The following control problem is a challenging issue in vehicle adaptive cruise control. In the control process, multiple objectives need to be considered while ensuring safety. To comprehensively study and evaluate the following control algorithms, this paper establishes a following model, vehicle model, and energy consumption model. After verifying the accuracy of the models, corresponding proportion-integral-derivative (PID), model predictive control (MPC), and adaptive dynamic programing (ADP) algorithms are proposed based on the models. The three algorithms are integrated into a vehicle using Simulink, and real vehicle experiments are conducted. The results show that the MPC algorithm achieves the best control performance and exhibits superior disturbance rejection capabilities. The control performance of the ADP and PID algorithms is ranked second. However, the MPC algorithm has very limited computational margin, which may restrict the use of additional computational resources. Therefore, in situations where computational resources are relatively scarce and strict control performance requirements are not imposed, the ADP algorithm can be used as a substitute for the MPC algorithm. The traditional PID algorithm exhibits the best real-time performance but significantly weaker control performance and disturbance rejection capabilities compared to the other two algorithms.
YangL. Study on traffic congestion pricing considering vehicle emission – taking Gucheng district of Suzhou as an example. PhD dissertation, Southeast University, China, 2020.
2.
BaskarLDHellendoornJDe SchutterB, et al. Traffic control and intelligent vehicle highway systems: a survey. IET Intell Transp Syst2011; 5(1): 38–52.
3.
SinghS. Critical reasons for crashes investigated in the national motor vehicle crash causation survey. Tech. Rep., 2018.
4.
CicchinoJB. Effectiveness of forward collision warning and autonomous emergency braking systems in reducing front-to-rear crash rates. Accid Anal Prev2017; 99: 142–152.
5.
LuoLHLiuHLiP, et al. Model predictive control for adaptive cruise control with multi-objectives: comfort, fuel-economy, safety, and car-following. J Zhejiang Univ Sci A2010; 11(3): 191–201.
6.
WuGGuoXZhangL. Multi-objective robust adaptive cruise control algorithm design of car following model. J Harbin Inst Technol2016; 48(1): 80–86.
GuvencBAKuralE. Adaptive cruise control simulator: a low-cost, multiple-driver-in-the-loop simulator. IEEE Control Syst Mag2006; 26(3): 42–55.
9.
HuPGuoJLiN, et al. A robust longitudinal sliding-mode controller design for autonomous ground vehicle based on fuzzy logic. Int J Veh Auton Syst2013; 11(4): 368.
10.
NaranjoJEGonzalezCGarciaR, et al. ACC+Stop&Go maneuvers with throttle and brake fuzzy control. IEEE Trans Intell Transp Syst2006; 7(2): 213–225.
11.
ChuHGuoLChenH, et al. Optimal car-following control for intelligent vehicles using online road-slope approximation method. Sci China Inf Sci2021; 64: 16.
12.
LiSLiKRajamaniR, et al. Model predictive multi-objective vehicular adaptive cruise control. IEEE Trans Control Syst Technol2011; 19(3): 556–566.
13.
ErnstDGlavicMCapitanescuF, et al. Reinforcement learning versus model predictive control: a comparison on a power system problem. IEEE Trans Syst Man Cybern B2009; 39(2): 517–529.
14.
LinYMcPheeJAzadNL. Comparison of deep reinforcement learning and model predictive control for adaptive cruise control. IEEE Trans Intell Vehicles2021; 6: 221–231.
15.
WangBZhaoDChengJ. Adaptive cruise control via adaptive dynamic programming with experience replay. Soft Comput2019; 23(12): 4131–4144.
16.
LiGGorgesD. Ecological adaptive cruise control for vehicles with step-gear transmission based on reinforcement learning. IEEE Trans Intell Transp Syst2020; 21: 4895–4905.
17.
JiangLWangYWangL, et al. Path tracking control based on deep reinforcement learning in Autonomous driving. In: 2019 3rd conference on vehicle control and intelligence (CVCI), pp.1–6. New York: IEEE.
18.
ChenXZhaiYLuC, et al. A learning model for personalized adaptive cruise control. In: 2017 IEEE intelligent vehicles symposium (IV), 2017, pp.379–384. New York: IEEE.
19.
ZhangY. Research on reinforcement learning algorithm for longitudinal control of autonomous vehicles. PhD dissertation, Jilin University, China, 2020.
20.
SunMZhaoWSongG, et al. DDPG-based decision-making strategy of adaptive cruising for heavy vehicles considering stability. IEEE Access2020; 8: 59225–59246.
21.
ZhuBJiangYZhaoJ, et al. A car-following control algorithm based on deep reinforcement learning. China J Highway Transport2019; 32(6): 53–60.
