Coverage control for mobile sensing robots in unknown environments using neural network

Abstract

This study proposes a distributed control algorithm for coverage in unknown environments with networked mobile sensors. The control law is derived according to the online neural network estimation of the sensory function of the environments. In contrary to previous adaptive approaches, a major advantage of the proposed method is that due to the neural network nonlinear approximation property, it is not restricted to multi Gaussian sensory functions. Simulation results show that the proposed controller outperforms the previous adaptive approaches in the sense of performance and convergence rate.