A Human-Robot Co-Manipulation Approach Based on Human Sensorimotor Information.

Area of Science:

• Robotics
• Human-Computer Interaction
• Biomechanics

Background:

• Cooperative tasks involving humans and robots require seamless interaction and coordination.
• Existing assistive robot controllers often lack adaptability to real-time human motor behavior.
• Dynamic and complex tasks pose significant challenges for human-robot teaming.

Purpose of the Study:

• To develop and evaluate a novel human-in-the-loop framework for assistive robots.
• To improve the interaction and coordination between humans and robots in cooperative tasks.
• To enable robots to adapt their assistance based on human motor function and manipulability.

Main Methods:

• Integration of online human motor function and manipulability data into a hybrid robot controller.
• Implementation of a human-in-the-loop control strategy for adaptive robotic assistance.
• Experimental validation in two human-robot co-manipulation tasks requiring complementary agent behaviors.

Main Results:

• The proposed approach demonstrated enhanced physical human-robot interaction performance.
• The system successfully adapted robot assistance to human motor behavior across different task phases.
• Effective complementary behavior between human and robot agents was achieved.

Conclusions:

• The novel human-in-the-loop framework significantly improves human-robot interaction in complex tasks.
• Adaptive robotic assistance based on real-time human data enhances cooperative task execution.
• The technique offers a promising direction for more intuitive and effective human-robot collaboration.