Research on automatic driving path optimization algorithm based on Frenet coordinate system and Cartesian coordinate system

Under complex traffic conditions, autonomous driving has high requirements for the real-time and accuracy of path planning. Existing methods have shortcomings: the Frenet coordinate system simplifies calculations but is difficult to meet kinematic constraints, and the Cartesian coordinate system adapts to complex road conditions but is inefficient. To this end, this study proposes a dual-coordinate system collaborative path planning method, which first preliminarily solves the problem in the Frenet coordinate system and then optimizes it in the Cartesian coordinate system. Combining the gradient method with curve interpolation (GCI), the system considers kinematic constraints, dynamic obstacle avoidance, and trajectory smoothness, constructs an efficient iterative framework, and greatly improves the path planning performance.