A Deep Learning and Depth Image based Obstacle Detection and Distance Measurement Method for Substation Patrol Robot

Author:

Hongsheng Xu,Tianyu Chen,Qipei Zhang,Jixiang Lu,Zhihong Yang

Abstract

Abstract Recently, substation patrol robot is gradually used to replace the manual inspection in order to improve the inspection efficiency as well as security and automation level of substation maintenance. The research of obstacle avoidance is a hot spot in substation intelligent patrol robot area. The emerging new generation of artificial intelligence (AI) technology provides a new way to solve the obstacle detection and distance measurement problem. To realize accurate, effective and real-time response to the environmental changes, a novel obstacle avoidance method based on deep learning and depth image is proposed. The core of this method is pixel-level instance segmentation between obstacles and roads, along with a pixel-level matching of obstacles’ segmentation mask and depth data. The effectiveness of the proposed method is validated by actual tests in real substation environment.

Publisher

IOP Publishing

Subject

General Engineering

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Stereo-image-based ground-line prediction and obstacle detection;Turkish Journal of Electrical Engineering and Computer Sciences;2024-05-20

2. Recognition, location, and depth estimation of objects in electrical substations;2023 Latin American Robotics Symposium (LARS), 2023 Brazilian Symposium on Robotics (SBR), and 2023 Workshop on Robotics in Education (WRE);2023-10-09

3. Research on Multi Machine Cooperative Autonomous Inspection Strategy for UHV Dense Transmission Channel Based on 5G Technology;Journal of Sensors;2022-08-25

4. Improved Path Planning for Indoor Patrol Robot Based on Deep Reinforcement Learning;Symmetry;2022-01-11

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3