VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS
Disclosed is a method for generating a virtual lane for assisting autonomous driving, the method comprising the steps of: deriving a driving history by accumulating driving data of at least one surrounding vehicle measured by a composite sensor according to the passage of time; classifying the drivi...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng ; fre ; kor |
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 | YI, Kyong Su KOH, Young Il YI, Zoo Hyeon |
description | Disclosed is a method for generating a virtual lane for assisting autonomous driving, the method comprising the steps of: deriving a driving history by accumulating driving data of at least one surrounding vehicle measured by a composite sensor according to the passage of time; classifying the driving history into at least one driving section according to a driving pattern on the basis of self-attention implemented by a convolutional neural network (CNN); deriving a weighted driving history of the at least one surrounding vehicle by assigning a weight to the at least one driving section on the basis of the self-attention; determining a driving trajectory of the at least one surrounding vehicle by performing curve fitting on the weighted driving history through the CNN; and generating a virtual lane on an HD map for assisting autonomous driving on the basis of the driving trajectory.
La divulgation concerne un procédé de génération d'une voie virtuelle destinée à aider à la conduite autonome, le procédé comprenant les étapes consistant : à déduire un historique de conduite au moyen de l'accumulation de données de conduite d'au moins un véhicule environnant mesurées par un capteur composite en fonction du passage du temps ; à classer l'historique de conduite en au moins une section de conduite selon un motif de conduite sur la base d'une attention automatique mise en œuvre par un réseau neuronal convolutionnel (CNN) ; à déduire un historique de conduite pondéré dudit véhicule environnant au moyen de l'attribution d'une pondération à ladite section de conduite sur la base de l'attention automatique ; à déterminer une trajectoire de conduite dudit véhicule environnant au moyen de la réalisation d'un réglage de courbe sur l'historique de conduite pondéré par le biais du CNN ; et à générer une voie virtuelle sur une carte HD pour aider à la conduite autonome sur la base de la trajectoire de conduite.
자율 주행을 보조하기 위한 가상 차선을 생성하는 방법에 있어서, 복합 센서에 의해 측정되는 적어도 하나의 주변 차량의 주행 데이터를 시간 흐름에 따라 누적하여 주행 히스토리를 도출하는 단계, CNN(convolutional neural network)에 의해 구현되는 셀프-어텐션(self-attention)에 기초하여 주행 히스토리를 주행 패턴에 따라 적어도 하나의 주행 구간으로 구분하는 단계, 셀프-어텐션에 기초하여 적어도 하나의 주행 구간에 가중치를 부여함으로써 적어도 하나의 주변 차량의 가중 주행 히스토리를 도출하는 단계, CNN을 통해 가중 주행 히스토리에 대한 커브 피팅을 수행하여 적어도 하나의 주변 차량의 주행 궤적을 결정하는 단계, 및 주행 궤적에 기초하여 자율 주행을 보조하기 위한 HD 맵 상에 가상 차선을 생성하는 단계를 포함하는 방법이 개시된다. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2021241834A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2021241834A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2021241834A13</originalsourceid><addsrcrecordid>eNqNjEsOgjAQhtm4MOodJnFtIuDC7dhOoQl0mlJgSYipK6MkeA7PbH0cwNX_5X8tk2ennW-xggoNQUGGHHrNBtBajNg2gEZCTb5kCSdsSEJMvUOltABVcQ_aKHb1d2bJCbIfjCZg69lwzfFGOt1pU8Q2oOzINQQ9oS_JgWAj9XvTrJPFZbzOYfPTVbJV5EW5C9N9CPM0nsMtPIaes32WZof0mB8wzf9rvQD9GUFE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS</title><source>esp@cenet</source><creator>YI, Kyong Su ; KOH, Young Il ; YI, Zoo Hyeon</creator><creatorcontrib>YI, Kyong Su ; KOH, Young Il ; YI, Zoo Hyeon</creatorcontrib><description>Disclosed is a method for generating a virtual lane for assisting autonomous driving, the method comprising the steps of: deriving a driving history by accumulating driving data of at least one surrounding vehicle measured by a composite sensor according to the passage of time; classifying the driving history into at least one driving section according to a driving pattern on the basis of self-attention implemented by a convolutional neural network (CNN); deriving a weighted driving history of the at least one surrounding vehicle by assigning a weight to the at least one driving section on the basis of the self-attention; determining a driving trajectory of the at least one surrounding vehicle by performing curve fitting on the weighted driving history through the CNN; and generating a virtual lane on an HD map for assisting autonomous driving on the basis of the driving trajectory.
