Toward safe and efficient autonomous platooning: A coalitional game-theoretic framework.

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Transportation Engineering

Background:

• Autonomous vehicle platooning faces safety risks in mixed traffic due to unpredictable human drivers and inflexible platoon structures.
• Fixed platoon formations struggle to adapt to dynamic traffic, increasing collision probability and reducing safety margins.

Purpose of the Study:

• To develop a safety-oriented hierarchical framework for autonomous platooning in mixed-traffic environments.
• To enhance coordination and adaptability by integrating centralized decision-making with distributed execution.

Main Methods:

• A coalitional game-theoretic mechanism for adaptive coalition formation and interaction-aware strategy generation at the decision-making level.
• Distributed motion controllers for translating strategies into safe, dynamically feasible control actions at the execution level.

Main Results:

• The proposed framework significantly improves safety by increasing minimum time-to-collision and reducing exposure to critical risk conditions.
• Operational efficiency is maintained at comparable levels to existing methods.
• Validation in mixed-traffic scenarios demonstrates enhanced safety performance.

Conclusions:

• The safety-oriented hierarchical framework effectively addresses the challenges of autonomous platooning in complex traffic.
• The integration of adaptive coalitions and interaction-aware strategies ensures safer and more efficient autonomous platooning.