An eikonal equation based path planning method using polygon decomposition and curve evolution

Path planning is a key technique of autonomous navigation for robots, and the velocity field is an important part. Constructing velocity field in a complex workspace is still challenging. In this paper, an inner normal guided segmentation algorithm in a complex polygon is proposed to decompose the complex workspace in this paper. The artificial potential field model based on probability theory is then used to calculate the potential field of the decomposed workspace, and the velocity field is obtained by utilizing the potential field of this workspace. Path optimization is implemented by curve evolution, during which the internal force generated in the smoothing process of the initial path by a mean filter and the external force is obtained from the gradient of the workspace potential field. The parameter selection principle is deduced by analyzing the influence of several parameters on the path length and smoothness. Simulation results show that the designed polygon decomposition algorithm can effectively segment complex workspace and that the path optimization algorithm can shorten and smoothen paths.     

基于混合算法的局部路径规划

人工势场法是一种常用的具有算法简单和便于实时控制的局部路径规划方法,但存在容易产生局部极小值的问题。基于模糊逻辑的局部路径规划法具有环境适应性强等优点,它在连续论域内采用模糊路径规划时,计算量比较大。提出了一种将人工势场法和模糊逻辑法相结合进行局部路径规划的混合算法。具体方法是在一般情况下采用人工势场法进行局部路径规划,当产生局部极小值时,采用模糊逻辑法进行局部路径规划。仿真结果表明,该方法能有效地解决局部极小值问题,给智能车规划出光滑的路径。