This paper proposes a reinforcement learning (RL)-based distributed leading cruise control (LCC) strategy for mixed vehicle platoons to ensure distance safety. First, a distributed modeling framework for mixed vehicle platoons composed of connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) is presented. Then, based on the parameter sharing proximal policy optimization (PS-PPO) algorithm, an RL controller is designed to achieve the distributed LCC for mixed vehicle platoons. Furthermore, a safety-critical control layer composed of robust control barrier function (RCBF) and quadratic programming (QP) is employed to provide distance safety guarantees. To extend the framework to multi-lane scenarios, a finite state machine (FSM)-based decision-making module is introduced to manage the lane-changing behavior of each CAV. Finally, the effectiveness of the distributed safety LCC strategy is verified on the simulation of urban mobility (SUMO) platform in both single-lane and multi-lane scenarios.
AkkayaSAkbatiOErgencAF (2021) Stability analysis of connected vehicles with V2V communication and time delays: CTCR method via Bézout’s resultant. Transactions of the Institute of Measurement and Control43(8): 1802–1829.
2.
AmesADCooganSEgerstedtM, et al. (2019) Control barrier functions: Theory and applications. In: Proceedings of the 18th European control conference (ECC), Naples, 25–28 June, pp. 3420–3431. New York: IEEE.
3.
AmosBKolterJZ (2017) Optnet: Differentiable optimization as a layer in neural networks. In: Proceedings of the 34th international conference on machine learning, Sydney, NSW, Australia, 6–11 August, pp. 136–145. Norfolk, MA: JMLR.
4.
ChengROroszGMurrayRM, et al. (2019) End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the thirty-third AAAI conference on artificial intelligence, vol. 33, Honolulu, HI, 27 January–1 February, pp. 3387–3395. Washington, DC: AAAI Press.
5.
CoskunSHuangCZhangF (2021) Quadratic programming-based cooperative adaptive cruise control under uncertainty via receding horizon strategy. Transactions of the Institute of Measurement and Control43(13): 2899–2911.
6.
EmamYNotomistaGGlotfelterP, et al. (2022) Safe reinforcement learning using robust control barrier functions. IEEE Robotics and Automation Letters10(3): 2886–2893.
7.
ErdmannJ (2014) Lane-changing model in SUMO. In: Proceedings of the SUMO2014 modeling mobility with open data, Berlin, 15–16 May, pp. 77–88. Cham: Springer.
8.
FengSSongZLiZ, et al. (2021) Robust platoon control in mixed traffic flow based on tube model predictive control. IEEE Transactions on Intelligent Vehicles6(4): 711–722.
9.
LiDDengHYuT, et al. (2025) Multi-vehicle cooperative localization using a TOA-based simulated annealing extended Kalman filter in urban canyons. IEEE Internet of Things Journal12(13): 22832–22846.
10.
LiKWangJZhengY (2022) Cooperative formation of autonomous vehicles in mixed traffic flow: Beyond platooning. IEEE Transactions on Intelligent Transportation Systems23(9): 15951–15966.
11.
LiMCaoZLiZ (2024) Augmented mixed vehicular platoon control with dense communication reinforcement learning for traffic oscillation alleviation. IEEE Internet of Things Journal11(22): 35989–36001.
12.
LiYLiZWangH, et al. (2017) Evaluating the safety impact of adaptive cruise control in traffic oscillations on freeways. Accident Analysis and Prevention104: 137–145.
13.
LiuLLiXLiY, et al. (2024) Reinforcement learning-based multi-lane cooperative control for on-ramp merging in mixed-autonomy traffic. IEEE Internet of Things Journal11(24): 39809–39819.
14.
MontaninoMPunzoV (2015) Trajectory data reconstruction and simulation-based validation against macroscopic traffic patterns. Transportation Research Part B: Methodological80: 82–106.
15.
MousaviSSBahramiSKouvelasA (2021) Output feedback controller design for a mixed traffic flow system moving in a loop. In: Proceedings of the American control conference (ACC), New Orleans, LA, 25–28 May, pp. 192–197. New York: IEEE.
16.
NingXZengMHuaM, et al. (2024) Multiple reconfigurable intelligent surfaces aided vehicular edge computing networks: A MAPPO-based approach. IEEE Transactions on Vehicular Technology73(11): 17496–17509.
17.
