Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC

Area of Science:

• Robotics and Autonomous Systems
• Control Engineering
• Artificial Intelligence

Background:

• Path planning and tracking control are critical for autonomous vehicles.
• The Artificial Potential Field (APF) algorithm offers completeness but suffers from local minima, unreachable targets, and safety concerns.
• Existing methods require enhancement to address these limitations for real-world applications.

Purpose of the Study:

• To propose an improved Artificial Potential Field (APF) algorithm for autonomous vehicle path planning.
• To develop a cubic B-spline path optimization method.
• To design an advanced sliding mode controller for accurate path tracking.

Main Methods:

• An improved APF algorithm incorporating obstacle velocity, road constraints, virtual sub-targets, and velocity repulsion fields.
• A cubic B-spline method for path optimization.
• A sliding mode controller integrating lateral and heading errors with an enhanced sliding mode function.

Main Results:

• The improved APF algorithm generates paths with smaller, continuous heading angles and curvatures, considering vehicle kinematics.
• Path tracking experiments show lateral error within 0.06 m and yaw angle error within 0.3 rad at various speeds.
• The proposed methods demonstrate effective path planning and high-precision tracking control.

Conclusions:

• The enhanced APF algorithm effectively addresses limitations of traditional APF methods.
• The integrated path planning and tracking control system ensures safe, smooth, and accurate autonomous vehicle navigation.
• The study validates the proposed methods on simulation platforms, showing significant improvements in performance.