Distributed cognition for collaboration between human drivers and self-driving cars

Area of Science:

• Human-Computer Interaction
• Cognitive Science
• Intelligent Transportation Systems

Background:

• Current research on autonomous vehicles often focuses on full automation.
• Intelligent vehicles require effective collaboration mechanisms between humans and AI.
• Distributed cognition offers a framework for understanding intelligence as a system property.

Purpose of the Study:

• To propose a new collaboration mechanism for human drivers and intelligent vehicles.
• To apply the concept of distributed cognition to vehicle intelligence.
• To explore a human-AI interaction paradigm distinct from full autonomy.

Main Methods:

• Conceptualizing vehicle intelligence as a distributed cognitive system.
• Utilizing the rider-horse metaphor to describe human-agent interaction.
• Employing a driving simulator to demonstrate and evaluate the collaboration mechanism.

Main Results:

• The proposed distributed cognition model enables effective human-agent collaboration in driving.
• The rider-horse metaphor accurately illustrates human influence on the autonomous agent.
• Simulations confirmed safe and interactive outcomes through various communication methods.

Conclusions:

• Distributed cognition provides a viable framework for human-intelligent vehicle collaboration.
• The rider-horse interaction model facilitates intuitive human control and communication.
• This approach offers a new perspective on developing cooperative intelligent vehicle systems.