Inspection robot navigation method based on deep reinforcement learning
The invention discloses an inspection robot navigation method based on deep reinforcement learning, and relates to the technical field of security inspection intelligence. According to the invention, the robot inspection environment is sensed only by using specially processed laser radar data and od...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | LIU JUN WANG PEII WANG JIA XU FENGHUO YANG HAOBO LUO YUHANG ZHANG JIAN HUANG BO LIU XIANG DENG JIALING WANG QIANG LUO YANGSEN ZHOU CHONGSHAN JIANG MINGYU WU JUNQI LI HANG XU RONGCHUAN FENG YANYING GAKU YASUHITO XIE JIACHENG SHANG ZHIYU YAN JIAWEI |
| description | The invention discloses an inspection robot navigation method based on deep reinforcement learning, and relates to the technical field of security inspection intelligence. According to the invention, the robot inspection environment is sensed only by using specially processed laser radar data and odometer data, compared with depth camera and radar fusion data, the hardware calculation cost is reduced, the difference with the real environment is also reduced, and a navigation decision model is easier to deploy and higher in applicability; the invention provides an improved Actor and Critic network, an LSTM layer is added in the Actor and Critic network, the relationship among action information of recent several time steps is extracted, and the final execution action is optimized, so that the moving action of the inspection robot is smoother, and a smoother navigation path is generated.
本发明公开了一种基于深度强化学习的巡检机器人导航方法，涉及安防巡检智能化技术领域。本发明仅利用经过特殊处理的激光雷达数据和里程计数据对机器人巡检环境进行感知，与基于深度相机与雷达融合数据相比，减少硬件计算成本的同时也减少了与现实环境的差距，使导航决策 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118670392A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118670392A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118670392A3</originalsourceid><addsrcrecordid>eNrjZHD3zCsuSE0uyczPUyjKT8ovUchLLMtMTwQL5KaWZOSnKCQlFqemKAD5KampBQpFqZl5aflFyam5qXklCjmpiUV5mXnpPAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbggMTk1L7Uk3tnP0NDCzNzA2NLI0ZgYNQChjTRm</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Inspection robot navigation method based on deep reinforcement learning</title><source>esp@cenet</source><creator>LIU JUN ; WANG PEII ; WANG JIA ; XU FENGHUO ; YANG HAOBO ; LUO YUHANG ; ZHANG JIAN ; HUANG BO ; LIU XIANG ; DENG JIALING ; WANG QIANG ; LUO YANGSEN ; ZHOU CHONGSHAN ; JIANG MINGYU ; WU JUNQI ; LI HANG ; XU RONGCHUAN ; FENG YANYING ; GAKU YASUHITO ; XIE JIACHENG ; SHANG ZHIYU ; YAN JIAWEI</creator><creatorcontrib>LIU JUN ; WANG PEII ; WANG JIA ; XU FENGHUO ; YANG HAOBO ; LUO YUHANG ; ZHANG JIAN ; HUANG BO ; LIU XIANG ; DENG JIALING ; WANG QIANG ; LUO YANGSEN ; ZHOU CHONGSHAN ; JIANG MINGYU ; WU JUNQI ; LI HANG ; XU RONGCHUAN ; FENG YANYING ; GAKU YASUHITO ; XIE JIACHENG ; SHANG ZHIYU ; YAN JIAWEI</creatorcontrib><description>The invention discloses an inspection robot navigation method based on deep reinforcement learning, and relates to the technical field of security inspection intelligence. According to the invention, the robot inspection environment is sensed only by using specially processed laser radar data and odometer data, compared with depth camera and radar fusion data, the hardware calculation cost is reduced, the difference with the real environment is also reduced, and a navigation decision model is easier to deploy and higher in applicability; the invention provides an improved Actor and Critic network, an LSTM layer is added in the Actor and Critic network, the relationship among action information of recent several time steps is extracted, and the final execution action is optimized, so that the moving action of the inspection robot is smoother, and a smoother navigation path is generated.
