An region-filling operation (RFO) is a kind of coverage
path planning, which requires the robot path to fill every
grid of the workspace. It is an essential issue in plenty of robotic
applications. Safety aware collision-free region-filling operation
of an autonomous vehicle is one of the major challenges in
intelligent vehicle systems. A virtual obstacle based safety aware strategy integrated with a biologically inspired neural network method is proposed for RFO in a non-stationary environment as safety consideration is greatly crucial in vehicle RFO. The real-time vehicle trajectory is planned through the varying neural activity landscape that represents the dynamic environment. The proposed model for vehicle navigation with safety consideration is capable of planning a real-time “comfortable” trajectory. The proposed approach is capable of overcoming the either “too close” or “too far” shortcoming by utilizing proposed virtual obstacles (VO) methodologies. Simulation and comparison studies validated
that the proposed model is capable of performing RFO task to plan more reasonable and shorter collision-free trajectories
in non-stationary and unstructured environments.