OroszG (2016) Connected cruise control: Modelling, delay effects, and nonlinear behaviour. Vehicle System Dynamics54(8): 1147–1176.
18.
SabouniEAhmadHMGiammarinoV, et al. (2024) Reinforcement learning-based receding horizon control using adaptive control barrier functions for safety-critical systems. In: Proceedings of the IEEE 63rd conference on decision and control (CDC), Milan, 16–19 December, pp. 401–406. New York: IEEE.
19.
ShiRLiTYamaguchiY, et al. (2025) Traffic scene-informed attribution of autonomous driving decisions. IEEE Transactions on Intelligent Transportation Systems26: 9175–9186.
20.
SternRECuiSDelle MonacheML, et al. (2018) Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments. Transportation Research Part C: Emerging Technologies89: 205–221.
21.
ThananjeyanBBalakrishnaANairS, et al. (2021) Recovery RL: Safe reinforcement learning with learned recovery zones. IEEE Robotics and Automation Letters6(3): 4915–4922.
22.
TreiberMHenneckeAHelbingD (2000) Congested traffic states in empirical observations and microscopic simulations. Physical Review E62(2): 1805.
23.
VogelK (2003) A comparison of headway and time to collision as safety indicators. Accident Analysis and Prevention35(3): 427–433.
24.
WangJZhengYChenC, et al. (2022a) Leading cruise control in mixed traffic flow: System modeling, controllability, and string stability. IEEE Transactions on Intelligent Transportation Systems23(8): 12861–12876.
25.
WangJZhengYLiK, et al. (2023a) Deep-LCC: Data-enabled predictive leading cruise control in mixed traffic flow. IEEE Transactions on Control Systems Technology31(6): 2760–2776.
26.
WangJZhengYXuQ, et al. (2021a) Controllability analysis and optimal control of mixed traffic flow with human-driven and autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems22(12): 7445–7459.
27.
WangJZhengYXuQ, et al. (2022b) Data-driven predictive control for connected and autonomous vehicles in mixed traffic. In: Proceedings of the American control conference (ACC), Atlanta, GA, 8–10 June, pp. 4739–4745. New York: IEEE.
28.
WangQDongHJuF, et al. (2023b) Adaptive leading cruise control in mixed traffic considering human behavioral diversity. IEEE Transactions on Intelligent Transportation Systems25(6): 5059–5070.
29.
WangQJuFWangH, et al. (2024) Multi-agent reinforcement learning for ecological car-following control in mixed traffic. IEEE Transactions on Transportation Electrification10(4): 8671–8684.
30.
WangSSternRLevinMW (2021b) Optimal control of autonomous vehicles for traffic smoothing. IEEE Transactions on Intelligent Transportation Systems23(4): 3842–3852.
31.
ZhanJHuaZZhangL (2023) Cooperative predictive control for arbitrarily mixed vehicle platoons with guaranteed global optimality. IET Intelligent Transport Systems17(8): 1702–1714.
32.
ZhanJMaZZhangL (2022) Data-driven modeling and distributed predictive control of mixed vehicle platoons. IEEE Transactions on Intelligent Vehicles8(1): 572–582.
33.
ZhanJZhangLJiaoQ (2025) Boundary consensus of networked hyperbolic systems of conservation laws. IEEE Transactions on Automatic Control70: 4989–5004.
34.
ZhaoCYuHMolnarTG (2023) Safety-critical traffic control by connected automated vehicles. Transportation Research Part C: Emerging Technologies154: 104230.
35.
ZhaoFZengGLuK (2019) EnLSTM-WPEO: Short-term traffic flow prediction by ensemble LSTM, NNCT weight integration, and population extremal optimization. IEEE Transactions on Vehicular Technology69(1): 101–113.
36.
ZhouJYanLYangK (2024) Enhancing system-level safety in mixed-autonomy platoon via safe reinforcement learning. IEEE Transactions on Intelligent Vehicles. Epub ahead of print 7 March. DOI: 10.1109/TIV.2024.3373512.
37.
ZhouYAhnSWangM, et al. (2020) Stabilizing mixed vehicular platoons with connected automated vehicles: An H-infinity approach. Transportation Research Part B: Methodological Methodol132: 152–170.
38.
ZhuMWangYPuZ, et al. (2020) Safe, efficient, and comfortable velocity control based on reinforcement learning for autonomous driving. Transportation Research Part C: Emerging Technologies117: 102662.
