AGV space obstacle avoidance method and system based on 3D vision

An obstacle avoidance and 3D technology, applied in the field of computer vision, can solve the problems of large amount of data calculation, poor accuracy, and poor real-time detection of obstacle avoidance.

Pending Publication Date: 2020-07-07
BLUESWORD INTELLIGENT TECH CO LTD
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the upgrading of the factory and the increase in the complexity of the working environment, objects of different heights and shapes appear on the work site. Since it is difficult for 2D planar laser sensors to detect such 3D obstacles, this has become an important factor limiting the use of AGVs.
The inventors found that most of the exis

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
  • AGV space obstacle avoidance method and system based on 3D vision
  • AGV space obstacle avoidance method and system based on 3D vision
  • AGV space obstacle avoidance method and system based on 3D vision

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0031] Example one

[0032] Such as figure 1 As shown, this embodiment provides a 3D vision-based AGV space obstacle avoidance method, which includes:

[0033] Step 1: Within the preset distance threshold of the current position of the AGV, determine whether there is obstacle 3D point cloud information in the forward direction of the AGV preset track. If not, the AGV operates normally; otherwise, the AGV enters the obstacle avoidance state.

[0034] In specific implementation, the current position and heading direction of the AGV are obtained based on real-time received AGV pose information. Among them, the AGV pose information includes the real-time position and velocity of the AGV.

[0035] For example: at time t, the AGV pose information includes the position p and velocity v of the AGV. Among them, the position p and velocity v of the AGV are both vectors, and they are in the same global coordinate system.

[0036] In this embodiment, within the preset distance threshold range of ...

Example Embodiment

[0060] Example two

[0061] This embodiment provides a 3D vision-based AGV space obstacle avoidance system, which includes:

[0062] (1) Obstacle judgment module, which is used to judge whether there is obstacle 3D point cloud information in the forward direction of the AGV preset track within the preset distance threshold range of the current position of the AGV, if not, the AGV operates normally; Otherwise, the AGV enters the obstacle avoidance state.

[0063] In specific implementation, the current position and heading direction of the AGV are obtained based on real-time received AGV pose information. Among them, the AGV pose information includes the real-time position and velocity of the AGV. For example: at time t, the AGV pose information includes the position p and velocity v of the AGV.

[0064] In this embodiment, within the preset distance threshold range of the current position of the AGV, it is determined whether there is obstacle 3D point cloud information in the forwar...

Example Embodiment

[0088] Example three

[0089] This embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps in the 3D vision-based AGV space obstacle avoidance method as described in the first embodiment are implemented.

[0090] This embodiment determines whether there is obstacle 3D point cloud information in the forward direction of the AGV preset track within the preset distance threshold range of the current position of the AGV, which can narrow the obstacle detection range, reduce the amount of data calculation, and improve obstacle avoidance detection Real-time.

[0091] According to the obstacle 3D point cloud information, this embodiment parses out the shape, size and position of each obstacle, and then obtains accurate information of the obstacle. In order to judge the state of the obstacle, the accurate data basis is improved, which is beneficial to improve the AGV. The accuracy of space obsta...

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 belongs to the technical field of computer vision, and provides an AGV space obstacle avoidance method based on 3D vision. The obstacle avoidance method comprises the steps: judging whether obstacle 3D point cloud information exists in the advancing direction of a preset track of the AGV or not within the preset distance threshold range of the current position of the AGV: if not, determining that the AGV operates normally, otherwise, enabling the AGV to enter an obstacle avoidance state; when the AGV enters an obstacle avoidance state, analyzing the shape, size and position of the obstacle based on the 3D point cloud information of the obstacle, and then calculating the speed of the obstacle in a global coordinate system according to the 3D point cloud information sampling period; obtaining the state of the obstacle based on a pre-trained support vector machine, and enabling the AGV to execute a temporary obstacle avoidance path matched with the current obstacle state from a preset obstacle avoidance execution position according to the shape, size and position of the obstacle. Obstacle avoidance precision and AGV stability can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an AGV space obstacle avoidance method and system based on 3D vision. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the advancement of technology, AGV (Automated Guided Vehicle) is increasingly used in warehousing, logistics, and manufacturing sites, which greatly improves the efficiency of cargo handling. Obstacle avoidance is one of the foundations for AGV to realize unmanned automatic driving. Its function is to detect obstacles in automatic driving and avoid collisions between AGV and obstacles. [0004] At present, the sensors used to detect obstacles on AGV mostly use 2D planar laser sensors, which are installed horizontally on the AGV, and can only detect whether there are obstacles on a certain height plane. ...

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
CPCG05D1/024G05D1/0251G05D1/0223G05D1/0221G05D1/0276G05D2201/02
Inventor 孙文侠徐光运张小艺刘鹏张贻弓沈长鹏
Owner BLUESWORD INTELLIGENT TECH CO LTD
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