate the designed controller achieves higher speeds, while maintaining compliance with safety standards. The proposed variable impedance holds significant potential for enabling efficient and safe collaboration between humans and robots in industrial settings.

The technical specification ISO/TS 15066 provides the foundational elements for assessing the safety of collaborative human-robot cells, which are the cornerstone of the modern industrial paradigm. The standard implementation of the ISO/TS 15066 procedure, however, often results in conservative motions of the robot, with consequently low performance of the cell. In this paper, we propose an energy tank-based approach that allows to directly satisfy the energetic bounds imposed by the ISO/TS 15066, thus avoiding the introduction of conservative modeling and assumptions. The proposed approach has been successfully validated in simulation.

Human safety has always been the main priority when working near an industrial robot. With the rise of Human-Robot Collaborative environments, physical barriers to avoiding collisions have been disappearing, increasing the risk of accidents and the need for solutions that ensure a safe Human-Robot Collaboration. This paper proposes a safety system that implements Speed and Separation Monitoring (SSM) type of operation. For this, safety zones are defined in the robot's workspace following current standards for industrial collaborative robots. A deep learning-based computer vision system detects, tracks, and estimates the 3D position of operators close to the robot. The robot control system receives the operator's 3D position and generates 3D representations of them in a simulation environment. Depending on the zone where the closest operator was detected, the robot stops or changes its operating speed. Three different operation modes in which the human and robot interact are presented. Results show that the vision-based system can correctly detect and classify in which safety zone an operator is located and that the different proposed operation modes ensure that the robot's reaction and stop time are within the required time limits to guarantee safety.