Dynamic Local Path Planning for Intelligent Vehicles Based on Sampling Area Point Discrete and Quadratic Programming

This paper proposes a dynamic path planning method based on discrete optimization applied to suburban highways or expressways. We optimize the generated candidate points according cost function and then generates local through quintic spline curve. The kinematics obstacle boundary conditions are set up improve reliability of planned path. Meanwhile, two-dimensional normal distribution function, comfort acceleration designed evaluate speed. Various types roads scenes, including static obstacles, such as straight roads, S- bend, established verify method’s feasibility. simulation shows that can efficiently avoid various obstacles plan an ideal complies with traffic laws.