Merging Strategy for Autonomous Vehicles on Highways Based on Acceptance Gaps and Model Predictive Control
DOI:
https://doi.org/10.54097/1svzjz89Keywords:
Ramp merging, Acceptance Gap, Gipps, MPC.Abstract
With the development of autonomous driving technology, highway ramp merging has become a critical challenge. The ramp merging area is a complex node in the highway system, where improper merging can lead to traffic congestion and accidents. Therefore, studying merging strategies for autonomous vehicles at highway entrances is of great significance for improving traffic safety and flow, as well as promoting the overall development of intelligent transportation systems. This paper proposes a merging strategy based on acceptance gaps and a Model Predictive Controller (MPC). A safety acceptance gap model and an experience acceptance gap model were constructed based on the Gipps model and historical data, respectively. By balancing merging efficiency and safety, a dynamic acceptance gap model with linear fusion was proposed. During the merging process, an MPC was used, which constructed the corresponding cost function and constraints based on the characteristics of highway ramp merging. Using the concept of dynamic programming, the MPC designed a merging trajectory controller. Finally, the effectiveness and feasibility of the merging strategy were verified through simulation experiments.
Downloads
References
Lv Ying, Cao Yuntao, Dong Xiaoyu, et al. Intelligent vehicle decision-making method for highway off-ramp scenarios [C] // China Society of Automotive Engineers. Proceedings of the 2023 Annual Conference of China Society of Automotive Engineers (1). State Key Laboratory of Advanced Automotive Integrated Control; China FAW Group Corporation; State Key Laboratory of Automotive Simulation and Control, Jilin University, 2023: 5. DOI: 10.26914/c.cnkihy.2023.063501.
Zhang Cunbao, Li Jinsong, Huang Chuanming, et al. Vehicle merging guidance method for highway entrance ramps based on vehicle-infrastructure cooperation [J]. Journal of Wuhan University of Technology (Transportation Science & Engineering Edition), 2017, 41(04): 537-542.
Guo Y, Ma J. Leveraging existing high-occupancy vehicle lanes for mixed-autonomy traffic management with emerging connected automated vehicle applications[J]. Transportmetrica A: Transport Science, 2020, 16(3): 1375-1399.
Nishi T, Doshi P, Prokhorov D. Merging in congested freeway traffic using multipolicy decision making and passive actor-critic learning[J]. IEEE Transactions on Intelligent Vehicles, 2019, 4(2): 287-297.
Mo S, Pei X, Chen Z. Decision-making for oncoming traffic overtaking scenario using double DQN[C]//2019 3rd Conference on Vehicle Control and Intelligence (CVCI). IEEE, 2019: 1-4.
Lu Ziyang. Research on automatic driving ramp merging decision-making based on deep reinforcement learning [D]. Jilin University, 2023. DOI: 10.27162/d.cnki.gjlin.2023.001383.
Treiber M, Hennecke A, Helbing D. Congested traffic states in empirical observations and microscopic simulations[J]. Physical review E, 2000, 62(2): 1805.
Kesting A, Treiber M, Helbing D. General lane-changing model MOBIL for car-following models[J]. Transportation Research Record, 2007, 1999(1): 86-94.
Liang, G., Shi, Q., Li, R., et al. (2021). The Impact of Main Parameters in Highway Merge Areas on Autonomous Vehicles. Journal of Harbin Institute of Technology, 53(9), 62-68.
Tang, S. (2020). Research on Lane-changing Decision-making of Intelligent Vehicles in Highway Merge Areas Based on Deep Reinforcement Learning [D]. Chongqing University. DOI: 10.27670/d.cnki.gcqdu.2020.001733.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
