An efficient neural network approach to dynamic robot motion planning

In this paper, a biologically inspired neural network approach to real-time collision-free motion planning of mobile robots or robot manipulators in a nonstationary environment is proposed. Each neuron in the topologically or ganized neural network has only local connections, whose neural dynamics is characterized by a shunting equation. Thus the computational complexity li nearly depends on the neural network size. The real-time robot motion is pl anned through the dynamic activity landscape of the neural network without any prior knowledge of the dynamic environment, without explicitly searchin g over the free workspace or the collision paths, and without any learning procedures. Therefore it is computationally efficient. The global stability of the neural network is guaranteed by qualitative analysis and the Lyapun ov stability theory. The effectiveness and efficiency of the proposed appro ach are demonstrated through simulation studies. (C) 2000 Elsevier Science Ltd. All rights reserved.