An efficient neural network model for path planning of car-like robots in dynamic environment

A neural network model is proposed for real-time path planning with obstacle avoidance of car-like robots in a dynamic environment. Each neuron in this biologically inspired, topologically organised neural network has only local lateral connections. The real-time collision-free path is planned through the dynamic neural activity landscape of the neural network without explicitly searching over the free workspace nor the collision paths, without explicitly optimising any cost functions, without any prior knowledge of the dynamic environment, without any learning procedures, and without any local collision checking procedures. Therefore it is computationally efficient. The stability and convergence of the neural network system is proved using Lyapunov stability analysis. The effectiveness and efficiency of the proposed approach are demonstrated through simulation studies.