A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost
Lane-changing (LC) is a critical task for autonomous driving, especially in complex dynamic environments. Numerous automatic LC algorithms have been proposed. This topic, however, has not been sufficiently addressed in existing on-road manoeuvre decision methods. Therefore, this paper presents a nov...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8950329/ |
| _version_ | 1829471874374959104 |
|---|---|
| author | Xinping Gu Yunpeng Han Junfu Yu |
| author_facet | Xinping Gu Yunpeng Han Junfu Yu |
| author_sort | Xinping Gu |
| collection | DOAJ |
| description | Lane-changing (LC) is a critical task for autonomous driving, especially in complex dynamic environments. Numerous automatic LC algorithms have been proposed. This topic, however, has not been sufficiently addressed in existing on-road manoeuvre decision methods. Therefore, this paper presents a novel LC decision (LCD) model that gives autonomous vehicles the ability to make human-like decisions. This method combines a deep autoencoder (DAE) network with the XGBoost algorithm. First, a DAE is utilized to build a robust multivariate reconstruction model using time series data from multiple sensors; then, the reconstruction error of the DAE trained with normal data is analysed for LC identification (LCI) and training data extraction. Then, to address the multi-parametric and nonlinear problem of the autonomous LC decision-making process, an XGBoost algorithm with Bayesian parameter optimization is adopted. Meanwhile, to fully train our learning model with large-scale datasets, we proposed an online training strategy that updates the model parameters with data batches. The experimental results illustrate that the DAE-based LCI model is able to accurately identify the LC behaviour of vehicles. Furthermore, with the same input features, the proposed XGBoost-based LCD model achieves better performance than other popular approaches. Moreover, a simulation experiment is performed to verify the effectiveness of the decision model. |
| first_indexed | 2024-12-14T02:03:59Z |
| format | Article |
| id | doaj.art-67071ac15d7c48968c49a9255c43bf9e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T02:03:59Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-67071ac15d7c48968c49a9255c43bf9e2022-12-21T23:20:56ZengIEEEIEEE Access2169-35362020-01-0189846986310.1109/ACCESS.2020.29642948950329A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoostXinping Gu0https://orcid.org/0000-0003-2629-6949Yunpeng Han1Junfu Yu2Key Laboratory of High Efficiency and Clean Mechanical Manufacture, Ministry of Education, Shandong University, Jinan, ChinaKey Laboratory of High Efficiency and Clean Mechanical Manufacture, Ministry of Education, Shandong University, Jinan, ChinaKey Laboratory of High Efficiency and Clean Mechanical Manufacture, Ministry of Education, Shandong University, Jinan, ChinaLane-changing (LC) is a critical task for autonomous driving, especially in complex dynamic environments. Numerous automatic LC algorithms have been proposed. This topic, however, has not been sufficiently addressed in existing on-road manoeuvre decision methods. Therefore, this paper presents a novel LC decision (LCD) model that gives autonomous vehicles the ability to make human-like decisions. This method combines a deep autoencoder (DAE) network with the XGBoost algorithm. First, a DAE is utilized to build a robust multivariate reconstruction model using time series data from multiple sensors; then, the reconstruction error of the DAE trained with normal data is analysed for LC identification (LCI) and training data extraction. Then, to address the multi-parametric and nonlinear problem of the autonomous LC decision-making process, an XGBoost algorithm with Bayesian parameter optimization is adopted. Meanwhile, to fully train our learning model with large-scale datasets, we proposed an online training strategy that updates the model parameters with data batches. The experimental results illustrate that the DAE-based LCI model is able to accurately identify the LC behaviour of vehicles. Furthermore, with the same input features, the proposed XGBoost-based LCD model achieves better performance than other popular approaches. Moreover, a simulation experiment is performed to verify the effectiveness of the decision model.https://ieeexplore.ieee.org/document/8950329/Autonomous vehiclelane-changing identificationlane-changing decision-makingdeep autoencoder networkXGBoost |
| spellingShingle | Xinping Gu Yunpeng Han Junfu Yu A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost IEEE Access Autonomous vehicle lane-changing identification lane-changing decision-making deep autoencoder network XGBoost |
| title | A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost |
| title_full | A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost |
| title_fullStr | A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost |
| title_full_unstemmed | A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost |
| title_short | A Novel Lane-Changing Decision Model for Autonomous Vehicles Based on Deep Autoencoder Network and XGBoost |
| title_sort | novel lane changing decision model for autonomous vehicles based on deep autoencoder network and xgboost |
| topic | Autonomous vehicle lane-changing identification lane-changing decision-making deep autoencoder network XGBoost |
| url | https://ieeexplore.ieee.org/document/8950329/ |
| work_keys_str_mv | AT xinpinggu anovellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost AT yunpenghan anovellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost AT junfuyu anovellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost AT xinpinggu novellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost AT yunpenghan novellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost AT junfuyu novellanechangingdecisionmodelforautonomousvehiclesbasedondeepautoencodernetworkandxgboost |