Full Coverage Path Planning Recombination Framework for Unmanned Vehicles With Multi-Objective Constraints

This article aims to solve the problem of full coverage path planning (FCPP) for unmanned vehicles with multi-objective constraints in an obstacle environment. A novel multi-objective coverage path planning recombination (MCPPR) framework is proposed to enhance the overall performance of the planned trajectory. The coordinate system transformation method is proposed to reduce the proportion of obstacles coverage area and optimize the solution space. Based on the improved FCPP mapping algorithm, a multicell recombination algorithm is developed. The constraints include coverage rate, overlap rate, trajectory length, and cumulative turning angle. An optimal double-layer agent motion and an improved probabilistic roadmaps algorithm are presented to plan obstacle avoidance paths for connecting neighboring cells. The final planning trajectory is smoothed using the Dubins algorithm. An index evaluation method is proposed to translate all indicators into the same quantitative space and to select the optimal trajectory. The results of the simulations and experiments show that the proposed MCPPR framework can provide an optimal solution to the FCPP problem.

Automated summary

This article proposes a novel multi-objective coverage path planning recombination framework to address the problem of full coverage path planning for unmanned vehicles in an obstacle environment. By utilizing methods such as coordinate system transformation and multi-cell recombination, the solution space and trajectory planning performance are optimized. The results demonstrate that the proposed framework can provide an optimal solution to the problem.