Supercharge Your Innovation With Domain-Expert AI Agents!

Robot obstacle avoidance system based on safety reinforcement learning and visual sensor

A visual sensor and reinforcement learning technology, applied in control/regulation systems, instruments, two-dimensional position/course control, etc.

Active Publication Date: 2021-09-07
JINAN UNIVERSITY
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in many real-world domains, it may not be acceptable to give agents complete freedom

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 obstacle avoidance system based on safety reinforcement learning and visual sensor
  • Robot obstacle avoidance system based on safety reinforcement learning and visual sensor
  • Robot obstacle avoidance system based on safety reinforcement learning and visual sensor

Examples

Experimental program
Comparison scheme
Effect test

example

[0096] Example analysis: For example, to complete the process of charging the intelligent sweeping robot back to the seat: in the construction of the model training module, we can first build a virtual obstacle simulation environment on the gym, that is, configure the obstacles that may appear during the process, such as Randomly placed chairs and tables in the living room; set up the initial convolutional neural network model, in which the first convolutional layer uses 32 one-dimensional convolutional kernels with a size of 5 and a step size of 2. This layer uses ReLU is used as the activation function. The second convolutional layer uses 16 one-dimensional convolutional kernels of size 3 and stride 2 for further feature extraction, using two fully connected layers with 256 units and 128 units respectively. The activation function used by the two fully connected layers is also ReLU, and the final output layer uses sigmoid and tanh as the activation function for the linear ve...

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 robot obstacle avoidance system based on safety reinforcement learning and a visual sensor, and the system comprises a convolutional neural network module, wherein the convolutional neural network module comprises a long short term memory unit, a LSTM adding unit, a first convolution layer, a second convolution layer, a first full-connecting layer, a second full-connecting layer and an output layer. According to the system, enhancement of the reinforcement learning algorithm is adopted, so that multi-dimensional, continuous and multi-constraint problems can be well converged in a trust domain, and many problems of the conventional reinforcement learning algorithm with constraints are solved. The production safety can be greatly improved, the system can be universally applied to dangerous work in different occasions, and the operation safety and accuracy are improved while labor force is liberated.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and mainly relates to the application of safety reinforcement learning algorithms in artificial intelligence to robot obstacle avoidance problems, in particular to a robot obstacle avoidance system based on safety reinforcement learning and visual sensors. Background technique [0002] In recent years, with the continuous development of science and technology, intelligent robots have been used in many fields, including industrial production, military, disaster relief, etc., which involve environmental perception, dynamic decision-making and planning, automatic control and other technologies. At the same time, various social problems have emerged in recent years, such as declining labor force, rising production costs, low automation production efficiency, unfinished industrial transformation, and increasingly serious social aging. The application of robots in the market can effectively allev...

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 Applications(China)
IPC IPC(8): G05D1/02
CPCG05D1/024G05D1/0251G05D1/0214G05D1/0221G05D1/0276
Inventor 郭洪飞陈世帆曾云辉何睿潼姜涛廖丁为何智慧任亚平张锐
Owner JINAN UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com