Area-covering operation of a cleaning robot in a dynamic environment with unforeseen obstacles

Abstract

Area-covering operation is a special kind of path planning, which requires the robot path to cover every part of the workspace. Area covering is an essential issue for cleaning robots and many other robotic applications such as painter robots, land mine detectors, lawn mowers, and windows cleaners. In this paper, a novel biologically inspired neural network approach to area-covering operation with avoidance of unforeseen obstacles is proposed for a cleaning robot in a dynamic environment. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation derived from a biological membrane model. There are only local lateral connections among neurons, thus the computational complexity depends linearly on the neural network size. The proposed approach is compared to fuzzy logic based, rule based and re-planning based models. It shows that the proposed model is capable of planning more reasonable and shorter area-covering path with obstacle avoidance. The proposed model algorithm is computationally efficient, and can also deal with changing environments.