Complete Coverage Path Planning Algorithm Based on Improved Biologically Inspired Neural Networks in Spray Painting

Intelligent putty coating technology is the main way to improve the degree of automation of railroad vehicle painting workshops. The two-component putty, which is currently used in the vehicle coating system, has extremely low fluidity, which requires improving the full coverage of the spray path while minimizing the number of gun switches, i.e., reducing the path overlap rate. We propose the following improvements for the complete coverage path planning (CCPP) of putty spraying robots as well as the under-performance of path planning by biologically inspired neural networks (BINN) algorithms: (1) making full use of the topological neurons of the traversed area to establish the feedback adjustment coefficients, and (2) optimizing the steering parameter terms in the movement control equation to solve the optimal path point selection problem. To minimize the path repetition rate and reduce the probability of dead zones, a region decomposition detection algorithm and an avoidance mechanism are proposed. Many simulation results show that the proposed improved algorithm is better adapted, and the generated spraying paths are coherent and orderly with a low repetition rate, which can meet the spraying requirements of the existing rail vehicles.