EFFECTIVE SOLUTIONS FOR COMMON PROBLEMS OF ARTIFICIAL POTENTIAL FIELD BASED PATH PLANNING ALGORITHMS FOR MOBILE ROBOTS

Abstract

Abstract Autonomous Path Planning (APP) capability is one of the main factors determining the autonomous level of a mobile robot. Although different methods are used for APP in the literature, the path planning approach based on Artificial Potential Fields (APF) has a very common usage area with its modeling ease and computational performance. APF-based APP, which is a grid-based path planning approach, is usually performed by combining a repulsive and attractive component that models many basic motions with a certain equation and calculating the gradient of this potential field to obtain the vector field. In this study, the basic models used for APF-based APP are examined, and how they are realized and how the resultant potential field is produced are mentioned. Although APF-based APP approaches have advantages, they also have problems such as local minimum, obstacles positioned too close, oscillation, and targets positioned too close to obstacles. Within the scope of the study, these problems were defined one by one and the approaches suggested in the literature for the solution of these problems were mentioned in detail. As a result, it has been seen that to obtain an effective APF-based APP solution, it is necessary to generate a convolutional vector field, limit the fundamental potential fields with exponential functions, use virtual potential fields and perform models with harmonic functions.