摘要：AbstractOne of the main problems related to path planning is to find a method which will effectively allow the robot or vehicle to avoid obstacles, provided that these obstacles can be static or dynamic. One of the most interesting methods for path planning is the use of the artificial potential fields in order to create a representation of the environment as proposed by Khatib and Ge & Cui. These approaches enable handling online situations, which is desirable when facing uncertain obstacles appearing in the path. Three propositions are provided in the repulsive potential fields to avoid acceleration oscillations occurring while the ego-vehicle enters the limit boundaries of an obstacle. The advantages and limitations of the proposed methods will be explored. The performance of the different propositions will be compared by using criteria such as length and energy in a simple scenario.
