An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios
Studies on self-driving transport vehicles have focused on longitudinal and lateral driving strategies in automated structured road scenarios. In this study, a double parallel network (DP-Net) combined with longitudinal and lateral strategy networks is constructed for self-driving transport vehicles...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sustainability |
Subjects: | |
Online Access: | https://www.mdpi.com/2071-1050/13/8/4531 |
id |
doaj-13d00af2f134429e81e424b6e884b4df |
---|---|
record_format |
Article |
spelling |
doaj-13d00af2f134429e81e424b6e884b4df2021-04-19T23:04:09ZengMDPI AGSustainability2071-10502021-04-01134531453110.3390/su13084531An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road ScenariosHuiyuan Xiong0Huan Liu1Jian Ma2Yuelong Pan3Ronghui Zhang4Guangdong Provincial Key Laboratory of Intelligent Transport System, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Provincial Key Laboratory of Intelligent Transport System, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, ChinaChina Nuclear Power Engineering Co., Ltd., Shenzhen 518000, ChinaChina Nuclear Power Engineering Co., Ltd., Shenzhen 518000, ChinaGuangdong Provincial Key Laboratory of Intelligent Transport System, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, ChinaStudies on self-driving transport vehicles have focused on longitudinal and lateral driving strategies in automated structured road scenarios. In this study, a double parallel network (DP-Net) combined with longitudinal and lateral strategy networks is constructed for self-driving transport vehicles in structured road scenarios, which is based on a convolutional neural network (CNN) and a long short-term memory network (LSTM). First, in feature extraction and perception, a preprocessing module is introduced that can ensure the effective extraction of visual information under complex illumination. Then, a parallel CNN sub-network is designed that is based on multifeature fusion to ensure better autonomous driving strategies. Meanwhile, a parallel LSTM sub-network is designed, which uses vehicle kinematic features as physical constraints to improve the prediction accuracy for steering angle and speed. The Udacity Challenge II dataset is used as the training set with the proposed DP-Net input requirements. Finally, for the proposed DP-Net, the root mean square error (RMSE) is used as the loss function, the mean absolute error (MAE) is used as the metric, and Adam is used as the optimization method. Compared with competing models such as PilotNet, CgNet, and E2E multimodal multitask network, the proposed DP-Net is more robust in handling complex illumination. The RMSE and MAE values for predicting the steering angle of the E2E multimodal multitask network are 0.0584 and 0.0163 rad, respectively; for the proposed DP-Net, those values are 0.0107 and 0.0054 rad, i.e., 81.7% and 66.9% lower, respectively. In addition, the proposed DP-Net also has higher accuracy in speed prediction. Upon testing the collected SYSU Campus dataset, good predictions are also obtained. These results should provide significant guidance for using a DP-Net to deploy multi-axle transport vehicles.https://www.mdpi.com/2071-1050/13/8/4531autonomous drivinglongitudinal and lateral driving strategycomplex illuminationvehicle kinematics |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Huiyuan Xiong Huan Liu Jian Ma Yuelong Pan Ronghui Zhang |
spellingShingle |
Huiyuan Xiong Huan Liu Jian Ma Yuelong Pan Ronghui Zhang An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios Sustainability autonomous driving longitudinal and lateral driving strategy complex illumination vehicle kinematics |
author_facet |
Huiyuan Xiong Huan Liu Jian Ma Yuelong Pan Ronghui Zhang |
author_sort |
Huiyuan Xiong |
title |
An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios |
title_short |
An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios |
title_full |
An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios |
title_fullStr |
An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios |
title_full_unstemmed |
An NN-Based Double Parallel Longitudinal and Lateral Driving Strategy for Self-Driving Transport Vehicles in Structured Road Scenarios |
title_sort |
nn-based double parallel longitudinal and lateral driving strategy for self-driving transport vehicles in structured road scenarios |
publisher |
MDPI AG |
series |
Sustainability |
issn |
2071-1050 |
publishDate |
2021-04-01 |
description |
Studies on self-driving transport vehicles have focused on longitudinal and lateral driving strategies in automated structured road scenarios. In this study, a double parallel network (DP-Net) combined with longitudinal and lateral strategy networks is constructed for self-driving transport vehicles in structured road scenarios, which is based on a convolutional neural network (CNN) and a long short-term memory network (LSTM). First, in feature extraction and perception, a preprocessing module is introduced that can ensure the effective extraction of visual information under complex illumination. Then, a parallel CNN sub-network is designed that is based on multifeature fusion to ensure better autonomous driving strategies. Meanwhile, a parallel LSTM sub-network is designed, which uses vehicle kinematic features as physical constraints to improve the prediction accuracy for steering angle and speed. The Udacity Challenge II dataset is used as the training set with the proposed DP-Net input requirements. Finally, for the proposed DP-Net, the root mean square error (RMSE) is used as the loss function, the mean absolute error (MAE) is used as the metric, and Adam is used as the optimization method. Compared with competing models such as PilotNet, CgNet, and E2E multimodal multitask network, the proposed DP-Net is more robust in handling complex illumination. The RMSE and MAE values for predicting the steering angle of the E2E multimodal multitask network are 0.0584 and 0.0163 rad, respectively; for the proposed DP-Net, those values are 0.0107 and 0.0054 rad, i.e., 81.7% and 66.9% lower, respectively. In addition, the proposed DP-Net also has higher accuracy in speed prediction. Upon testing the collected SYSU Campus dataset, good predictions are also obtained. These results should provide significant guidance for using a DP-Net to deploy multi-axle transport vehicles. |
topic |
autonomous driving longitudinal and lateral driving strategy complex illumination vehicle kinematics |
url |
https://www.mdpi.com/2071-1050/13/8/4531 |
work_keys_str_mv |
AT huiyuanxiong annnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT huanliu annnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT jianma annnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT yuelongpan annnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT ronghuizhang annnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT huiyuanxiong nnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT huanliu nnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT jianma nnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT yuelongpan nnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios AT ronghuizhang nnbaseddoubleparallellongitudinalandlateraldrivingstrategyforselfdrivingtransportvehiclesinstructuredroadscenarios |
_version_ |
1721518915879698432 |