Hybrid Dijkstra-PSO algorithm for motion planning of non-holonomic multiple-trailer platforms in dense contexts

This work proposes and illustrates an efficient path planning algorithm for non-holonomic multiple-trailer platforms. The goal is to find optimal paths according to different criteria using dense properties of a map and considering the robot's dynamic constraints. The proposed algorithm combines a low dimensional Dijkstra cost-to-go function with PSO minimisation, performed in the higher dimensional configuration space, in order to find optimal paths according to diverse constraints. The methodology includes adaptations to both algorithms to achieve higher efficiency of the computational cost and optimality of the planned path. Experimental results show the performance of the algorithm under several circumstances.