Human-Robot Interaction and Tracking System Based on Mixed Reality Disassembly Tasks

Disassembly is a crucial process in industrial operations, especially in tasks requiring high precision and strict safety standards when handling components with collaborative robots. However, traditional methods often rely on rigid and sequential task planning, which makes it difficult to adapt to unforeseen changes or dynamic environments. This rigidity not only limits flexibility but also leads to prolonged execution times, as operators must follow predefined steps that do not allow for real-time adjustments. Although techniques like teleoperation have attempted to address these limitations, they often hinder direct human–robot collaboration within the same workspace, reducing effectiveness in dynamic environments. In response to these challenges, this research introduces an advanced human–robot interaction (HRI) system leveraging a mixed-reality (MR) interface embedded in a head-mounted device (HMD). The system enables operators to issue real-time control commands using multimodal inputs, including voice, gestures, and gaze tracking. These inputs are synchronized and processed via the Robot Operating System (ROS2), enabling dynamic and flexible task execution. Additionally, the integration of deep learning algorithms ensures precise detection and validation of disassembly components, enhancing accuracy. Experimental evaluations demonstrate significant improvements, including reduced task completion times, enhanced operator experience, and compliance with strict adherence to safety standards. This scalable solution offers broad applicability for general-purpose disassembly tasks, making it well-suited for complex industrial scenarios.

• Publication year

  2025

• Venue

  Robotics

• Publication date

  2025-07-30

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.3390/robotics14080106
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• No references are available for this paper.

• A Comprehensive Review of Human-Robot Collaborative Manufacturing Systems: Technologies, Applications, and Future Trends

  2026cites this paper
• A Dataset of Standard and Abrupt Industrial Gestures Recorded Through MIMUs

  2025cites this paper
• Human-Robot Interaction-Integrated Code Review Interface for Collaborative Development

  2025cites this paper