La divulgation concerne un procédé de génération d'une voie virtuelle destinée à aider à la conduite autonome, le procédé comprenant les étapes consistant : à déduire un historique de conduite au moyen de l'accumulation de données de conduite d'au moins un véhicule environnant mesurées par un capteur composite en fonction du passage du temps ; à classer l'historique de conduite en au moins une section de conduite selon un motif de conduite sur la base d'une attention automatique mise en œuvre par un réseau neuronal convolutionnel (CNN) ; à déduire un historique de conduite pondéré dudit véhicule environnant au moyen de l'attribution d'une pondération à ladite section de conduite sur la base de l'attention automatique ; à déterminer une trajectoire de conduite dudit véhicule environnant au moyen de la réalisation d'un réglage de courbe sur l'historique de conduite pondéré par le biais du CNN ; et à générer une voie virtuelle sur une carte HD pour aider à la conduite autonome sur la base de la trajectoire de conduite.
자율 주행을 보조하기 위한 가상 차선을 생성하는 방법에 있어서, 복합 센서에 의해 측정되는 적어도 하나의 주변 차량의 주행 데이터를 시간 흐름에 따라 누적하여 주행 히스토리를 도출하는 단계, CNN(convolutional neural network)에 의해 구현되는 셀프-어텐션(self-attention)에 기초하여 주행 히스토리를 주행 패턴에 따라 적어도 하나의 주행 구간으로 구분하는 단계, 셀프-어텐션에 기초하여 적어도 하나의 주행 구간에 가중치를 부여함으로써 적어도 하나의 주변 차량의 가중 주행 히스토리를 도출하는 단계, CNN을 통해 가중 주행 히스토리에 대한 커브 피팅을 수행하여 적어도 하나의 주변 차량의 주행 궤적을 결정하는 단계, 및 주행 궤적에 기초하여 자율 주행을 보조하기 위한 HD 맵 상에 가상 차선을 생성하는 단계를 포함하는 방법이 개시된다.</description><language>eng ; fre ; kor</language><subject>ANALOGOUS ARRANGEMENTS USING OTHER WAVES ; CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION ; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES ; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES ; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES ; MEASURING ; PERFORMING OPERATIONS ; PHYSICS ; RADIO DIRECTION-FINDING ; RADIO NAVIGATION ; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT ; TESTING ; TRANSPORTING ; VEHICLES IN GENERAL ; VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR</subject><creationdate>2021</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=20211202&DB=EPODOC&CC=WO&NR=2021241834A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211202&DB=EPODOC&CC=WO&NR=2021241834A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YI, Kyong Su</creatorcontrib><creatorcontrib>KOH, Young Il</creatorcontrib><creatorcontrib>YI, Zoo Hyeon</creatorcontrib><title>VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS</title><description>Disclosed is a method for generating a virtual lane for assisting autonomous driving, the method comprising the steps of: deriving a driving history by accumulating driving data of at least one surrounding vehicle measured by a composite sensor according to the passage of time; classifying the driving history into at least one driving section according to a driving pattern on the basis of self-attention implemented by a convolutional neural network (CNN); deriving a weighted driving history of the at least one surrounding vehicle by assigning a weight to the at least one driving section on the basis of the self-attention; determining a driving trajectory of the at least one surrounding vehicle by performing curve fitting on the weighted driving history through the CNN; and generating a virtual lane on an HD map for assisting autonomous driving on the basis of the driving trajectory.
