Potential field reconstruction-based path planning system for autonomous vehicle with enhancing stability.

Area of Science:

• Robotics
• Artificial Intelligence
• Control Systems

Background:

• Path planning and tracking are crucial for autonomous vehicle (AV) operation.
• Conventional methods struggle to ensure AV stability during emergency scenarios.
• Existing systems often prioritize obstacle avoidance over dynamic stability in critical situations.

Purpose of the Study:

• To propose a novel path planning system for autonomous vehicles (AV) that ensures stability during emergency scenarios.
• To address the limitations of conventional path planning methods in maintaining AV stability under sudden events.
• To enhance the velocity adaptability and path stability of AVs in critical situations.

Main Methods:

• A potential field reconstruction-based path planning system (PFR-BPPS) was developed.
• The system comprises a potential field reconstruction module and an adaptive fusion module.
• Fuzzy inference rules were employed for adaptive integration of potential velocity and stability fields.

Main Results:

• The PFR-BPPS demonstrated superior performance in simulations conducted on the Matlab-Carsim co-simulation platform.
• The system effectively improved velocity adaptability for autonomous vehicles.
• The proposed method significantly enhanced path stability during emergency situations.

Conclusions:

• The PFR-BPPS offers a robust solution for path planning in autonomous vehicles, particularly in emergency scenarios.
• The integration of potential velocity and stability fields through fuzzy logic improves overall system performance.
• This approach contributes to safer and more reliable autonomous vehicle operation.