Adaptive Collision Sensitivity for Efficient and Safe Human-Robot Collaboration

2024-09-30

AI Summary

To address the frequent false stops and reduced efficiency caused by ISO/TS 15066’s mandatory global fixed contact force threshold in physical human–robot collaboration, this paper proposes an adaptive interruption decision framework based on body-part-level dynamic collision force estimation. The method integrates AIRSKIN tactile sensing, joint torque measurement, and rigid-body dynamics modeling to estimate the real-time effective mass and velocity of each robot link, enabling differential and dynamic adjustment of contact sensitivity across the robot’s surface. For the first time, it overcomes the standard’s constraint of a uniform threshold while guaranteeing full compliance with ISO/TS 15066 safety limits throughout operation. Experimental validation on UR10e and KUKA iiwa platforms executing pick-and-place tasks demonstrates a >45% reduction in stoppages and significantly shortened cycle times, confirming the framework’s generality and engineering practicality.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

What is considered safe for a robot operator during physical human-robot collaboration (HRC) is specified in corresponding HRC standards (e.g., 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 that decides whether the robot should interrupt or continue its 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 of each robot link and the link velocity. We performed experiments on simulated and real 6-axis collaborative robot arm (UR10e) with sensitive skin (AIRSKIN) for collision detection and isolation. To demonstrate the generality of our method, we added experiments on the simulated KUKA LBR iiwa robot, where collision detection and isolation draws on joint torque sensing. On a mock pick-and-place scenario with both transient and quasi-static collisions, we demonstrate how sensitivity to collisions influences the task performance and number of stops. We show an increase in productivity over 45% from using the standard approach that interrupts the tasks during every collision. While reducing the cycle time and the number of interruptions, our framework also ensures the safety of human operators. The method is applicable to any robot for which the effective mass can be calculated.

Problem

• Dynamic collision sensitivity for human-robot collaboration safety.
• Reducing productivity loss by adaptive collision force thresholds.
• Ensuring safety while minimizing robot interruptions in HRC.

Innovation

• Dynamic collision force estimation for robot parts
• Adaptive sensitivity based on robot link mass
• Increased productivity with ensured human safety