La divulgation concerne un procédé de génération d'une voie virtuelle destinée à aider à la conduite autonome, le procédé comprenant les étapes consistant : à déduire un historique de conduite au moyen de l'accumulation de données de conduite d'au moins un véhicule environnant mesurées par un capteur composite en fonction du passage du temps ; à classer l'historique de conduite en au moins une section de conduite selon un motif de conduite sur la base d'une attention automatique mise en œuvre par un réseau neuronal convolutionnel (CNN) ; à déduire un historique de conduite pondéré dudit véhicule environnant au moyen de l'attribution d'une pondération à ladite section de conduite sur la base de l'attention automatique ; à déterminer une trajectoire de conduite dudit véhicule environnant au moyen de la réalisation d'un réglage de courbe sur l'historique de conduite pondéré par le biais du CNN ; et à générer une voie virtuelle sur une carte HD pour aider à la conduite autonome sur la base de la trajectoire de conduite.
자율 주행을 보조하기 위한 가상 차선을 생성하는 방법에 있어서, 복합 센서에 의해 측정되는 적어도 하나의 주변 차량의 주행 데이터를 시간 흐름에 따라 누적하여 주행 히스토리를 도출하는 단계, CNN(convolutional neural network)에 의해 구현되는 셀프-어텐션(self-attention)에 기초하여 주행 히스토리를 주행 패턴에 따라 적어도 하나의 주행 구간으로 구분하는 단계, 셀프-어텐션에 기초하여 적어도 하나의 주행 구간에 가중치를 부여함으로써 적어도 하나의 주변 차량의 가중 주행 히스토리를 도출하는 단계, CNN을 통해 가중 주행 히스토리에 대한 커브 피팅을 수행하여 적어도 하나의 주변 차량의 주행 궤적을 결정하는 단계, 및 주행 궤적에 기초하여 자율 주행을 보조하기 위한 HD 맵 상에 가상 차선을 생성하는 단계를 포함하는 방법이 개시된다.</description><subject>ANALOGOUS ARRANGEMENTS USING OTHER WAVES</subject><subject>CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION</subject><subject>CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES</subject><subject>DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES</subject><subject>LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES</subject><subject>MEASURING</subject><subject>PERFORMING OPERATIONS</subject><subject>PHYSICS</subject><subject>RADIO DIRECTION-FINDING</subject><subject>RADIO NAVIGATION</subject><subject>ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT</subject><subject>TESTING</subject><subject>TRANSPORTING</subject><subject>VEHICLES IN GENERAL</subject><subject>VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjEsOgjAQhtm4MOodJnFtIuDC7dhOoQl0mlJgSYipK6MkeA7PbH0cwNX_5X8tk2ennW-xggoNQUGGHHrNBtBajNg2gEZCTb5kCSdsSEJMvUOltABVcQ_aKHb1d2bJCbIfjCZg69lwzfFGOt1pU8Q2oOzINQQ9oS_JgWAj9XvTrJPFZbzOYfPTVbJV5EW5C9N9CPM0nsMtPIaes32WZof0mB8wzf9rvQD9GUFE</recordid><startdate>20211202</startdate><enddate>20211202</enddate><creator>YI, Kyong Su</creator><creator>KOH, Young Il</creator><creator>YI, Zoo Hyeon</creator><scope>EVB</scope></search><sort><creationdate>20211202</creationdate><title>VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS</title><author>YI, Kyong Su ; KOH, Young Il ; YI, Zoo Hyeon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2021241834A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; kor</language><creationdate>2021</creationdate><topic>ANALOGOUS ARRANGEMENTS USING OTHER WAVES</topic><topic>CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION</topic><topic>CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES</topic><topic>DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES</topic><topic>LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES</topic><topic>MEASURING</topic><topic>PERFORMING OPERATIONS</topic><topic>PHYSICS</topic><topic>RADIO DIRECTION-FINDING</topic><topic>RADIO NAVIGATION</topic><topic>ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT</topic><topic>TESTING</topic><topic>TRANSPORTING</topic><topic>VEHICLES IN