Unlock instant, AI-driven research and patent intelligence for your innovation.

A multi-robot cooperative multi-target sampling method for open scenes

A multi-robot and robot technology, applied in the direction of instruments, two-dimensional position/channel control, control/regulation system, etc., to achieve the effect of saving time and cost

Active Publication Date: 2022-05-31
NAT UNIV OF DEFENSE TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] However, there is currently no public literature involving the application of knowledge distillation to multi-robot collaborative multi-target sampling for open scenarios.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-robot cooperative multi-target sampling method for open scenes
  • A multi-robot cooperative multi-target sampling method for open scenes
  • A multi-robot cooperative multi-target sampling method for open scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0122] figure 2 It is an overall flow chart of the present invention. like figure 2 Shown, the present invention comprises the following steps:

[0123] In the first step, build as figure 1 In the shown multi-robot system, the multi-robot system is composed of N robot nodes and cloud server nodes, where N is a positive integer. Each robot node works in the same way. It is a robot hardware device that can run software programs and has the capabilities of movement, observation, and communication, such as the ground robot Turtlebot3, the UAV Intelaero, etc. Each robot node includes multiple modules ( The first communication module, the detection module, the first calculation module, the first storage module, and the movement module).

[0124] like image 3 Shown:

[0125] The detection module is a sensor that collects mission environment data, including scanning radar, infrared camera, depth camera, etc. The detection module is connected to the first storage module, and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an open scene-oriented multi-robot cooperative multi-target sampling method. The technical solution is to build a multi-robot system consisting of N robot nodes and cloud server nodes. Communication modules, detection modules, computing modules, storage modules, and motion modules are installed on robot nodes; communication modules and storage modules are installed on cloud server nodes; In the multi-target sampling scenario, pre-train the simulation model of N robot nodes, and obtain N .data parameter format files that record the cooperative multi-target sampling strategy of the robot in the corresponding simulation scenario; deploy the multi-robot system in a real open scene, use The .data parameter format file is trained to obtain the multi-robot autonomous cooperative multi-target sampling strategy; the multi-robot system cooperates to complete the multi-target sampling task according to the sampling strategy. The invention can solve the problems of low timeliness, large amount of training data, long training time, strong task correlation and the like in the current multi-target sampling method.

Description

technical field [0001] The invention relates to how to make distributed multi-robots quickly and cooperatively complete multi-objective sampling tasks in an open unknown environment by using the domain knowledge of the intelligent robot system and multi-agent reinforcement learning technology. Especially when it involves some multi-robot untrained unpredictable sampling task scenarios (such as lunar rovers sampling lunar soil, sampling epidemic areas, etc.), they can autonomously form a collaborative strategy to complete the search sampling target and track the sampling target. And methods for tasks such as planning a route and sampling along the planned route. Background technique [0002] Due to its mobility and reproducibility, mobile robots can replace humans to perform tasks such as reconnaissance, search and rescue, and operations in complex, dangerous, and environmentally constrained environments. They can largely ignore terrain constraints and reduce manpower. Cost,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05D1/02
CPCG05D1/0242G05D1/0253G05D1/0257G05D1/0223G05D1/0214G05D1/0221G05D1/0276
Inventor 许可乐王怀民冯大为高梓健丁博刘惠贾宏达
Owner NAT UNIV OF DEFENSE TECH