Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-Time Adaptive Industrial Robots: Improving Safety And Comfort In Human-Robot Collaboration

Damian Hostettler, Simon Mayer, Jan Liam Albert, Kay Erik Jenss, Christian Hildebrand

TL;DR

The paper tackles the challenge of making industrial robot collaboration safer and more comfortable by introducing a real-time, user-aware HRI system that adapts robot movement based on proximity and pupil dilation. It implements a prototype using an articulated arm and a depth camera plus eye tracker, and evaluates it with a within-subject study (n=16) across trial and assembly tasks, comparing adaptive and non-adaptive modes. Key findings show the adaptive system reduces cognitive workload (lower NASA-TLX) and sympathetic arousal (smaller pupil dilation in critical moments), while improving pragmatic usability; qualitative feedback favors adaptiveness, though productivity trade-offs are noted due to speed reductions. The work demonstrates the feasibility and benefits of non-intrusive physiological sensing to drive real-time robot adaptations in manufacturing, and provides a methodological framework and open data/code to enable replication and further research in adaptive HRI.

Abstract

Industrial robots become increasingly prevalent, resulting in a growing need for intuitive, comforting human-robot collaboration. We present a user-aware robotic system that adapts to operator behavior in real time while non-intrusively monitoring physiological signals to create a more responsive and empathetic environment. Our prototype dynamically adjusts robot speed and movement patterns while measuring operator pupil dilation and proximity. Our user study compares this adaptive system to a non-adaptive counterpart, and demonstrates that the adaptive system significantly reduces both perceived and physiologically measured cognitive load while enhancing usability. Participants reported increased feelings of comfort, safety, trust, and a stronger sense of collaboration when working with the adaptive robot. This highlights the potential of integrating real-time physiological data into human-robot interaction paradigms. This novel approach creates more intuitive and collaborative industrial environments where robots effectively 'read' and respond to human cognitive states, and we feature all data and code for future use.

Real-Time Adaptive Industrial Robots: Improving Safety And Comfort In Human-Robot Collaboration

TL;DR

The paper tackles the challenge of making industrial robot collaboration safer and more comfortable by introducing a real-time, user-aware HRI system that adapts robot movement based on proximity and pupil dilation. It implements a prototype using an articulated arm and a depth camera plus eye tracker, and evaluates it with a within-subject study (n=16) across trial and assembly tasks, comparing adaptive and non-adaptive modes. Key findings show the adaptive system reduces cognitive workload (lower NASA-TLX) and sympathetic arousal (smaller pupil dilation in critical moments), while improving pragmatic usability; qualitative feedback favors adaptiveness, though productivity trade-offs are noted due to speed reductions. The work demonstrates the feasibility and benefits of non-intrusive physiological sensing to drive real-time robot adaptations in manufacturing, and provides a methodological framework and open data/code to enable replication and further research in adaptive HRI.

Abstract

Industrial robots become increasingly prevalent, resulting in a growing need for intuitive, comforting human-robot collaboration. We present a user-aware robotic system that adapts to operator behavior in real time while non-intrusively monitoring physiological signals to create a more responsive and empathetic environment. Our prototype dynamically adjusts robot speed and movement patterns while measuring operator pupil dilation and proximity. Our user study compares this adaptive system to a non-adaptive counterpart, and demonstrates that the adaptive system significantly reduces both perceived and physiologically measured cognitive load while enhancing usability. Participants reported increased feelings of comfort, safety, trust, and a stronger sense of collaboration when working with the adaptive robot. This highlights the potential of integrating real-time physiological data into human-robot interaction paradigms. This novel approach creates more intuitive and collaborative industrial environments where robots effectively 'read' and respond to human cognitive states, and we feature all data and code for future use.
Paper Structure (29 sections, 4 figures, 3 tables)

This paper contains 29 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work and Theoretical Foundations
  3. Ergonomic Robot Behavior
  4. Applicable Movement Modulations for Articulated Robot Arms
  5. Adaptive Behavior Triggers
  6. Static Human-Related Factors
  7. Dynamic Human-Related Factors
  8. Suitability for Real-Time Data Collection
  9. Suitability for Non-Intrusive Data Collection
  10. Context-related Factors
  11. Resulting Factors Suitable for Real-Time Adaptiveness in Manufacturing Shopfloors
  12. Evaluation of an Adaptive Industrial Robot
  13. Study Design
  14. Experimental Procedure
  15. Data Processing and Analysis
  16. ...and 14 more sections

Figures (4)

  • Figure 1: System Architecture Illustrating the Perceived Operator's States and the Robot's Movement Adaptations.
  • Figure 2: Experimental Setup Showing the Movement Episodes 1-3 and the Areas A-E Further Described in the Text.
  • Figure 3: Mean Distance and Pupil Diameter of Operators Across the 4 Steps and 3 Episodes of the Evaluation.
  • Figure 4: UEQ Benchmark Analysis for the Adaptive and Non-Adaptive Conditions of the Evaluated System.