GENERAL</topic><topic>VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR</topic><toplevel>online_resources</toplevel><creatorcontrib>YI, Kyong Su</creatorcontrib><creatorcontrib>KOH, Young Il</creatorcontrib><creatorcontrib>YI, Zoo Hyeon</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YI, Kyong Su</au><au>KOH, Young Il</au><au>YI, Zoo Hyeon</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS</title><date>2021-12-02</date><risdate>2021</risdate><abstract>Disclosed is a method for generating a virtual lane for assisting autonomous driving, the method comprising the steps of: deriving a driving history by accumulating driving data of at least one surrounding vehicle measured by a composite sensor according to the passage of time; classifying the driving history into at least one driving section according to a driving pattern on the basis of self-attention implemented by a convolutional neural network (CNN); deriving a weighted driving history of the at least one surrounding vehicle by assigning a weight to the at least one driving section on the basis of the self-attention; determining a driving trajectory of the at least one surrounding vehicle by performing curve fitting on the weighted driving history through the CNN; and generating a virtual lane on an HD map for assisting autonomous driving on the basis of the driving trajectory.
La divulgation concerne un procédé de génération d'une voie virtuelle destinée à aider à la conduite autonome, le procédé comprenant les étapes consistant : à déduire un historique de conduite au moyen de l'accumulation de données de conduite d'au moins un véhicule environnant mesurées par un capteur composite en fonction du passage du temps ; à classer l'historique de conduite en au moins une section de conduite selon un motif de conduite sur la base d'une attention automatique mise en œuvre par un réseau neuronal convolutionnel (CNN) ; à déduire un historique de conduite pondéré dudit véhicule environnant au moyen de l'attribution d'une pondération à ladite section de conduite sur la base de l'attention automatique ; à déterminer une trajectoire de conduite dudit véhicule environnant au moyen de la réalisation d'un réglage de courbe sur l'historique de conduite pondéré par le biais du CNN ; et à générer une voie virtuelle sur une carte HD pour aider à la conduite autonome sur la base de la trajectoire de conduite.
자율 주행을 보조하기 위한 가상 차선을 생성하는 방법에 있어서, 복합 센서에 의해 측정되는 적어도 하나의 주변 차량의 주행 데이터를 시간 흐름에 따라 누적하여 주행 히스토리를 도출하는 단계, CNN(convolutional neural network)에 의해 구현되는 셀프-어텐션(self-attention)에 기초하여 주행 히스토리를 주행 패턴에 따라 적어도 하나의 주행 구간으로 구분하는 단계, 셀프-어텐션에 기초하여 적어도 하나의 주행 구간에 가중치를 부여함으로써 적어도 하나의 주변 차량의 가중 주행 히스토리를 도출하는 단계, CNN을 통해 가중 주행 히스토리에 대한 커브 피팅을 수행하여 적어도 하나의 주변 차량의 주행 궤적을 결정하는 단계, 및 주행 궤적에 기초하여 자율 주행을 보조하기 위한 HD 맵 상에 가상 차선을 생성하는 단계를 포함하는 방법이 개시된다.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng ; fre ; kor |
recordid | cdi_epo_espacenet_WO2021241834A1 |
source | esp@cenet |
subjects | ANALOGOUS ARRANGEMENTS USING OTHER WAVES CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES MEASURING PERFORMING OPERATIONS PHYSICS RADIO DIRECTION-FINDING RADIO NAVIGATION ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT TESTING TRANSPORTING VEHICLES IN GENERAL VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR |
title | VIRTUAL LANE GENERATION APPARATUS AND METHOD BASED ON TRAFFIC FLOW INFORMATION PERCEPTION FOR AUTONOMOUS DRIVING IN ADVERSE WEATHER CONDITIONS |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T03%3A27%3A10IST&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=YI,%20Kyong%20Su&rft.date=2021-12-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2021241834A1%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 |