Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A task assignment method based on deep learning inference for resource-constrained robots

A deep learning and task allocation technology, applied in the direction of resource allocation, instruments, electrical and digital data processing, etc., can solve the problem that the unknown characteristics of multi-robot system resources are not considered, the robot cannot be clearly known, and more work cannot be allocated to those with stronger abilities. It can reduce the data transmission delay, reduce the data transmission overhead, and optimize the execution time.

Active Publication Date: 2021-06-18
NAT UNIV OF DEFENSE TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

3) Unknown capabilities: In a multi-robot system, the capabilities of the robots cannot be clearly known, so more work cannot be assigned to more capable nodes
However, this solution is only for homogeneous robots, and only considers the resource-constrained characteristics of robots, without considering the more computing power and unequal resources faced by heterogeneous robots, and this solution does not consider multi-robots The unknown characteristics of resources in the system are based on the number of isomorphic robots to divide and assign tasks based on deep learning classification tasks
At present, there is no public technical solution related to the deep learning-based engineering task assignment method based on heterogeneous robots

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 task assignment method based on deep learning inference for resource-constrained robots
  • A task assignment method based on deep learning inference for resource-constrained robots
  • A task assignment method based on deep learning inference for resource-constrained robots

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] image 3 It is an overall flow chart of the present invention. Such as image 3 Shown, the present invention comprises the following steps:

[0091] The first step is to build a task distribution system composed of multiple robot nodes. Such as figure 1 As shown, the task distribution system is composed of various heterogeneous robot nodes (such as drones, ground robots, humanoid robots, etc.), and these heterogeneous robot nodes are interconnected through WIFI.

[0092] Robot nodes are divided into task robot nodes and collaborative robot nodes according to their functions. The task robot node refers to the initiator of the robot engineering task based on deep learning. The task robot node interacts with complex and harsh environments such as earthquake relief, mountainous areas, and floods to collect environmental data; the collaborative robot node refers to the rest of the robots in the robot environment. Responsible for supporting task robots and cooperating w...

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 a task allocation method based on deep learning reasoning of a resource-limited robot, and aims to realize the task allocation of a multi-robot system to robot engineering tasks. The technical solution is to build a task allocation system, build a layer prediction model and store it on the robot; the task robot collects environmental data, the model interpretation module extracts the model layer type and related parameter configuration, and the resource consumption estimation sub-module estimates the level of each robot based on the layer prediction model. The delay of each layer of the deep learning model; the resource availability sub-module queries the resource status of the task allocation system; the decision-making module determines the optimal task allocation plan, and allocates engineering tasks to the robot nodes according to the optimal task allocation plan; The task allocation plan carries out the execution of engineering tasks. The invention can coordinate engineering task allocation between heterogeneous robots according to the task allocation system resource state, and optimize the execution time of the engineering task.

Description

technical field [0001] The present invention relates to the field of robot distribution and multi-robot task assignment, and specifically relates to the realization of the engineering task assignment of multiple resource-limited robots based on the idea of ​​model division based on the collective processing capability of multi-cooperative resource-limited robots, so that the limited robots Groups can cooperate to complete engineering tasks that traditional single robots cannot complete (ie, engineering tasks that require deep learning). Background technique [0002] A robot is a "physical agent that completes tasks by manipulating the physical world", and has the ability to interact with the physical world similar to human beings, and even surpasses human beings in some aspects. However, just like a single individual, a single robot system has been unable to meet the increasingly complex task requirements of modern society due to its own limitations in perception and process...

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): G06F9/50
CPCG06F9/5027
Inventor 丁博刘惠王怀民怀智博史佩昌初宁骆杰贾宏达巩旭东耿铭阳
Owner NAT UNIV OF DEFENSE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products