Loading…
A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns
•An integrated framework is proposed to predict lane-changing risk.•Driving intentions are recognized using LSTM neural network.•LGBM algorithm achieves a higher lane-changing risk prediction accuracy.•Feature importance analysis is conducted using LGBM classifier. Proactive lane-changing (LC) risk...
Saved in:
Published in: | Accident analysis and prevention 2022-01, Vol.164, p.106500-106500, Article 106500 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03 |
---|---|
cites | cdi_FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03 |
container_end_page | 106500 |
container_issue | |
container_start_page | 106500 |
container_title | Accident analysis and prevention |
container_volume | 164 |
creator | Shangguan, Qiangqiang Fu, Ting Wang, Junhua Fang, Shou'en Fu, Liping |
description | •An integrated framework is proposed to predict lane-changing risk.•Driving intentions are recognized using LSTM neural network.•LGBM algorithm achieves a higher lane-changing risk prediction accuracy.•Feature importance analysis is conducted using LGBM classifier.
Proactive lane-changing (LC) risk prediction can assist driver’s LC decision-making to ensure driving safety. However, most previous studies on LC risk prediction did not consider the driver’s intention recognition, which made it difficult to guarantee the timeliness and practicability of LC risk prediction. Moreover, the difference in driving risks and its influencing factors between LC to left lane (LCL) and LC to right lane (LCR) have rarely been investigated. To bridge the above research gaps, this study proposes a proactive LC risk prediction framework which integrates the LC intention recognition module and LC risk prediction module. The Long Short-term Memory (LSTM) neural network with time-series input was employed to recognize the driver’s LC intention. The Light Gradient Boosting Machine (LGBM) algorithm was then applied to predict the LC risk. Feature importance analysis was lastly conducted to obtain the key features that affect the LC risk. The highD trajectory dataset was used for framework validation. Results show that the recognition accuracy of the driver’s LCL, LCR and lane-keeping (LK) intentions based on the proposed LSTM model are 97%, 96% and 97%, respectively. Meanwhile, the LGBM algorithm outperforms other machine learning algorithms in LC risk prediction. The results from feature importance analysis show that the interaction characteristics of the LC vehicle and its preceding vehicle in the current lane have the greatest impact on the LC risk. The proposed framework could potentially be implemented in advanced driver-assistance system (ADAS) or autonomous driving system for improved driving safety. |
doi_str_mv | 10.1016/j.aap.2021.106500 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2604016458</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0001457521005315</els_id><sourcerecordid>2604016458</sourcerecordid><originalsourceid>FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03</originalsourceid><addsrcrecordid>eNp9kD1PwzAQhi0EEqXwA9gysqSckzhOxFRVfEmVWGC2XPtc3A872GkRK78cp2ViYLo7ve97unsIuaYwoUDr29VEym5SQEHTXDOAEzKiDW_zAhg_JSMAoHnFODsnFzGu0sgbzkbke5p1wUvV2z1mG-kwV-_SLa1bZsHGdRJR26R6l5kgt_jpwzpT3kWrMQwuHex-qNb16A6-gMovnT300ulMW2MwJPHP_k72PQYXL8mZkZuIV791TN4e7l9nT_n85fF5Np3nqiyhzzlHzRemahtkoCrZYCW1aalURtWaa24Ya6RUrFQLQxnQpiwL0GCgMHWroRyTm-Pe9PDHDmMvtjYq3AxX-V0URQ1VQlmxJlnp0aqCjzGgEV2wWxm-BAUx8BYrkXiLgbc48k6Zu2MG0w97i0FEZdGpxC8R6YX29p_0DynSjCk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2604016458</pqid></control><display><type>article</type><title>A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns</title><source>ScienceDirect Journals</source><creator>Shangguan, Qiangqiang ; Fu, Ting ; Wang, Junhua ; Fang, Shou'en ; Fu, Liping</creator><creatorcontrib>Shangguan, Qiangqiang ; Fu, Ting ; Wang, Junhua ; Fang, Shou'en ; Fu, Liping</creatorcontrib><description>•An integrated framework is proposed to predict lane-changing risk.•Driving intentions are recognized using LSTM neural network.•LGBM algorithm achieves a higher lane-changing risk prediction accuracy.•Feature importance analysis is conducted using LGBM classifier.