22.
WangS. Research on driving decision-making algorithms of intelligent vehicles for structured road environment. PhD dissertation, Jilin University, China, 2019.
23.
PanFBaoH. Reinforcement learning model with a reward function based on human driving characteristics. In: 2019 15th International conference on computational intelligence and security (CIS), 2019, pp.225–229. New York: IEEE.
24.
LiuDWangDYangX. An iterative adaptive dynamic programming algorithm for optimal control of unknown discrete-time nonlinear systems with constrained inputs. Inf Sci2013; 220: 331–342.
25.
HuangCXuSWangZ, et al. Opportunistic intermittent control with safety guarantees for autonomous systems. In: 2020 57th ACM/IEEE design automation conference (DAC), 2020, pp.1–6. New York: IEEE.
26.
DeyKCYanLWangX, et al. A review of communication, driver characteristics, and controls aspects of cooperative adaptive cruise control (CACC). IEEE Trans Intell Transp Syst2016; 17(2): 491–509.
27.
MoonSYiK. Human driving data-based design of a vehicle adaptive cruise control algorithm. Veh Syst Dyn2008; 46(8): 661–690.
28.
GaoWGaoJOzbayK, et al. Reinforcement-learning-based cooperative adaptive cruise control of buses in the Lincoln tunnel corridor with time-varying topology. IEEE Trans Intell Transp Syst2019; 20(10): 3796–3805.
29.
LiSEPengH. Strategies to minimize the fuel consumption of passenger cars during car-following scenarios. Proc IMechE, Part D: J Automobile Engineering2012; 226(3): 419–429.
30.
LiSEGuoQXinL, et al. Fuel-saving servo-loop control for an adaptive cruise control system of road vehicles with step-gear transmission. IEEE Trans Vehicular Technol2017; 66(3): 2033–2043.
31.
JiaYSaitoTItohY, et al. Energy-optimal adaptive cruise control in time domain based on model predictive control. IFAC-PapersOnLine2018; 51(31): 846–853.
32.
RenJ. Research on adaptive cruise control of pure electric vehicles based on multi-objective optimization. PhD dissertation, Beijing Jiaotong University, China, 2020.
33.
YiKChungJ. Nonlinear brake control for vehicle CW/CA systems. IEEE/ASME Trans Mechatron2001; 6(1): 17–25.
34.
MartinezJJCanudas-de WitC. A safe longitudinal control for adaptive cruise control and stop-and-go scenarios. IEEE Trans Control Syst Technol2007; 15(2): 246–258.
35.
SaatyTL. Decision making with the analytic hierarchy process. Int J Serv Sci2008; 1(1): 83.
36.
LiS. Research on vehicle adaptive cruise control strategy based on MPC. PhD dissertation, Chang’an University, China, 2019.
37.
MurrayJJCoxCJLendarisGG, et al. Adaptive dynamic programming. IEEE Trans Syst Man Cybern C2002; 32(2): 140–153.
LewisFLVrabieD. Reinforcement learning and adaptive dynamic programming for feedback control. IEEE Circuits Syst Mag2009; 9(3): 32–50.
40.
SiJBartoAGPowellWB, et al. Handbook of learning and approximate dynamic programming. New York: John Wiley & Sons, 2004, vol. 2.
41.
Al-TamimiALewisFLAbu-KhalafM. Discrete-time nonlinear HJB solution using approximate dynamic programming: convergence proof. IEEE Trans Automat Contr2008; 38(4): 943–2649.
42.
LooHJKimJ. Adaptive dynamic programming based guidance law design against maneuvering target. J Guid Control Dyn2017; 40(2): 407–412.
43.
AngeliDSontagED. Approximate feedback linearization via neural networks. Syst Control Lett2005; 54(2): 199–208.
44.
KimJKSastryS. Nonlinear control for a class of systems arising in vehicle dynamics. IEEE Trans Automat Contr1995; 40(8): 1470–1473.
45.
WangFYJinNLiuD. Adaptive dynamic programming for finite-horizon optimal control of discrete-time nonlinear systems with ε-error bound. IEEE Trans Neural Netw2011; 22(1): 24–36.
46.
WangDLiuDWeiQ. Finite-horizon neuro-optimal tracking control for a class of discrete-time nonlinear systems using adaptive dynamic programming approach. Neurocomputing2012; 78(1): 14–22.
47.
BuechelMKnollA. Deep reinforcement learning for predictive longitudinal control of automated vehicles. In: Proc. 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, 2018, pp.2391–2397.
48.
BoydSBoydSPVandenbergheL. Convex optimization. Cambridge: Cambridge University Press, 2004.
