Research on Dynamic Trajectory Planning Based on Model Predictive Theory for Complex Driving Scenarios.

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence for Transportation
• Automotive Engineering

Background:

• Autonomous driving relies heavily on trajectory planning for safe and efficient navigation.
• Current trajectory planning methods face challenges in dynamic driving scenarios with real-time environmental changes.
• Dynamic lane-changing is crucial for autonomous vehicles operating in complex traffic.

Purpose of the Study:

• To propose a novel dynamic lane-changing trajectory planning method for autonomous vehicles.
• To address the limitations of existing methods in real-time, dynamic driving environments.
• To enhance the performance and safety of autonomous driving systems.

Main Methods:

• Developed kinematic models for the host vehicle and surrounding vehicles.
• Applied model predictive control (MPC) theory, including prediction models, objective functions, and constraints.
• Utilized a least-squares fitting method to generate adaptable lane-changing trajectories.

Main Results:

• The proposed method demonstrated excellent real-time adaptability in dynamic driving scenarios.
• Simulation studies validated the effectiveness of the trajectory planning approach.
• The method successfully generated optimal control sequences for dynamic lane changes.

Conclusions:

• The novel dynamic lane-changing trajectory planning method provides a robust solution for autonomous driving.
• This research contributes to the development of autonomous vehicles capable of full-scenario operation.
• The findings pave the way for safer and more efficient autonomous navigation in complex environments.