Proactive lane-changing (LC) risk prediction can assist driver’s LC decision-making to ensure driving safety. However, most previous studies on LC risk prediction did not consider the driver’s intention recognition, which made it difficult to guarantee the timeliness and practicability of LC risk prediction. Moreover, the difference in driving risks and its influencing factors between LC to left lane (LCL) and LC to right lane (LCR) have rarely been investigated. To bridge the above research gaps, this study proposes a proactive LC risk prediction framework which integrates the LC intention recognition module and LC risk prediction module. The Long Short-term Memory (LSTM) neural network with time-series input was employed to recognize the driver’s LC intention. The Light Gradient Boosting Machine (LGBM) algorithm was then applied to predict the LC risk. Feature importance analysis was lastly conducted to obtain the key features that affect the LC risk. The highD trajectory dataset was used for framework validation. Results show that the recognition accuracy of the driver’s LCL, LCR and lane-keeping (LK) intentions based on the proposed LSTM model are 97%, 96% and 97%, respectively. Meanwhile, the LGBM algorithm outperforms other machine learning algorithms in LC risk prediction. The results from feature importance analysis show that the interaction characteristics of the LC vehicle and its preceding vehicle in the current lane have the greatest impact on the LC risk. The proposed framework could potentially be implemented in advanced driver-assistance system (ADAS) or autonomous driving system for improved driving safety.</description><identifier>ISSN: 0001-4575</identifier><identifier>EISSN: 1879-2057</identifier><identifier>DOI: 10.1016/j.aap.2021.106500</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Driving intention recognition ; Lane-changing risk prediction ; Long Short-term Memory (LSTM) ; Trajectory data</subject><ispartof>Accident analysis and prevention, 2022-01, Vol.164, p.106500-106500, Article 106500</ispartof><rights>2021 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03</citedby><cites>FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Shangguan, Qiangqiang</creatorcontrib><creatorcontrib>Fu, Ting</creatorcontrib><creatorcontrib>Wang, Junhua</creatorcontrib><creatorcontrib>Fang, Shou'en</creatorcontrib><creatorcontrib>Fu, Liping</creatorcontrib><title>A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns</title><title>Accident analysis and prevention</title><description>•An integrated framework is proposed to predict lane-changing risk.•Driving intentions are recognized using LSTM neural network.•LGBM algorithm achieves a higher lane-changing risk prediction accuracy.•Feature importance analysis is conducted using LGBM classifier.
Proactive lane-changing (LC) risk prediction can assist driver’s LC decision-making to ensure driving safety. However, most previous studies on LC risk prediction did not consider the driver’s intention recognition, which made it difficult to guarantee the timeliness and practicability of LC risk prediction. Moreover, the difference in driving risks and its influencing factors between LC to left lane (LCL) and LC to right lane (LCR) have rarely been investigated. To bridge the above research gaps, this study proposes a proactive LC risk prediction framework which integrates the LC intention recognition module and LC risk prediction module. The Long Short-term Memory (LSTM) neural network with time-series input was employed to recognize the driver’s LC intention. The Light Gradient Boosting Machine (LGBM) algorithm was then applied to predict the LC risk. Feature importance analysis was lastly conducted to obtain the key features that affect the LC risk. The highD trajectory dataset was used for framework validation. Results show that the recognition accuracy of the driver’s LCL, LCR and lane-keeping (LK) intentions based on the proposed LSTM model are 97%, 96% and 97%, respectively. Meanwhile, the LGBM algorithm outperforms other machine learning algorithms in LC risk prediction. The results from feature importance analysis show that the interaction characteristics of the LC vehicle and its preceding vehicle in the current lane have the greatest impact on the LC risk. The proposed framework could potentially be implemented in advanced driver-assistance system (ADAS) or autonomous driving system for improved driving safety.