Brain-Inspired Multi-Pathway Motion Decision-Making for Obstacle Avoidance of Humanoid Arms

Area of Science:

• Robotics
• Artificial Intelligence
• Neuroscience

Background:

• Robotic obstacle avoidance in dynamic environments is challenging.
• Humanoid arms require enhanced adaptability and flexibility for navigation.

Purpose of the Study:

• To propose a brain-inspired multi-pathway motion decision-making method for humanoid arm obstacle avoidance.
• To improve robot adaptability and flexibility in complex environments.

Main Methods:

• A novel framework with slow (rational planning via RT-RRT*) and fast (habitual actions via Soft Actor-Critic) pathways.
• An emotional neural network modulates pathway integration based on environmental and body information.
• The fast pathway's model guides the slow pathway's sampling strategy.

Main Results:

• The proposed framework achieved a higher obstacle-avoidance success rate compared to existing methods.
• Generated motion characteristics mimic aspects of human obstacle-avoidance behavior.
• Demonstrated enhanced adaptability and flexibility in complex, dynamic environments.

Conclusions:

• The brain-inspired multi-pathway method effectively enhances humanoid arm obstacle avoidance.
• The system integrates deliberate planning with rapid, habitual responses for improved performance.
• This approach offers a promising direction for developing more adaptive and human-like robotic systems.