Multi-robot scheduling method and device

Abstract

The invention aims to provide a multi-robot scheduling method and equipment, a server program of the multi-robot scheduling method mainly plays a role in sharing operation data, and is responsible for collecting and distributing operation data packets of shared robots to robot individuals; and the robot individuals can trigger multi-machine scheduling of the corresponding scheduling strategies only when running into the scheduling areas, the decision-making process of the multi-machine scheduling is not initiated by a server but independently completed by client programs carried by the robot individuals, and the scheduling strategies can be preset decision-making tree models of the corresponding scheduling areas according to the scheduling strategies. According to the invention, a lightweight data packet format is adopted between the robot and the server to carry out operation information exchange, so that the communication load caused by an overlarge data packet and a retransmission mechanism is greatly reduced. The server can be arranged in a local area network and does not need to be connected with an external network, so that the information safety in a user environment is ensured, and the interactive communication traffic between the server and the robot is small.

Description

technical field [0001] The invention relates to the field of computers, in particular to a multi-robot scheduling method and equipment. Background technique [0002] In recent years, with the rapid development of sensor technology and artificial intelligence technology, service robots have gradually transformed from laboratory research objects into intelligent products that can be applied on the ground. Service robots replace humans in specific scenarios to complete highly repetitive and high-risk tasks. Among them, the joint application of multi-robots in large-scale scenarios is one of the common landing scenarios, such as food delivery robots and distribution robots. In such application scenarios, there are problems such as the installation position of the robot’s sensors at the same position, the blind area limitation of the sensor, and the independent path planning methods used by individual robots in the process of performing tasks, etc., resulting in occasional colli...

AI Technical Summary

Problems solved by technology

[0003] 1. Existing solutions are often only applicable to homogeneous robot groups (or robot products of the same company), but future robot applications will be a diversified application scenario, so multi-machine scheduling solutions should also support heterogeneous robot groups

[0004] 2. Existing solutions often rely heavily on centralized servers. This model will cause the following bottleneck problems:

However, the deadlock problem caused by mutual blocking between robots will cause the robot to fall into an endless loop and stop executing tasks, which also restricts the execution of scene tasks, and is also a key problem to be solved in the multi-machine scheduling system.

[0008] 3. The scheduling behavior of the existing solution is relatively fixed and does not support custom development of the user end, which is not conducive to defining the robot scheduling behavior in a specific user scenario, and cannot meet the intelligent needs of the user scenario

Images