Integration of Tracking, Re-Identification, and Gesture Recognition for Facilitating Human-Robot Interaction

Area of Science:

• Robotics
• Human-Computer Interaction
• Artificial Intelligence

Background:

• Effective human-robot collaboration requires high-quality human-robot interaction (HRI).
• Advancements in robot intelligence allow robots to proactively initiate and sustain HRI.
• Facilitating seamless HRI enables human users to focus on primary tasks.

Purpose of the Study:

• To introduce the Robot-Facilitated Interaction System (RFIS).
• To demonstrate a system for proactive, real-time, and user-friendly HRI using mobile robots.
• To showcase the integration of identification, tracking, re-identification, and gesture recognition for HRI.

Main Methods:

• Implemented the RFIS on an autonomous mobile robot for patient transport scenarios.
• Focused on integrating interaction facilitation modules within an edge computing environment.
• Utilized caretaker recognition, tracking, re-identification, and gesture recognition for HRI.

Main Results:

• The RFIS demonstrated high-quality HRI facilitation in real-time operations.
• Achieved average accuracies exceeding 90% for caretaker recognition, tracking, re-identification, and gesture recognition.
• Operated effectively at 5 frames per second (FPS) in an edge computing setting.

Conclusions:

• The RFIS provides a comprehensive solution for facilitating high-quality HRI.
• The system's integration of multiple interaction modules ensures anytime readiness for collaboration.
• The successful implementation highlights the potential of intelligent mobile robots in caretaking environments.