Multi-robot cooperative multi-target sampling method for open scene
A multi-robot and robotic technology, applied in the direction of instruments, two-dimensional position/channel control, non-electric variable control, etc., to achieve the effect of saving time and cost
Active Publication Date: 2021-07-30
NAT UNIV OF DEFENSE TECH
View PDF12 Cites 4 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0122] figure 2 It is an overall flow chart of the present invention. Such as 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 motion module).
[0124] Such as 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, ...
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
Login to View More Abstract
The invention discloses a multi-robot cooperative multi-target sampling method for an open scene. According to the technical scheme. A multi-robot system composed of N robot nodes and a cloud server node is constructed, and each robot node is provided with a communication module I, a detection module, a calculation module, a storage module I and a motion module; a communication module II and a storage module II are installed on the cloud server node. The method comprises steps of constructing a multi-target sampling scene, and pre-training the N robot node simulation models to obtain N.data parameter format files recording a collaborative multi-target sampling strategy of the robot in the corresponding simulation scene; deploying the multi-robot system in a real open scene, and training by utilizing a. Data parameter format file to obtain a multi-robot autonomous cooperative multi-target sampling strategy; and enabling the multi-robot system to cooperatively complete a multi-target sampling task according to the sampling strategy. According to the method, the problems of low timeliness, large training data volume, long training time, strong task correlation and the like of the existing multi-target sampling method can be solved.
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
Login to View More Patent Type & Authority Applications(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