Energy-Based Injury Protection Database: Including Shearing Contact Thresholds for Hand and Finger Using Porcine Surrogates
Authors: Robin Jeanne Kirschner, Anna Huber, Carina M. Micheler, Dirk Müller, Nader Rajaei, Rainer Burgkart, Sami Haddadin
Organizations: Munich Institute of Robotics and Machine Intelligence, Technical University of Munich, 80992 Munich, Germany · TUM Hospital, Department of Orthopaedics and Sports Orthopaedics, 81675 Munich, Germany · Institute for Machine Tools and Industrial Management, TUM School of Engineering and Design, Technical University of Munich, 85748 Garching near Munich, Germany · Mohamed Bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates
While robotics research continues to propose strategies for collision avoidance in human-robot interaction, the reality of constrained environments and future humanoid systems makes contact inevitable. To mitigate injury risks, energy-constraining control approaches are commonly used, often relying on safety thresholds derived from blunt impact data in EN ISO 10218-2:2025. However, this dataset does not extend to edged or pointed collisions. Without scalable, clinically grounded datasets covering diverse contact scenarios, safety validation remains limited. Previous studies have laid the groundwork by assessing surrogate-based velocity and mass limits across various geometries, focusing on perpendicular impacts. This study expands those datasets by including shearing contact scenarios in unconstrained collisions, revealing that collision angle significantly affects injury outcomes. Notably, unconstrained shearing contacts result in fewer injuries than perpendicular ones. By reevaluating all prior porcine surrogate data, we establish energy thresholds across geometries and contact types, forming the first energy-based Injury Protection Database. This enables the development of meaningful energy-limiting controllers that ensure safety across a wide range of realistic collision events.
Figures & tables
Fig. 1 : Shearing collisions, common in real-world contact scenarios, are not yet covered by existing energy-based safety thresholds. To investigate injury severity, the robot is modeled as a moving mass with defined impact geometry and collision angle. Surrogate experiments provide initial energy limits based on contact geometry, enabling estimation of safe energy densities for non-perpendicular impacts and adding it to the Injury Protection Database.
Fig. 2 : Schematic of the shearing contact and energy distribution as well as skin deformation. The individual layers of tissue can be seen here qualitatively specifically on the back of the hand. The muscle tissue can be disregarded.
Fig. 4 : Impact conditions: a) dissected specimen with collision locations and b) impact angle α for different impactors.
Impactor
0 kg
2×1 kg
2×2 kg
2×3 kg
2×4 kg
Wedge
1.56
3.53
5.47
7.46
9.46
Edge
1.43
3.40
5.64
7.33
9.33
Sheet
1.52
3.49
5.43
7.43
9.42
TABLE I : Effective mass ( meff ) values for different impactor types and added weights.
Fig. 5 : Observed injury types.
Injury Classification
α = 45∘
α = 70∘
Total
Skin Imprint
154
255
409
Skin Cut
27
80
107
Skin Abrasion
31
19
50
Tendon Injury
1
6
7
TABLE II : Injury occurrences by collision angle across all experiments. The table highlights differences in injury types between 45° and 70° impact configurations.
Fig. 6 : Observed percentage of injury for skin cuts occurring at 45∘ impacts using pendulum Ia) and Ib) with 2.6kg and 6.4kg mass with all impactors.
Fig. 7 : Observed percentage of skin cuts occurring at 70∘ impacts using pendulum Ia) and Ib) with 2.6kg and 6.4kg mass with all impactors.
Fig. 8 : Energy distribution of observed injury types using the respective impactors for Ib).
Fig. 9 : Observed Injury severity in unconstrained, shearing contacts over all impactors distributed over the kinetic energy of the pendulum in the contact.
Fig. 10 : Injury Protection Database (surrogate studies): Most conservative thresholds for avoiding occurrence of any open skin injury from surrogate studies on pig front paws.
Fig. 11 : Scenario-based threshold selection for choosing safety threshold focused on human hand and fingers.
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.
Lukas Rustler, Matej Misar, Matej Hoffmann
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic
Humanoid robots often execute motion commands through whole-body controllers (WBCs) that track targets while maintaining balance and stability. However, most WBCs are blind to scene geometry, which can lead to collisions from imperfect target motions that are geometrically unsafe due to perception, planning, or teleoperation errors. We propose RECAL, a Robot--Environment Cross-Attention Layer that wraps a blind WBC to trade off target tracking against collision avoidance using external scene geometry. RECAL supports collision-aware tracking of floating-base and end-effector commands, including collision avoidance for held objects. It represents the robot, held objects, and environment as point clouds, using cross-attention between robot/object points and the environment to produce geometry-aware control features. In simulation, RECAL improves collision avoidance while preserving target-tracking performance across frozen-arm and adaptive-arm locomotion, object-carrying, and standing-manipulation scenarios relative to alternative geometry-aware WBC architectures. We further demonstrate the controller on a real Digit V3 humanoid robot.
Mohitvishnu S. Gadde, Ashish Malik, Pranay Dugar +3
Collaborative Robotics and Intelligent Systems Institute (CoRIS), Oregon State University, Corvallis, OR 97331
Smoothed implicit contact dynamics enables gradient-based planning and control for contact-rich tasks without predefined mode sequences. However, safety-critical control remains challenging because implicit contact dynamics makes safety-filter design nontrivial. The smoothing parameter κ relaxes contact complementarity constraints, which makes the dynamics smooth but affects the contact force. This paper provides a safety-filtering framework for smoothed implicit contact dynamics. We first derive a discrete-time control barrier function (CBF) constraint using a first-order Taylor approximation of the implicitly defined contact force. We show that, although reducing κ can improve local force-approximation accuracy, the resulting closed-loop force-constraint violations can vary non-monotonically with κ. Motivated by this observation, we introduce boundary-focused rollouts that screen candidate κ values by comparing the predicted safety margin with the observed one-step under-prediction. We then robustly tighten the predicted CBF constraint with a fixed margin to account for residual force under-prediction. Simulations on four contact-rich systems show that the proposed method eliminates force violations observed under a standard CBF. Project website https://contact-cbf.github.io/
Haegu Lee, Yitaek Kim, Christoffer Sloth
The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark