Integrated Decision and Motion Planning for Highways with Multiple Objects Using a Naturalistic Driving Study
Abstract
:1. Introduction
2. Two-Layered Decision and Planning Strategy
- (1)
- It is assumed that all vehicles obey the traffic rules of the highway;
- (2)
- There is a virtual area around the EV, which describes the required safety area for humans;
- (3)
- Considering the driving scenario on the highway, this virtual area is designed to be rectangular, and its width is set to be the width of the lane.
2.1. Parameter Design of Safety Area
- (1)
- (2)
- The lateral dynamics of the safety area directly determine the lateral acceleration and, accordingly, the driving comfort of the EV;
- (3)
- Under the dynamical and critical conditions, the failure of the lane change should also be addressed using the designed method.
2.2. Motion Planning of EV
- (1)
- The influences from other surrounding objects have already been considered when designing the size and dynamics of the safety region in Section 2.1;
- (2)
3. Lateral Motion of Safety Area for Lane Change
3.1. Decision of Lateral Moving Based on Projection of Field Forces
3.2. Parameter Analysis Based on Naturalistic Driving Data
3.2.1. Data Preparation
- (1)
- The starting moment is the time when the EV leaves the centerline of the current lane;
- (2)
- The ending moment is the time when the EV reaches the centerline of the target lane;
- (3)
- The EV should move to the target lane continuously and smoothly without such conditions as driving in the lane for a long time;
- (4)
- The EV should move to the target lane successfully just in time, and the data of the lane change should also be complete;
- (5)
- The surrounding vehicles keep driving in their lanes without a lane change;
- (6)
- The data for scenarios where the EV moves to a lane with a lower speed and there is no vehicle in front of the EV are removed.
3.2.2. Statistical Analysis of Conversion Factor
- (1)
- A bigger conversion factor means that less longitudinal social force can be projected toward the lateral direction. This implies that the EV tends to stay in the current lane, i.e., there is less intention to change lanes;
- (2)
- With the increase in EV speed, its intention to change lanes increases slightly and the average value of the conversion factor decreases from about −0.21 to −0.35;
- (3)
- For a given speed, the converting factor varies in a comparatively large range, since there are obvious differences in driving style for different drivers [35]. Accordingly, the conversion factor can act as a customization parameter to be set by the user, and a lower one implies an aggressive driving style.
3.2.3. Statistical Analysis of Moving Speed
- (1)
- A shorter time for a lane change means a more aggressive driving style;
- (2)
- The average time required for a lane change varies with the speed of the EV in a small range from about 3.5 s to 4.5 s; therefore, in this study, the influence of speed on the time for a lane change is ignored;
- (3)
- For a given speed of an EV, the time for a lane change varies in a large range. Being similar to the conversion factor, this may be caused by the style of different drivers;
- (4)
- Accordingly, the required time for a lane change can also act as a customization parameter to be set by the user.
4. Validation and Analysis
Algorithm 1. IDP: Integrated driving decision and motion planning algorithm |
Initialization: desired driving speed , converting factor , lateral moving speed, parameters of following distance in [33], parameters of motion dynamics in (2); While EV drives autonomously Obtain detection results of surrounding vehicles and lanes; Set longitudinal speed of safety area using (1); Calculate social force generated by lane and projected force for lane change using (4); Determine direction of lane change using (3); If EV stays in current lane Set lateral deviation of safety area to be zero; Otherwise, if EV makes lane change Calculate lateral deviation of safety area according to lateral moving speed; End Calculate desired longitudinal and lateral acceleration of EV using (2); Send desired control values to actuator controllers; End |
4.1. Open-Loop Tests Based on Naturalistic Driving Data
4.2. Closed-Loop Validation in Naturalistic Driving Scenarios
4.3. Test Under Multi-Task and Dynamic Scenario
5. Conclusions
- (1)
- The proposed framework can decompose the complex interactions in driving scenarios and motion planning tasks for an EV by using the safety area;
- (2)
- The proposed method has good adaptability to different scenarios by integrating the motion planning algorithm under different conditions into a unified spring-mass system, which also benefits performance in terms of comfort and smoothness;
- (3)
- The open/closed-loop test results show that the proposed method demonstrates better overall performance than IDP and NMPC and can control the EV safely, efficiently, and comfortably in real time.
