Enhanced Intelligent Potential Field Algorithm for Unmanned Ground Vehicles Trajectory Planning in Complex Environments | ||
| Port-Said Engineering Research Journal | ||
| Articles in Press, Accepted Manuscript, Available Online from 24 September 2025 | ||
| Document Type: Original Article | ||
| DOI: 10.21608/pserj.2025.405608.1425 | ||
| Authors | ||
| Aya Abdelhady Deaf* 1; Hala Samir Elhadidy1; Walaa Elsayed Saber2; Rawya Yehia Rizk3 | ||
| 1Faculty of Engineering, Port Said University | ||
| 2Faculty of Engineering, Port said University | ||
| 3Faculty of Engineering, Port Said University | ||
| Abstract | ||
| Obtaining the best path and trajectory planning in real-time for mobile robots in complex environments while meeting all movement limitations and navigating safely and efficiently continue to be major robotics challenges. The optimal path is primarily limited by curvature continuity, least bending energy, minimum length, minimum travel time, and safety requirements for both static and dynamic environmental barriers. The potential field algorithm is the most widely used in path planning; however, it has drawbacks in complex environments. To overcome its limitations, an Enhanced Intelligent Potential Field (EIPF) algorithm is proposed for the path and trajectory planning of unmanned ground vehicles. The proposed method offered a hybrid approach that combines an optimal parameter selection procedure utilizing particle swarm optimization with adaptive step size modulation based on the strength of repulsive forces. Additionally, the proposed method introduces a safety zone around both static and dynamic obstacles to reduce the risk of collision and enhance the robustness of the robot’s navigation in real-world scenarios. The EIPF algorithm improves by 14% in the total curvature of the path and 48.51% in total bending energy compared to the classical method in a static environment. Furthermore, it improves by 49.84% in the total curvature and 84.87% in total bending energy in a dynamic environment. | ||
| Keywords | ||
| Complex Environment; Unmanned Ground Vehicles; Path Planning; Particle Swarm Optimization; Potential Field algorithm | ||
|
Statistics Article View: 1 |
||
