Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent obstacle avoidance method based on deep learning

An intelligent obstacle avoidance and deep learning technology, applied in two-dimensional position/channel control, vehicle position/route/altitude control, non-electric variable control, etc., can solve the problem of no effective obstacle avoidance method in the substation environment, threatening the life of the staff Safety, increase labor costs and other issues, to achieve the effect of reducing life threats, improving intelligence, and reducing labor costs

Pending Publication Date: 2020-08-11
STATE GRID SICHUAN ELECTRIC POWER CORP ELECTRIC POWER RES INST
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The stable operation of the substation is inseparable from its daily inspection. The traditional manual inspection method has the following problems: First, the substation needs long-term inspection throughout the year, and some bad weather can easily threaten the safety of staff
Second, inspection tasks require staff to have extremely high work experience, because missed inspections caused by lack of experience will leave serious safety hazards
Third, most of the large substations are located in the suburbs with inconvenient transportation and living conditions, which further increases labor costs
[0005] Traditional inspection robots need to navigate autonomously in complex outdoor environments, but there is currently no effective obstacle avoidance method for substation environments with too many weeds

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
  • Intelligent obstacle avoidance method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] A method for intelligent obstacle avoidance based on deep learning, the steps are as follows:

[0022] Step 1: Train the neural network model for substation-specific obstacle detection, and rate the risk of obstacles;

[0023] Step 2: Put the trained inspection robot into the substation environment, and conduct inspection based on the neural network model;

[0024] Step 3: When an obstacle triggers an alarm from the inspection robot, call the neural network model for detection, detect different obstacles, and control the inspection robot in different ways.

[0025] When the inspection robot is driving normally, when the ultrasonic radar on the front of the car detects an obstacle within 1 meter in front, the inspection robot stops immediately, controls the camera to take pictures of the front to obtain pictures, and divides the width into the width of the body and the length of the front. The picture of the 1-meter area of ​​interest is sent to the neural network model...

Embodiment 2

[0027] On the basis of Embodiment 1, the neural network model described in step 1 needs to be trained from a large number of substation image data samples, so that the model can cope with various road conditions of the substation.

Embodiment 3

[0029] On the basis of Embodiment 1, the substation environment described in step 2 refers to a section of road containing obstacles such as weeds and gravel.

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 relates to an intelligent obstacle avoidance method based on deep learning, and the method comprises the steps: 1, training a neural network model for the detection of a specific obstacle of a transformer substation, and carrying out the risk rating of the obstacle; 2, putting the trained inspection robot into a transformer substation environment, and carrying out inspection based ona neural network model; and 3, when the obstacle triggers the inspection robot to give an alarm, calling the neural network model for detection, detecting different obstacles, and controlling the inspection robot in different modes. The invention provides an intelligent obstacle avoidance method based on deep learning, manual inspection is replaced by inspection robots, leak inspection is avoided, and labor cost is reduced. According to the method for training the transformer substation inspection robot based on the neural network model, the obstacle avoidance mode of a traditional inspectionrobot is changed, the obstacle avoidance intelligence of the inspection robot is greatly improved, and the inspection range of the inspection robot is expanded.

Description

technical field [0001] The invention belongs to the field of machine technology, in particular to an intelligent obstacle avoidance method based on deep learning. Background technique [0002] With the rapid development of the whole society, people's life is increasingly inseparable from electricity, and the demand for electricity is increasing, so the number of substations has risen sharply. The substation is an important part of electricity supply, and the long-term and stable operation of the substation is a prerequisite for ensuring the smooth supply of electric energy. [0003] The stable operation of the substation is inseparable from its daily inspection. The traditional manual inspection method has the following problems: First, the substation needs long-term inspection throughout the year, and some severe weather can easily threaten the safety of staff. Second, the patrol inspection task requires the staff to have extremely high work experience, because missed insp...

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
CPCG05D1/024G05D1/0246G05D1/0255G05D1/0257G05D1/0214G05D1/0221G05D1/0276
Inventor 刘益岑范松海龚奕宇刘小江马小敏罗磊吴天宝
Owner STATE GRID SICHUAN ELECTRIC POWER CORP ELECTRIC POWER RES INST