Multi-vehicle path planning method for closed, dense network type and automatic logistics park

Abstract

The invention discloses a multi-vehicle path planning method for a closed, dense network type and automatic logistics park, which is used for modeling a two-dimensional space map to obtain a directed connected graph G(V, E), and comprises the following steps of: 1) creating an initial set; 2) expanding the path to a time dimension; 3) calculating conflicts and classification; 4) constructing a candidate path set; 5) solving a better path combination; 6) evaluating whether an end condition is reached or not; and 7) determining whether to quit according to the result of the step 6) and the number of iterations, and if not, iterating the step 2) to the step 6). According to the method, on the basis of the two-dimensional space, the driving conflict is comprehensively solved by considering the time dimension and the vehicle dimension, the problem of vehicle comprehensive feasibility is solved, and the approximate path comprehensive optimum is achieved on the basis.

Description

technical field [0001] The invention relates to the automatic driving technology of vehicles in logistics parks, and more specifically, to a multi-vehicle path planning method for closed, dense network and automated logistics parks. Background technique [0002] Closed automated logistics park refers to the work area where only automatic horizontal handling equipment (such as automatic guided vehicles) is used to carry out horizontal handling of goods within a limited range. This type of park has designed space resources such as access roads and interactive nodes. On the roads, the handling equipment is usually allowed to go straight, change lanes, turn, and rotate on the spot. Intersections are allowed between roads, and traffic lights are not set at intersections. Control measures. Due to limited road space resources, there are many spatial conflicts between roads in the design, especially in some applications, where the roads present a dense network intersection design. ...

AI Technical Summary

Problems solved by technology

However, this kind of method focuses on the waiting control of the traveling process, that is, solving conflicts from the time dimension, and does not optimize from the perspective of adjusting the path, that is, the space perspective, so it also has this obvious limitation.

[0021] 4) The method based on dynamic path planning, that is, according to the running state of the vehicle, the path is adjusted in real time, which can be adjusted in space and time, but the calculation complexity is high, so the space conflict and time conflict generally considered will not be too much Far, that is, considering the road in front of you and the situation in the future, this will lead to the "fool" phenomenon that the vehicle will move forward first and then reverse

[0022] To sum up, the shortcomings of these methods in the industry are all because there is no real solution to the problem from the perspective of multi-vehicle joint planning path

Images