- (1)
- Ethical and legal requirements must be satisfied for autonomous driving, especially for unavoidable accident scenarios [40]. How to simultaneously consider such requirements in the design of the driving decision and motion planning system needs to be further studied.
- (2)
- As shown in Figure 3a, though the HighD dataset includes various highway scenarios, the proposed method needs to be tested using more datasets and considering additional factors, such as weather, to show the robustness and generalization of the method.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
AV | Automated vehicle |
APF | Artificial potential field |
EV | Ego vehicle |
IDM | Intelligent driver model |
IDP | Integrated driving decision and motion planning |
NMPC | Nonlinear model predictive control |
References
- Akopov, A.S.; Beklaryan, L.A.; Beklaryan, A.L. Simulation-based optimization for autonomous transportation systems using a parallel real-coded genetic algorithm with scalable nonuniform mutation. Cybern. Inf. Technol. 2021, 21, 127–144. [Google Scholar]
- Alqurashi, R.; Altman, T. Hierarchical agent-based modeling for improved traffic routing. Appl. Sci. 2019, 9, 4376. [Google Scholar] [CrossRef]
- Gao, F.; Han, Y.; Li, E.S.; Xu, S.; Dang, D. Accurate pseudospectral optimization of nonlinear model predictive control for high-performance motion planning. IEEE Trans. Intell. Veh. 2023, 8, 1034–1045. [Google Scholar] [CrossRef]
- Peng, B.Y.; Sun, Q.; Li, E.S.; Kum, D.; Yin, Y.; Wei, J.; Gu, T. End-to-end autonomous driving through dueling double deep Q-network. Automot. Innov. 2021, 4, 328–337. [Google Scholar] [CrossRef]
- Ye, L.; Wu, F.; Zou, X.; Li, J. Path planning for mobile robots in unstructured orchard environments: An improved kinematically constrained bi-directional RRT approach. Comput. Electron. Agric. 2023, 215, 108453. [Google Scholar] [CrossRef]
- Hu, Q.X.; Ma, J.; Zhang, G.L.; Gao, F. A dual-dimensionality reduction strategy for optimization-based parallel parking path planner. Expert Syst. Appl. 2025, 263, 125781. [Google Scholar] [CrossRef]
- Hu, K.; Chen, Z.; Kang, H.; Tang, Y. 3D vision technologies for a self-developed structural external crack damage recognition robot. Automaiton Constr. 2024, 159, 105262. [Google Scholar] [CrossRef]
- Gao, F.; Wang, C.M. Hybrid strategy for traffic light detection by combining classical and self-learning detectors. IET Intell. Transp. Syst. 2020, 14, 735–741. [Google Scholar] [CrossRef]
- Gao, F.; Li, C.H.; Zhang, B.W. A dynamic clustering algorithm for lidar obstacle detection of autonomous driving system. IEEE Sens. J. 2021, 21, 25922–25930. [Google Scholar] [CrossRef]
- Chbouk, A.; Gotni, M.; Chawki, F.; En-Nay, M.; Hattati, M.A.; Salih-Alj, Y. Efficient sparse lidar data reconstruction using compressed sensing for real-time perception in autonomous vehicles. In Proceedings of the IEEE International Conference on Mechatronics and Automation, Tianjin, China, 4–7 August 2024. [Google Scholar]
- Zhu, H.; Qiu, Y.; Li, Y.; Mihaylova, L.; Leung, H. An adaptive multi-sensor fusion for intelligent vehicle localization. IEEE Sens. J. 2024, 24, 8798–8806. [Google Scholar] [CrossRef]
- Baek, S.; Kim, J.; Yi, K. Robust tracking and detection based on radar camera fusion filtering in urban autonomous driving. Intell. Serv. Robot. 2024, 17, 1125. [Google Scholar] [CrossRef]
- Yang, D.; Zhu, L.; Liu, Y.; Wu, D.; Ran, B. A novel car-following control model combining machine learning and kinematics models for automated vehicles. IEEE Trans. Intell. Transp. Syst. 2019, 20, 1991–2000. [Google Scholar] [CrossRef]
