A Neural Network-Based Model with Conditional-Deactivation Structure for Autonomous Vehicle Motivation Prediction at Intersections
Article No.: 16, Pages 1 - 10
Abstract
Autonomous driving is now a hot research topic due to its great significance in improving traffic safety. Among the scenarios involved in autonomous driving, the intersection scenario is undoubtedly one of the most challenging scenarios due to its complex traffic patterns. Therefore, predicting the motivation of vehicles at intersections can improve traffic safety and efficiency. Most current researches focused on motivation prediction modelling in ideal resource environments, but vehicle information may be missing due to environment factors, which may cause the model to work abnormally. To address this shortcoming, this study analyses the characteristics of vehicle motions at intersections, segments vehicle motion processes, and proposes a data compensation method based on the segmented data to simulate the vehicle data missing condition. Based on the characteristics of the data, a neural network model with conditional-deactivation structure is proposed, which is trained and then dynamic real-time simulation and testing are carried out using the simulation environment composed of CARLA and SUMO to verify the effectiveness of the model. The test results show that the proposed model can work properly in certain scenarios, and can reach up to 97.7% prediction accuracy and 2.3s prospective time, better than some existing works. In summary, the proposed model can provide a certain research basis for the motivation prediction of autonomous vehicles.
References
[1]
Wei, C, Hui, F, Yang, Z, Jia, S and Khattak, A J 2022. Fine-grained highway autonomous vehicle lane-changing trajectory prediction based on a heuristic attention-aided encoder-decoder model. Transportation Research Part C: Emerging Technologies, 140, 103706.
[2]
Wei, C, Hui, F, Khattak, A. J., Zhang, Y and Wang, W 2023 Controllable probability-limited and learning-based human-like vehicle behavior and trajectory generation for autonomous driving testing in highway scenario. Expert Systems with Applications, 227, 120336.
[3]
Liu, Q, Wang, Z, and Sun, J 2017. Left-turn vehicles crossing behavior prediction and modeling at mixed traffic flow intersection. In 2017 4th International Conference on Systems and Informatics (ICSAI) pp. 862-868. IEEE.
[4]
Zhang, H, Fu, R, Wang, C, Guo, Y and Yuan, W 2022. Turning maneuver prediction of connected vehicles at signalized intersections: A Dictionary Learning-Based Approach. IEEE Internet of Things Journal, 9(22), 23142-159.
[5]
Von Eichhorn, A, Werling, M, Zahn, P and Schramm, D 2013 Maneuver prediction at intersections using cost-to-go gradients. In 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) pp. 112-17. IEEE.
[6]
Graf, R Deusch, H, Seeliger, F, Fritzsche, M and Dietmayer, K 2014. A learning concept for behavior prediction at intersections. In 2014 IEEE Intelligent Vehicles Symposium Proceedings pp. 939-45. IEEE.
[7]
Zohdy, I, and Rakha, H A 2012. Agent-based framework for modeling gap acceptance behavior of drivers turning left at signalized intersections. Transportation research record, 2316(1), pp:1-10.
[8]
Zhang, G, Zhou, Q, and Chen, J 2021. Exploring Factors Impacting on the Lane Choice of Riders of Non-Motorized Vehicles at Exit Legs of Signalized At-Grade Intersections. International Journal of Environmental Research and Public Health, 18(12), 6327.
[9]
Graichen, M, and Nitsch, V 2017. Effects of driver characteristics and driver state on predicting turning maneuvers in urban areas: Is there a need for individualized parametrization?. In Advances in Human Aspects of Transportation: Proceedings of the AHFE 2016 International Conference on Human Factors in Transportation, pp. 15-29.
[10]
Sun, J, Qi, X, Xu, Y and Tian, Y 2019. Vehicle turning behavior modeling at conflicting areas of mixed-flow intersections based on deep learning. IEEE transactions on intelligent transportation systems, 21(9), pp: 3674-85.
[11]
Yao, R, Zeng, W, Chen, Y and He, Z 2021. A deep learning framework for modelling left-turning vehicle behaviour considering diagonal-crossing motorcycle conflicts at mixed-flow intersections. Transportation research part C: emerging technologies, 132, 103415.
[12]
Zhang, M, Fu, R, Morris, D D and Wang, C 2019. A framework for turning behavior classification at intersections using 3D LIDAR. IEEE Transactions on Vehicular Technology, 68(8), pp: 7431-42.
[13]
Zhang, H, and Fu, R 2020. A hybrid approach for turning intention prediction based on time series forecasting and deep learning. Sensors, 20(17), 4887.
[14]
Nan, J, Deng, W and Zheng, B 2022. Intention prediction and mixed strategy nash equilibrium-based decision-making framework for autonomous driving in uncontrolled intersection. IEEE Transactions on Vehicular Technology, 71(10), 10316-26.
[15]
Ou, C and Karray, F 2019. Deep learning-based driving maneuver prediction system. IEEE transactions on vehicular technology, 69(2), pp:1328-40.
[16]
Bock, J, Krajewski, R, Moers, T, Runde, S, Vater, L, and Eckstein, L 2020. The ind dataset: A drone dataset of naturalistic road user trajectories at german intersections. In 2020 IEEE Intelligent Vehicles Symposium pp. 1929-34. IEEE.
[17]
Wei, C, Hui, F, Zhao, X, and Fang, S 2022. Real-time Simulation and Testing of a Neural Network-based Autonomous Vehicle Trajectory Prediction Model. In 2022 18th International Conference on Mobility, Sensing and Networking. pp. 641-48. IEEE.
Index Terms
- A Neural Network-Based Model with Conditional-Deactivation Structure for Autonomous Vehicle Motivation Prediction at Intersections
Recommendations
Neural network based lane change trajectory prediction in autonomous vehicles
Transactions on computational science XIIIDuring a lane change, vehicle collision warning systems detect the likelihood of collision and time to collision to warn vehicles of an imminent collision. In autonomous systems, a vehicle utilizes data obtained by its own sensors to predict future ...
Autonomous vehicle routing in multiple intersections
ASPDAC '19: Proceedings of the 24th Asia and South Pacific Design Automation ConferenceAdvancements in artificial intelligence and Internet of Things indicates the realization of commercial autonomous vehicles is almost ready. With autonomous vehicles comes new approaches in solving some of the current traffic problems such as fuel ...
Macro Prediction Model of Road Traffic Accident Based on Neural Network and Genetic Algorithm
ICICTA '09: Proceedings of the 2009 Second International Conference on Intelligent Computation Technology and Automation - Volume 01The whole society has paid more and more attention to the road traffic safety in China. In order to scientifically and accurately predict the future road traffic safety situation, evaluation indexes and main influence factors of road traffic safety were ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2023
552 pages
ISBN:9781450399951
DOI:10.1145/3630138
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 17 January 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- National Natural Science Foundation of China
- National Key R&D Program of China
Conference
PCCNT 2023
PCCNT 2023: 2023 International Conference on Power, Communication, Computing and Networking Technologies
September 24 - 25, 2023
Wuhan, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 12Total Downloads
- Downloads (Last 12 months)12
- Downloads (Last 6 weeks)1
Reflects downloads up to 06 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format