Production line mobile robot aggregation type recovery warehousing simulation method and system

A mobile robot and simulation method technology, which is applied in the field of production line mobile robot aggregated return-to-warehouse simulation, can solve the problems that the control effect depends on the richness of training samples, cannot effectively deal with environmental diversity and various changes, and learn experience.

Active Publication Date: 2021-07-13
UNIV OF JINAN
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventors found that most of the existing control methods use the reinforcement learning control algorithm to make the agent learn the motion control strategy for the collective recovery and storage of mobile robots, but so far there is no simple and stable multi-agent cluster control At the same time, the existing methods based on deep reinforcement learning need to use self-explored samples for the agent to learn, and cannot learn from the environment independently and explore the unknown by itself. environment, which leads to its control effect heavily dependent on the richness of training samples, unable to effectively deal with the diversity and changes of the environment

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
  • Production line mobile robot aggregation type recovery warehousing simulation method and system
  • Production line mobile robot aggregation type recovery warehousing simulation method and system
  • Production line mobile robot aggregation type recovery warehousing simulation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] The purpose of this embodiment is to provide a method for simulating collection and warehousing of mobile robots in a production line.

[0043] A method for simulating the collection and warehousing of mobile robots in a production line, comprising:

[0044] Based on the scene information and the parameter information of the mobile robot, a kinematics model for the recovery and storage of the mobile robot is established;

[0045] Each mobile robot selects the storage location in the library as the target, uses the pre-trained improved deep deterministic policy gradient model to generate the optimal behavior strategy for each mobile robot, and realizes the recycling of the mobile robot through the control of force and speed;

[0046] Among them, the improved deep deterministic policy gradient model includes an actor network and a critic network, through the reward function mechanism based on the improved artificial potential energy function, the reward between agents is ...

Embodiment 2

[0087] The purpose of this embodiment is to provide a simulation system for collecting and warehousing of mobile robots in a production line.

[0088] A method for simulating the collection and warehousing of mobile robots in a production line, comprising:

[0089] A motion model construction unit, which is used to establish a recovery kinematics model for the mobile robot based on scene information and mobile robot parameter information;

[0090] The path planning unit is used for each mobile robot to select the storage location in the library as the target, and uses the pre-trained improved deep deterministic policy gradient model to generate the optimal behavior strategy for each mobile robot, and realizes the mobile robot through the control of force and speed. recycling;

[0091] Among them, the improved deep deterministic policy gradient model includes an actor network and a critic network, through the reward function mechanism based on the improved artificial potential...

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 provides a production line mobile robot aggregation type recovery warehousing simulation method and system, and the method comprises the steps that an improved artificial potential energy function mechanism is added into a depth deterministic strategy gradient algorithm, and the design of a reward function mechanism of an intelligent agent is achieved in the depth deterministic strategy gradient algorithm; through a reward mechanism based on an improved artificial potential energy function, the agents can learn clustering actions with high rewards, and then the clustering effect of the multiple agents is achieved; and specific agent local communication information is added into a criticer neural network module of a depth deterministic gradient algorithm, so that the agents can better judge the surrounding environment, and the agents can learn a better cluster strategy to realize warehousing and recycling.

Description

technical field [0001] The disclosure belongs to the technical field of motion control of intelligent mobile robots, and in particular relates to a simulation method and system for gathering type recycling and storage of mobile robots in a production line. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] At this stage, with the rapid development of artificial intelligence technology, reinforcement learning algorithms are used to solve many complex problems in real life. Single-agent systems are difficult to solve, and even if they can be solved, they will be limited in terms of speed and reliability. Therefore, using multiple agents to cooperate with each other can complete higher-level tasks. After multiple agents on the production line have completed their tasks, it is necessary to realize the aggregated recycling of mobile robots on th...

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 & AuthorityApplications(China)
IPC IPC(8): G05B17/02
CPCG05B17/02
Inventor张涵程金王琪琪王中华
OwnerUNIV OF JINAN