</description><subject>Driving intention recognition</subject><subject>Lane-changing risk prediction</subject><subject>Long Short-term Memory (LSTM)</subject><subject>Trajectory data</subject><issn>0001-4575</issn><issn>1879-2057</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp9kD1PwzAQhi0EEqXwA9gysqSckzhOxFRVfEmVWGC2XPtc3A872GkRK78cp2ViYLo7ve97unsIuaYwoUDr29VEym5SQEHTXDOAEzKiDW_zAhg_JSMAoHnFODsnFzGu0sgbzkbke5p1wUvV2z1mG-kwV-_SLa1bZsHGdRJR26R6l5kgt_jpwzpT3kWrMQwuHex-qNb16A6-gMovnT300ulMW2MwJPHP_k72PQYXL8mZkZuIV791TN4e7l9nT_n85fF5Np3nqiyhzzlHzRemahtkoCrZYCW1aalURtWaa24Ya6RUrFQLQxnQpiwL0GCgMHWroRyTm-Pe9PDHDmMvtjYq3AxX-V0URQ1VQlmxJlnp0aqCjzGgEV2wWxm-BAUx8BYrkXiLgbc48k6Zu2MG0w97i0FEZdGpxC8R6YX29p_0DynSjCk</recordid><startdate>202201</startdate><enddate>202201</enddate><creator>Shangguan, Qiangqiang</creator><creator>Fu, Ting</creator><creator>Wang, Junhua</creator><creator>Fang, Shou'en</creator><creator>Fu, Liping</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>202201</creationdate><title>A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns</title><author>Shangguan, Qiangqiang ; Fu, Ting ; Wang, Junhua ; Fang, Shou'en ; Fu, Liping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Driving intention recognition</topic><topic>Lane-changing risk prediction</topic><topic>Long Short-term Memory (LSTM)</topic><topic>Trajectory data</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shangguan, Qiangqiang</creatorcontrib><creatorcontrib>Fu, Ting</creatorcontrib><creatorcontrib>Wang, Junhua</creatorcontrib><creatorcontrib>Fang, Shou'en</creatorcontrib><creatorcontrib>Fu, Liping</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Accident analysis and prevention</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shangguan, Qiangqiang</au><au>Fu, Ting</au><au>Wang, Junhua</au><au>Fang, Shou'en</au><au>Fu, Liping</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns</atitle><jtitle>Accident analysis and prevention</jtitle><date>2022-01</date><risdate>2022</risdate><volume>164</volume><spage>106500</spage><epage>106500</epage><pages>106500-106500</pages><artnum>106500</artnum><issn>0001-4575</issn><eissn>1879-2057</eissn><abstract>•An integrated framework is proposed to predict lane-changing risk.•Driving intentions are recognized using LSTM neural network.•LGBM algorithm achieves a higher lane-changing risk prediction accuracy.•Feature importance analysis is conducted using LGBM classifier.
Proactive lane-changing (LC) risk prediction can assist driver’s LC decision-making to ensure driving safety. However, most previous studies on LC risk prediction did not consider the driver’s intention recognition, which made it difficult to guarantee the timeliness and practicability of LC risk prediction. Moreover, the difference in driving risks and its influencing factors between LC to left lane (LCL) and LC to right lane (LCR) have rarely been investigated. To bridge the above research gaps, this study proposes a proactive LC risk prediction framework which integrates the LC intention recognition module and LC risk prediction module. The Long Short-term Memory (LSTM) neural network with time-series input was employed to recognize the driver’s LC intention. The Light Gradient Boosting Machine (LGBM) algorithm was then applied to predict the LC risk. Feature importance analysis was lastly conducted to obtain the key features that affect the LC risk. The highD trajectory dataset was used for framework validation. Results show that the recognition accuracy of the driver’s LCL, LCR and lane-keeping (LK) intentions based on the proposed LSTM model are 97%, 96% and 97%, respectively. Meanwhile, the LGBM algorithm outperforms other machine learning algorithms in LC risk prediction. The results from feature importance analysis show that the interaction characteristics of the LC vehicle and its preceding vehicle in the current lane have the greatest impact on the LC risk. The proposed framework could potentially be implemented in advanced driver-assistance system (ADAS) or autonomous driving system for improved driving safety.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.aap.2021.106500</doi><tpages>1</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0001-4575 |
ispartof | Accident analysis and prevention, 2022-01, Vol.164, p.106500-106500, Article 106500 |
issn | 0001-4575 1879-2057 |
language | eng |
recordid | cdi_proquest_miscellaneous_2604016458 |
source | ScienceDirect Journals |
subjects | Driving intention recognition Lane-changing risk prediction Long Short-term Memory (LSTM) Trajectory data |
title | A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T15%3A08%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20proactive%20lane-changing%20risk%20prediction%20framework%20considering%20driving%20intention%20recognition%20and%20different%20lane-changing%20patterns&rft.jtitle=Accident%20analysis%20and%20prevention&rft.au=Shangguan,%20Qiangqiang&rft.date=2022-01&rft.volume=164&rft.spage=106500&rft.epage=106500&rft.pages=106500-106500&rft.artnum=106500&rft.issn=0001-4575&rft.eissn=1879-2057&rft_id=info:doi/10.1016/j.aap.2021.106500&rft_dat=%3Cproquest_cross%3E2604016458%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c330t-77ed7bf498e50c4a8e4adf91acfc6d7d7f558aac53cbf150183320d0f02f69d03%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2604016458&rft_id=info:pmid/&rfr_iscdi=true |