本发明公开了一种基于深度强化学习的巡检机器人导航方法，涉及安防巡检智能化技术领域。本发明仅利用经过特殊处理的激光雷达数据和里程计数据对机器人巡检环境进行感知，与基于深度相机与雷达融合数据相比，减少硬件计算成本的同时也减少了与现实环境的差距，使导航决策</description><language>chi ; eng</language><subject>ANALOGOUS ARRANGEMENTS USING OTHER WAVES ; CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES ; GYROSCOPIC INSTRUMENTS ; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES ; MEASURING ; MEASURING DISTANCES, LEVELS OR BEARINGS ; NAVIGATION ; PHOTOGRAMMETRY OR VIDEOGRAMMETRY ; PHYSICS ; RADIO DIRECTION-FINDING ; RADIO NAVIGATION ; SURVEYING ; TESTING</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240920&DB=EPODOC&CC=CN&NR=118670392A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240920&DB=EPODOC&CC=CN&NR=118670392A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU JUN</creatorcontrib><creatorcontrib>WANG PEII</creatorcontrib><creatorcontrib>WANG JIA</creatorcontrib><creatorcontrib>XU FENGHUO</creatorcontrib><creatorcontrib>YANG HAOBO</creatorcontrib><creatorcontrib>LUO YUHANG</creatorcontrib><creatorcontrib>ZHANG JIAN</creatorcontrib><creatorcontrib>HUANG BO</creatorcontrib><creatorcontrib>LIU XIANG</creatorcontrib><creatorcontrib>DENG JIALING</creatorcontrib><creatorcontrib>WANG QIANG</creatorcontrib><creatorcontrib>LUO YANGSEN</creatorcontrib><creatorcontrib>ZHOU CHONGSHAN</creatorcontrib><creatorcontrib>JIANG MINGYU</creatorcontrib><creatorcontrib>WU JUNQI</creatorcontrib><creatorcontrib>LI HANG</creatorcontrib><creatorcontrib>XU RONGCHUAN</creatorcontrib><creatorcontrib>FENG YANYING</creatorcontrib><creatorcontrib>GAKU YASUHITO</creatorcontrib><creatorcontrib>XIE JIACHENG</creatorcontrib><creatorcontrib>SHANG ZHIYU</creatorcontrib><creatorcontrib>YAN JIAWEI</creatorcontrib><title>Inspection robot navigation method based on deep reinforcement learning</title><description>The invention discloses an inspection robot navigation method based on deep reinforcement learning, and relates to the technical field of security inspection intelligence. According to the invention, the robot inspection environment is sensed only by using specially processed laser radar data and odometer data, compared with depth camera and radar fusion data, the hardware calculation cost is reduced, the difference with the real environment is also reduced, and a navigation decision model is easier to deploy and higher in applicability; the invention provides an improved Actor and Critic network, an LSTM layer is added in the Actor and Critic network, the relationship among action information of recent several time steps is extracted, and the final execution action is optimized, so that the moving action of the inspection robot is smoother, and a smoother navigation path is generated.
本发明公开了一种基于深度强化学习的巡检机器人导航方法，涉及安防巡检智能化技术领域。本发明仅利用经过特殊处理的激光雷达数据和里程计数据对机器人巡检环境进行感知，与基于深度相机与雷达融合数据相比，减少硬件计算成本的同时也减少了与现实环境的差距，使导航决策</description><subject>ANALOGOUS ARRANGEMENTS USING OTHER WAVES</subject><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES</subject><subject>GYROSCOPIC INSTRUMENTS</subject><subject>LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES</subject><subject>MEASURING</subject><subject>MEASURING DISTANCES, LEVELS OR BEARINGS</subject><subject>NAVIGATION</subject><subject>PHOTOGRAMMETRY OR VIDEOGRAMMETRY</subject><subject>PHYSICS</subject><subject>RADIO DIRECTION-FINDING</subject><subject>RADIO NAVIGATION</subject><subject>SURVEYING</subject><subject>TESTING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHD3zCsuSE0uyczPUyjKT8ovUchLLMtMTwQL5KaWZOSnKCQlFqemKAD5KampBQpFqZl5aflFyam5qXklCjmpiUV5mXnpPAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbggMTk1L7Uk3tnP0NDCzNzA2NLI0ZgYNQChjTRm</recordid><startdate>20240920</startdate><enddate>20240920</enddate><creator>LIU JUN</creator><creator>WANG PEII</creator><creator>WANG JIA</creator><creator>XU FENGHUO</creator><creator>YANG HAOBO</creator><creator>LUO YUHANG</creator><creator>ZHANG JIAN</creator><creator>HUANG BO</creator><creator>LIU XIANG</creator><creator>DENG JIALING</creator><creator>WANG QIANG</creator><creator>LUO YANGSEN</creator><creator>ZHOU CHONGSHAN</creator><creator>JIANG MINGYU</creator><creator>WU JUNQI</creator><creator>LI HANG</creator><creator>XU RONGCHUAN</creator><creator>FENG YANYING</creator><creator>GAKU YASUHITO</creator><creator>XIE JIACHENG</creator><creator>SHANG ZHIYU</creator><creator>YAN JIAWEI</creator><scope>EVB</scope></search><sort><creationdate>20240920</creationdate><title>Inspection