- Wu, P.; Gao, F.; Ki, K.Q. Humanlike decision and motion planning for expressway lane changing based on artificial potential field. IEEE Access 2022, 10, 4359–4373. [Google Scholar] [CrossRef]
- González, D.; Pérez, J.; Milanés, V.; Nashashibi, F. A review of motion planning techniques for automated vehicles. IEEE Trans. Intell. Transp. Syst. 2016, 17, 1135–1145. [Google Scholar] [CrossRef]
- Baker, C.R.; Dolan, J.M. Traffic interaction in the urban challenge: Putting boss on its best behavior. In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Nice, France, 22-26 September 2008. [Google Scholar]
- Zhang, B.; Fan, P.; Tang, S.; Gao, F.; Zhen, S. NMPC design for local planning of automated vehicle with less computational consumption. Int. J. Automot. Technol. 2024, 25, 445–454. [Google Scholar] [CrossRef]
- Jiang, J.; Ren, Y.; Guan, Y.; Li, S.E.; Yin, Y.; Yu, D.; Jin, X. Integrated decision and control at multi-lane intersections with mixed traffic flow. In Proceedings of the International Symposium on Intelligent Robotics and Systems, Virtual, 7–9 November 2021. [Google Scholar]
- Wang, Q.; Ayalew, B.; Weiskircher, T. Predictive maneuver planning for an autonomous vehicle in public highway traffic. IEEE Trans. Intell. Transp. Syst. 2019, 20, 1303–1315. [Google Scholar] [CrossRef]
- Xie, D.; Fang, Z.; Jia, B.; He, Z. A data-driven lane-changing model based on deep learning. Transp. Res. Part C Emerg. Technol. 2019, 106, 41–60. [Google Scholar] [CrossRef]
- Wang, D.; Wen, J.; Wang, Y.; Huang, X.; Pei, F. End-to-end self-driving using deep neural networks with multi-auxiliary tasks. Automot. Innov. 2019, 2, 127–136. [Google Scholar] [CrossRef]
- Wu, J.; Huang, Z.; Hu, Z.; Lv, C. Toward human-in-loop AI: Enhancing deep reinforcement learning via real time human guidance for autonomous driving. Engineering 2023, 21, 75–91. [Google Scholar] [CrossRef]
- Yang, Z.; Chen, Y.; Wang, J.; Manivasagam, S.; Ma, W.C.; Yang, A.J.; Urtasun, R. UniSIM: A neural closed-loop sensor simulator. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 17–24 June 2023. [Google Scholar]
- Yang, B.; Su, H.; Gkanatsios, N.; Ke, T.W.; Jain, A.; Schneider, J.; Fragkiadaki, K. Diffusion-ES: Gradient-free planning with diffusion for autonomous and instruction-guided driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 16–22 June 2024. [Google Scholar]
- Jia, F.; Mao, W.; Liu, Y.; Zhao, Y.; Wen, Y.; Zhang, C.; Zhang, X.; Wang, T. ADriver-I: A general world model for autonomous driving. arXiv 2023, arXiv:2311.13549. [Google Scholar] [CrossRef]
- Dai, E.; Zhao, T.; Zhu, H.; Xu, J.; Guo, Z.; Liu, H.; Tang, J.; Wang, S. A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability. Mach. Intell. Res. 2024, online. [Google Scholar] [CrossRef]
- Zablocki, É.; Ben-Younes, H.; Pérez, P.; Cord, M. Explainability of deep vision-based autonomous driving systems: Review and challenges. Int. J. Comput. Vis. 2022, 130, 2425–2452. [Google Scholar] [CrossRef]
- Zheng, X.; Huang, H.; Wang, J.; Zhao, X.; Xu, Q. Behavioral decision-making model of the intelligent vehicle based on driving risk assessment. Comput.-Aided Civ. Infrastruct. Eng. 2021, 36, 820–837. [Google Scholar] [CrossRef]
- Li, L.; Gan, J.; Ji, X.; Qu, X.; Ran, B. Dynamic driving risk potential field model under the connected and automated vehicles environment and its application in car-following modeling. IEEE Trans. Intell. Transp. Syst. 2022, 23, 122–141. [Google Scholar] [CrossRef]
- Wang, J.; Wu, J.; Zheng, X.; Ni, D.; Li, K. Driving safety field theory modeling and its application in pre-collision warning system. Transp. Res. Part C Emerg. Technol. 2016, 72, 306–324. [Google Scholar] [CrossRef]
