Robot Static Path Planning Method Based on Deterministic Annealing

Heuristic calculation is an essential method to solve optimisation problems. However, its vast computing requirements limit its real-time and online applications, especially in embedded systems with limited computing resources, such as mobile robots. This paper presents a robot path planning algorithm called DA-APF based on deterministic annealing. It is derived from the artificial potential field and can effectively solve the local minimum problem of the model established by the potential field method. The calculation performance of DA-APF is considerably improved by introducing temperature parameters to enhance the potential field function and by using annealing and tempering methods. Moreover, an optimal or near-optimal robot path planning scheme is given. A comprehensive case study is performed using heuristic methods, such as genetic algorithm and simulated annealing. Simulation results show that DA-APF performs well in various static path planning environments.