Multi-vehicle cooperative exploration method and device via environment segmentation

Abstract

The invention relates to a multi-vehicle cooperative exploration method and device via environment segmentation. The method comprises the followings steps that segmentation areas in a map are identified, and an edge point set of each segmentation area in the map is determined; the corresponding cost for reaching each segmentation area of each vehicle is calculated; and the corresponding cost are substituted into a cost value matrix to calculate an optimal distribution manner, and the vehicles are assigned to target areas according to the optimal distribution manner. Different from the prior art, a lattice point occupied map is identified and segmented into a node skeleton type map (a Voronoi diagram), repetition in map segmentation is reduced, the Voronoi diagram is used to calculate the moving costs of the vehicles, response cost exists when each vehicle moves to each node of the Voronoi diagram, the vehicles and the costs are substituted into a Hungary method, and a method enabling minimal total movement cost is obtained. The efficiency of a multi-vehicle environment exploration method is improved. Problems when multiple vehicles collaborate to explore the unknown environment are sovled.

Description

Technical field [0001] The invention relates to the field of unmanned vehicle design, in particular to a method and device for collaborative exploration of multiple vehicles using environment segmentation. Background technique [0002] The exploration of the environment has always been a fundamental issue in the field of unmanned vehicles. In order to construct a relatively complete and detailed environment map, the vehicle must be able to efficiently explore the environment. This article introduces a method of using multiple vehicles to collaborate to explore the environment. Compared with using a single vehicle system, using multiple vehicles for environmental exploration has the following four advantages. First, compared to a single vehicle, the collaborative cooperation of multiple fake vehicles has the potential to complete an environmental exploration mission faster. Second, whenever multiple vehicles can sense each other, they can exchange information about their respec...

AI Technical Summary

Problems solved by technology

[0003] However, when multiple vehicles conduct cooperative exploration, the risk of mutual interference between vehicles will be introduced

For example, if the vehicle uses active sensors, such as ultrasonic sensors, crosstalk between sensors may degrade the overall performance of the system

Images