Robot global path planning method based on deeply enhanced learning

A technology of global path planning and reinforcement learning, applied in the directions of instruments, two-dimensional position/course control, vehicle position/route/altitude control, etc. And other issues

Active Publication Date: 2017-08-18
TSINGHUA UNIV
View PDF9 Cites 81 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in many practical application scenarios, we cannot build high-quality global maps, and we do not even have the conditions to enter the scene in advance to build a global map
Therefore, a variety of limiting factors lead to a huge workload i

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
  • Robot global path planning method based on deeply enhanced learning
  • Robot global path planning method based on deeply enhanced learning
  • Robot global path planning method based on deeply enhanced learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] A global path planning method for a robot based on deep reinforcement learning proposed by the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0068] A global path planning method for a robot based on deep reinforcement learning proposed by the present invention is divided into two stages, a training stage and an execution stage, including the following steps:

[0069] 1) Training phase; the process is as follows figure 1 As shown, the specific steps are as follows:

[0070] 1-1) Install a top-down camera in the scene where the global path planning of the robot is required;

[0071] The distance h from the ground in the scene where the global path planning of the robot is required g (The value range is 2m to 3.5m, and the distance in this example is 2.8m). The overhead camera is installed on the roof (there is no special requirement for the model of the overhead camera, and the produ...

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 proposes a robot global path planning method based on deeply enhanced learning, which belongs to the robot learning and global path planning technology fields. The method comprises: in the training session: firstly, installing a top-view camera in a scenario; constructing a deep neural network; after a training path is created, outputting the executing actions by the deep neural network according to the images photographed by the camera; and according to the execution effect of the actions, optimizing the parameters of the deep neural network; then, updating the position of a target; performing different path planning trainings to obtain a final deep neural network; and in the execution session: outputting the executing actions for the robot by the final deep neural network according to the images photographed by the camera so that the robot executes the actions; and if the robot reaches the position of the target after its execution of the actions, then, completing the global path planning by the robot. The method of the invention is very practical in use, does not require manual participation, or the entrance of a scenario for constructing an environment map in advance. The method can be applied to multiple scenarios at a low cost.

Description

technical field [0001] The invention relates to a robot global path planning method based on deep reinforcement learning, which belongs to the field of machine learning and the technical field of global path planning. Background technique [0002] In recent years, robotics has become one of the rapidly developing important industries in the high-tech field, and global path planning technology is an important field of robotics research. A good robot global path planning technology can reduce the robot's working time, reduce energy consumption, improve the working efficiency of the robot, and improve the quality of human life. For example, in some accident sites where the environment is harsh and it is difficult for humans to reach, good global path planning technology can enable the rescue robot to cross obstacles to reach the target location to carry out rescue tasks; in family life, the "eyes" and "ears" of the service robot can understand the home environment , from one r...

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
IPC IPC(8): G05D1/02
CPCG05D1/0253G05D1/0276
Inventor 刘华平韩建晖王博文孙富春
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap