Cloud service platform and collaborative scheduling method, device and system

Abstract

The invention discloses a cloud service platform, a cooperative scheduling method, a cooperative scheduling device and a cooperative scheduling system. The cooperative scheduling method comprises the following steps: acquiring current subinterval information; obtaining the operation content of the current subinterval and the capability information of each vehicle operating in the current subinterval according to the information of the current subinterval; selecting a current sentry vehicle corresponding to the current subinterval according to the operation content and the capability information of each vehicle; determining a current operation constraint condition corresponding to the current subinterval according to the operation content; and sending the current operation constraint condition to the current sentry vehicle. Different guard vehicles can be selected to serve as edge servers for different sub-operation intervals of the same operation, and each engineering vehicle does not need to have the capabilities of environmental perception fusion, behavior decision planning and multi-machine cooperative scheduling. Therefore, the scheduling comprehensive effect of the whole function is optimal.

Description

technical field [0001] The invention relates to the technical field of cluster operations, in particular to a cloud service platform, a collaborative scheduling method, device and system. Background technique [0002] The unmanned cluster operation is a joint operation of multiple types of work and multiple devices under the coordinated scheduling of the system. Most of the current solutions for unmanned cluster operations are vehicle-cloud collaboration (such as figure 1 ), that is, engineering vehicle-cloud server, or vehicle-side-cloud collaboration (such as figure 2 ), that is, engineering vehicle-edge server-cloud server. [0003] When vehicle-cloud collaboration is adopted, if each engineering vehicle has the capabilities of environment perception fusion, behavior decision-making planning, and multi-machine collaborative scheduling required for unmanned operations, each engineering vehicle needs to be equipped with a large number of sensors and high-performance comp...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present invention provide a cloud service platform, a collaborative scheduling method, device, and system to solve the problem of increased operating costs when car-cloud collaboration is used, or when car-side-cloud collaboration is used, the edge server Difficult problems with recycling and moving

[0007] Using the collaborative scheduling method provided by the embodiment of the present invention, different sentinel vehicles can be selected to act as edge servers for different sub-job intervals of the same job, which solves the problem of difficult recovery and movement of edge servers; and it is not necessary for each engineering vehicle to have an environment Perception fusion, behavioral decision-making planning, and multi-machine cooperative scheduling capabilities, so in addition to sentinel vehicles, it is not necessary for every engineering vehicle to be equipped with many sensors and high-performance computing platforms, and the cost of the entire system is effectively controlled; Divide it into multiple sub-intervals, and assign different sentry vehicles to each sub-interval to optimally schedule the operations in this sub-interval, so that the operations in each sub-interval are optimal, and the overall scheduling effect of the entire function is also optimal.

Images