| Summary: | Coverage Path Planning (CPP in short) is a basic problem for mobile robot when facing a variety of applications. <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning based coverage path planning algorithms are beginning to be explored recently. To overcome the problem of traditional <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning of easily falling into local optimum, in this paper, the new-type reward functions originating from Predator-Prey model are introduced into traditional <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning based CPP solution, which introduces a comprehensive reward function that incorporates three rewards including Predation Avoidance Reward Function, Smoothness Reward Function and Boundary Reward Function. In addition, the influence of weighting parameters on the total reward function is discussed. Extensive simulation results and practical experiments verify that the proposed Predator-Prey reward based <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning Coverage Path Planning (PP-<inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning based CPP in short) has better performance than traditional BCD and <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-Learning based CPP in terms of repetition ratio and turns number.
|
|---|