- Moghadam, M.; Elkaim, G.H. An autonomous driving framework for long-term decision-making and short-term trajectory planning on Frenet space. In Proceedings of the International Conference on Automation Science and Engineering, Lyon, France, 23–27 August 2021. [Google Scholar]
- Sharath, M.N.; Velaga, N.R. Enhanced intelligent driver model for two-dimensional motion planning in mixed traffic. Transp. Res. Part C Emerg. Technol. 2020, 120, 102780. [Google Scholar] [CrossRef]
- Lakhkar, R.A.; Talty, T. A naturalistic driving study for lane change detection and personalization. In Proceedings of the SAE World Congress Experience, Detroit, MI, USA, 16–18 April 2024. [Google Scholar]
- Krajewski, R.; Bock, J.; Kloeker, L.; Eckstein, L. The high Ddataset: A drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems. In Proceedings of the International Conference on Intelligent Transportation Systems, Maui, HI, USA, 4–7 November 2018. [Google Scholar]
- Gomes, L.P.; Wolf, D.F. Driving style recognition using interval type-2 fuzzy inference system and multiple experts decision-making. Int. J. Fuzzy Syst. 2024, 26, 553–571. [Google Scholar] [CrossRef]
- Duan, J.; Gao, F.; He, Y. Test scenario generation and optimization technology for intelligent driving systems. IEEE Intell. Transp. Syst. Mag. 2022, 14, 115–127. [Google Scholar] [CrossRef]
- Gao, F.; Duan, J.L.; Han, Z.D.; He, Y. Automatic virtual test technology for intelligent driving systems considering both coverage and efficiency. IEEE Trans. Veh. Technol. 2020, 69, 14365–14376. [Google Scholar] [CrossRef]
- ISO 2631-1; Mechanical Vibration and Shock-Evaluation of Human Exposure to Whole-Body Vibration (Part 1): General Requirements, Acoustical Society of America. International Organization for Standardization: Geneva, Switzerland, 1997.
- Shwartz, S.; Shammah, S.; Shashua, A. On a Formal Model of Safe and Scalable Self-driving Cars. arXiv 2017, arXiv:1708.06374. Available online: https://arxiv.org/pdf/1708.06374.pdf (accessed on 17 December 2024).
- Poszler, F.; Geisslinger, M.; Luetge, C. Ethical decision-making for self-driving vehicles: A proposed model & list of value-laden terms that warrant (technical) specification. Sci. Eng. Ethics 2024, 30, 47. [Google Scholar]
Proposed Method | IDM | |||||
---|---|---|---|---|---|---|
Acceleration (m/s2) | Speed (m/s) | Displacement (m) | Acceleration (m/s2) | Speed (m/s) | Displacement (m) | |
Mean | −0.011 | −0.059 | −0.061 | −0.168 | −0.225 | 0.547 |
Variance | 0.003 | 0.008 | 0.064 | 0.052 | 0.400 | 0.769 |
Mean (s) | Variance (s) | Max (s) | Min (s) | |
---|---|---|---|---|
Proposed method | −0.450 | 1.632 | 1.660 | −3.641 |
IDM | −1.969 | 2.259 | 0.950 | −5.389 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Gao, F.; Zheng, X.; Hu, Q.; Liu, H. Integrated Decision and Motion Planning for Highways with Multiple Objects Using a Naturalistic Driving Study. Sensors 2025, 25, 26. https://doi.org/10.3390/s25010026
Gao F, Zheng X, Hu Q, Liu H. Integrated Decision and Motion Planning for Highways with Multiple Objects Using a Naturalistic Driving Study. Sensors. 2025; 25(1):26. https://doi.org/10.3390/s25010026
Chicago/Turabian StyleGao, Feng, Xu Zheng, Qiuxia Hu, and Hongwei Liu. 2025. "Integrated Decision and Motion Planning for Highways with Multiple Objects Using a Naturalistic Driving Study" Sensors 25, no. 1: 26. https://doi.org/10.3390/s25010026
APA StyleGao, F., Zheng, X., Hu, Q., & Liu, H. (2025). Integrated Decision and Motion Planning for Highways with Multiple Objects Using a Naturalistic Driving Study. Sensors, 25(1), 26. https://doi.org/10.3390/s25010026