Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory
The personalization of autonomous vehicles or advanced driver assistance systems has been a widely researched topic, with many proposals aiming to achieve human-like or driver-imitating methods. However, these approaches rely on an implicit assumption that all drivers prefer the vehicle to drive lik...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/11/5246 |
| _version_ | 1797596688884432896 |
|---|---|
| author | Wei Ran Hui Chen Taokai Xia Yosuke Nishimura Chaopeng Guo Youyu Yin |
| author_facet | Wei Ran Hui Chen Taokai Xia Yosuke Nishimura Chaopeng Guo Youyu Yin |
| author_sort | Wei Ran |
| collection | DOAJ |
| description | The personalization of autonomous vehicles or advanced driver assistance systems has been a widely researched topic, with many proposals aiming to achieve human-like or driver-imitating methods. However, these approaches rely on an implicit assumption that all drivers prefer the vehicle to drive like themselves, which may not hold true for all drivers. To address this issue, this study proposes an online personalized preference learning method (OPPLM) that utilizes a pairwise comparison group preference query and the Bayesian approach. The proposed OPPLM adopts a two-layer hierarchical structure model based on utility theory to represent driver preferences on the trajectory. To improve the accuracy of learning, the uncertainty of driver query answers is modeled. In addition, informative query and greedy query selection methods are used to improve learning speed. To determine when the driver’s preferred trajectory has been found, a convergence criterion is proposed. To evaluate the effectiveness of the OPPLM, a user study is conducted to learn the driver’s preferred trajectory in the curve of the lane centering control (LCC) system. The results show that the OPPLM can converge quickly, requiring only about 11 queries on average. Moreover, it accurately learned the driver’s favorite trajectory, and the estimated utility of the driver preference model is highly consistent with the subject evaluation score. |
| first_indexed | 2024-03-11T02:56:35Z |
| format | Article |
| id | doaj.art-4c28e4d1e5a04793b1d34f3ec7b8b648 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T02:56:35Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4c28e4d1e5a04793b1d34f3ec7b8b6482023-11-18T08:34:32ZengMDPI AGSensors1424-82202023-05-012311524610.3390/s23115246Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control TrajectoryWei Ran0Hui Chen1Taokai Xia2Yosuke Nishimura3Chaopeng Guo4Youyu Yin5School of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaJTEKT Corporation, Nara 634-8555, JapanJTEKT Corporation, Nara 634-8555, JapanJTEKT Research and Development Center (WUXI) Co., Ltd., Wuxi 214161, ChinaThe personalization of autonomous vehicles or advanced driver assistance systems has been a widely researched topic, with many proposals aiming to achieve human-like or driver-imitating methods. However, these approaches rely on an implicit assumption that all drivers prefer the vehicle to drive like themselves, which may not hold true for all drivers. To address this issue, this study proposes an online personalized preference learning method (OPPLM) that utilizes a pairwise comparison group preference query and the Bayesian approach. The proposed OPPLM adopts a two-layer hierarchical structure model based on utility theory to represent driver preferences on the trajectory. To improve the accuracy of learning, the uncertainty of driver query answers is modeled. In addition, informative query and greedy query selection methods are used to improve learning speed. To determine when the driver’s preferred trajectory has been found, a convergence criterion is proposed. To evaluate the effectiveness of the OPPLM, a user study is conducted to learn the driver’s preferred trajectory in the curve of the lane centering control (LCC) system. The results show that the OPPLM can converge quickly, requiring only about 11 queries on average. Moreover, it accurately learned the driver’s favorite trajectory, and the estimated utility of the driver preference model is highly consistent with the subject evaluation score.https://www.mdpi.com/1424-8220/23/11/5246online learningpreference learningutility theoryBayesian approachLCC trajectory |
| spellingShingle | Wei Ran Hui Chen Taokai Xia Yosuke Nishimura Chaopeng Guo Youyu Yin Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory Sensors online learning preference learning utility theory Bayesian approach LCC trajectory |
| title | Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory |
| title_full | Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory |
| title_fullStr | Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory |
| title_full_unstemmed | Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory |
| title_short | Online Personalized Preference Learning Method Based on In-Formative Query for Lane Centering Control Trajectory |
| title_sort | online personalized preference learning method based on in formative query for lane centering control trajectory |
| topic | online learning preference learning utility theory Bayesian approach LCC trajectory |
| url | https://www.mdpi.com/1424-8220/23/11/5246 |
| work_keys_str_mv | AT weiran onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory AT huichen onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory AT taokaixia onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory AT yosukenishimura onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory AT chaopengguo onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory AT youyuyin onlinepersonalizedpreferencelearningmethodbasedoninformativequeryforlanecenteringcontroltrajectory |