robot navigation method based on deep reinforcement learning</title><author>LIU JUN ; WANG PEII ; WANG JIA ; XU FENGHUO ; YANG HAOBO ; LUO YUHANG ; ZHANG JIAN ; HUANG BO ; LIU XIANG ; DENG JIALING ; WANG QIANG ; LUO YANGSEN ; ZHOU CHONGSHAN ; JIANG MINGYU ; WU JUNQI ; LI HANG ; XU RONGCHUAN ; FENG YANYING ; GAKU YASUHITO ; XIE JIACHENG ; SHANG ZHIYU ; YAN JIAWEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118670392A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>ANALOGOUS ARRANGEMENTS USING OTHER WAVES</topic><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES</topic><topic>GYROSCOPIC INSTRUMENTS</topic><topic>LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES</topic><topic>MEASURING</topic><topic>MEASURING DISTANCES, LEVELS OR BEARINGS</topic><topic>NAVIGATION</topic><topic>PHOTOGRAMMETRY OR VIDEOGRAMMETRY</topic><topic>PHYSICS</topic><topic>RADIO DIRECTION-FINDING</topic><topic>RADIO NAVIGATION</topic><topic>SURVEYING</topic><topic>TESTING</topic><toplevel>online_resources</toplevel><creatorcontrib>LIU JUN</creatorcontrib><creatorcontrib>WANG PEII</creatorcontrib><creatorcontrib>WANG JIA</creatorcontrib><creatorcontrib>XU FENGHUO</creatorcontrib><creatorcontrib>YANG HAOBO</creatorcontrib><creatorcontrib>LUO YUHANG</creatorcontrib><creatorcontrib>ZHANG JIAN</creatorcontrib><creatorcontrib>HUANG BO</creatorcontrib><creatorcontrib>LIU XIANG</creatorcontrib><creatorcontrib>DENG JIALING</creatorcontrib><creatorcontrib>WANG QIANG</creatorcontrib><creatorcontrib>LUO YANGSEN</creatorcontrib><creatorcontrib>ZHOU CHONGSHAN</creatorcontrib><creatorcontrib>JIANG MINGYU</creatorcontrib><creatorcontrib>WU JUNQI</creatorcontrib><creatorcontrib>LI HANG</creatorcontrib><creatorcontrib>XU RONGCHUAN</creatorcontrib><creatorcontrib>FENG YANYING</creatorcontrib><creatorcontrib>GAKU YASUHITO</creatorcontrib><creatorcontrib>XIE JIACHENG</creatorcontrib><creatorcontrib>SHANG ZHIYU</creatorcontrib><creatorcontrib>YAN JIAWEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU JUN</au><au>WANG PEII</au><au>WANG JIA</au><au>XU FENGHUO</au><au>YANG HAOBO</au><au>LUO YUHANG</au><au>ZHANG JIAN</au><au>HUANG BO</au><au>LIU XIANG</au><au>DENG JIALING</au><au>WANG QIANG</au><au>LUO YANGSEN</au><au>ZHOU CHONGSHAN</au><au>JIANG MINGYU</au><au>WU JUNQI</au><au>LI HANG</au><au>XU RONGCHUAN</au><au>FENG YANYING</au><au>GAKU YASUHITO</au><au>XIE JIACHENG</au><au>SHANG ZHIYU</au><au>YAN JIAWEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Inspection robot navigation method based on deep reinforcement learning</title><date>2024-09-20</date><risdate>2024</risdate><abstract>The invention discloses an inspection robot navigation method based on deep reinforcement learning, and relates to the technical field of security inspection intelligence. According to the invention, the robot inspection environment is sensed only by using specially processed laser radar data and odometer data, compared with depth camera and radar fusion data, the hardware calculation cost is reduced, the difference with the real environment is also reduced, and a navigation decision model is easier to deploy and higher in applicability; the invention provides an improved Actor and Critic network, an LSTM layer is added in the Actor and Critic network, the relationship among action information of recent several time steps is extracted, and the final execution action is optimized, so that the moving action of the inspection robot is smoother, and a smoother navigation path is generated.
本发明公开了一种基于深度强化学习的巡检机器人导航方法，涉及安防巡检智能化技术领域。本发明仅利用经过特殊处理的激光雷达数据和里程计数据对机器人巡检环境进行感知，与基于深度相机与雷达融合数据相比，减少硬件计算成本的同时也减少了与现实环境的差距，使导航决策</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118670392A |
| source | esp@cenet |
| subjects | ANALOGOUS ARRANGEMENTS USING OTHER WAVES CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES GYROSCOPIC INSTRUMENTS LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES MEASURING MEASURING DISTANCES, LEVELS OR BEARINGS NAVIGATION PHOTOGRAMMETRY OR VIDEOGRAMMETRY PHYSICS RADIO DIRECTION-FINDING RADIO NAVIGATION SURVEYING TESTING |
| title | Inspection robot navigation method based on deep reinforcement learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T09%3A35%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LIU%20JUN&rft.date=2024-09-20&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118670392A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |