A NEW ALGORITHM FOR MOBILE ROBOT GLOBAL PATH PLANNING

For simulated annealing algorithm, the convergence speed is very slow. So this paper presents a new hybrid optimal algorithm, which is successfully used for robot neural networks path planning, based on the combination of the simulated annealing algorithm and the conjugate direction method. This new hybrid optimal algorithm can not only prevent optimizing course from trapping the local minimum, but also achieve the global minimum. The simulation experiment demonstrates that this new algorithm's computation is simple, the convergence speed is fast. Also it can significantly improve the computational efficiency of solving mobile robot's global optimization problems.