Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Electronic Skin Sensitivity for Safe Human-Robot Interaction

Lukas Rustler, Matej Misar, Matej Hoffmann

TL;DR

The paper tackles safe yet productive human-robot interaction by making protective skin thresholds adaptive across a robot's body. It compares four thresholding schemes—UNIFORM, BODY PARTS, LINK VELOCITY, and EFFECTIVE MASS—with two collision responses, STOP and AVOID, updating thresholds at 25 Hz and grounding them in ISO/TS 15066 models. Through both simulation (PyBullet) and real UR10e experiments with AIRSKIN, it shows that adaptive schemes, especially effective-mass-based thresholds, reduce interruption times and shorten avoidance travel without compromising safety. This work lays a scalable foundation for expanding full-body robotic skins to larger robots and humanoids, enabling safer, more productive physical human-robot collaboration and potential social interaction scenarios.

Abstract

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.

Adaptive Electronic Skin Sensitivity for Safe Human-Robot Interaction

TL;DR

The paper tackles safe yet productive human-robot interaction by making protective skin thresholds adaptive across a robot's body. It compares four thresholding schemes—UNIFORM, BODY PARTS, LINK VELOCITY, and EFFECTIVE MASS—with two collision responses, STOP and AVOID, updating thresholds at 25 Hz and grounding them in ISO/TS 15066 models. Through both simulation (PyBullet) and real UR10e experiments with AIRSKIN, it shows that adaptive schemes, especially effective-mass-based thresholds, reduce interruption times and shorten avoidance travel without compromising safety. This work lays a scalable foundation for expanding full-body robotic skins to larger robots and humanoids, enabling safer, more productive physical human-robot collaboration and potential social interaction scenarios.

Abstract

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.
Paper Structure (17 sections, 7 equations, 6 figures, 4 tables)

This paper contains 17 sections, 7 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Method
  4. Robot and Skin
  5. Simulation, Software and Data
  6. Performed Task
  7. Collision Reaction
  8. Collision Sensitivity Thresholds
  9. UNIFORM
  10. BODY PARTS
  11. LINK VELOCITY
  12. EFFECTIVE MASS
  13. Experiments and Results
  14. Experiment Description
  15. Simulation Experiments
  16. ...and 2 more sections

Figures (6)

  • Figure 1: The UR10e robot with AIRSKIN robotic skin. The ellipses distinguish three parts of the robot---upper arm, lower arm and hand. The numbers on individual skin pads represent their IDs (pads 4 and 7 on the other side of the robot). The table shows sensitivity thresholds values changing over time (with frequency of 25Hz) during the motion in given axis (in robot orientation system) during a task for all the skin pads in four different settings of the robotic skin. The thresholds are color-coded based on their sensitivity as: the highest sensitivity---red, medium sensitivity---orange, lowest sensitivity---yellow.
  • Figure 2: Top-view of the task performed by the robot. Order of movements is depicted by numbers in brackets.
  • Figure 3: Average total run times $\pm$ 1 sd. The values are averaged over all runs of the experiment in the given threshold setting.
  • Figure 4: Average reaction times $\pm$ 1 sd. The values are computed from runs of the experiments in which the robot actually reacted to collision.
  • Figure 5: Average distance moved to avoid collision. The values are averaged over all runs of the experiment in the given scenario.
  • ...and 1 more figures