An Efficient Neural Network Approach to Dynamic Robot Motion Planning and Map Building

摘要

In this paper, a novel biologically inspired neural network approach is proposed for real-time simultaneous map building and path planning with limited measurable sensor information in a nonstationary environment. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation with both excitatory and inhibitory connections. There are only local connections in the proposed neural network. The environment is assumed completely unknown, and subject to sudden change. The map of the environment is build during the real-time robot navigation with its sensor information that is limited to a short range. The real-time robot path is generated through the dynamic activity landscape of the neural network. The system stability is guaranteed by a Lyapunov stability theory. The effectiveness and the efficiency are demonstrated by simulations studies.