NEURAL DYNAMICS AND COMPUTATION FOR REAL-TIME MAP BUILDING AND PATH PLANNING OF MOBILE ROBOTS

摘要

A novel neural dynamics based 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 or additive neural model with both excitatory and inhibitory connections and with only local connections among neurons. The environment is assumed to be completely unknown, and subject to arbitrary changes. The map of the environment is built during the real-time robot navigation through its sensor measurements that are 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 of the proposed approach are demonstrated by simulations studies.