The control performance of model predictive control (MPC) strongly depends on the accuracy of the model description. To better capture and predict the dynamic behaviors of the controlled plant, a non-parametric model which is regressed by the Gaussian Process (GP) is proposed in this paper to evaluate the unknown deviation between the nominal model and the physical system. Firstly, an efficient MPC formulation that integrates a nominal model with GP model which evaluates the unmodeled dynamics is designed for safe and robust maneuver planning. Secondly, the geometric hard constraints for collision avoidance between ego cars and obstacles are softened by using a relaxed barrier function for optimization efficiency. A configuration space convexification algorithm is designed for convexifying the corridor constraints in path pre-selection and re-planned for obstacle avoidance. The control performance of the learning-based MPC is demonstrated and compared with the standard MPC strategy under two typical scenarios. Numerical simulation as well as experiment results indicate that the proposed method could keep the safety, stability, and maneuverability of the ego vehicle during obstacle avoidance.
MercorelliPVossTStrassbergerD, et al. Optimal trajectory generation using MPC in robotino and its implementation with ROS system. In: 2017 IEEE 26th international symposium on industrial electronics (ISIE), Edinburgh, UK, 19–21 June 2017, pp.1642–1647. New York: IEEE.
2.
RaaijmakersM. Towards environment perception for highly automated driving: with a case study on roundabouts. PhD Thesis, Eindhoven University of Technology, Eindhoven, 2017.
3.
ForbesMGPatwardhanRSHamadahH, et al. Model predictive control in industry: challenges and opportunities. IFAC Pap OnLine2015; 48(8): 531–538.
4.
RosoliaUDe BruyneSAlleyneAG. Autonomous vehicle control: a nonconvex approach for obstacle avoidance. IEEE Trans Control Syst Technol2016; 25(2): 469–484.
5.
BerntorpKQuirynenRUnoT, et al. Trajectory tracking for autonomous vehicles on varying road surfaces by friction-adaptive nonlinear model predictive control. Veh Syst Dyn2019; 58(5): 705–725.
6.
WischnewskiAHerrmannTWernerF, et al. A tube-MPC approach to autonomous multi-vehicle racing on high-speed ovals. IEEE Trans Intell Veh2022; 8(1): 368–378.
7.
LiuJJayakumarPSteinJL, et al. A nonlinear model predictive control formulation for obstacle avoidance in high-speed autonomous ground vehicles in unstructured environments. Veh Syst Dyn2017; 56(6): 853–882.
8.
BruntonSLKutzJN. Data-driven science and engineering: machine learning, dynamical systems, and control. Cambridge: Cambridge University Press, 2019.
9.
KabzanJHewingLLinigerA, et al. Learning-based model predictive control for autonomous racing. IEEE Robot Autom Lett2019; 4(4): 3363–3370.
10.
SeborgDEMellichampDAEdgarTF, et al. Process dynamics and control. Hoboken, New Jersey: John Wiley & Sons, 2019.
11.
HedmanMMercorelliP. FFTSMC with optimal reference trajectory generated by MPC in robust robotino motion planning with saturating inputs. In: 2021 American control conference (ACC), New Orleans, LA, USA, 25–28 May 2021, pp.1470–1477. New York: IEEE.
12.
ChaiRTsourdosASavvarisA, et al. Design and implementation of deep neural network-based control for automatic parking maneuver process. IEEE Trans Neural Netw Learn Syst2020; 99: 1–14.
13.
YangHPanCQinY, et al. Dual-loop tube-based robust model predictive control for active suspension system with parameter uncertainty. In: 2021 5th CAA international conference on vehicular control and intelligence (CVCI), Tianjin, China, 29–31 October 2021.
14.
ZhaoYGeLZhongS, et al. An efficient solver of predictive control methods for motion control of autonomous vehicles with experimental verification. Proc IMechE, Part D: J Automobile Engineering2023; 237(6): 1423–1434.
15.
MesbahA. Stochastic model predictive control with active uncertainty learning: a survey on dual control. Annu Rev Control2018; 45: 107–117.
16.
RenHChenSYangL, et al. Optimal path planning and speed control integration strategy for UGVs in static and dynamic environments. IEEE Trans Veh Technol2020; 69(10): 10619–10629.
17.
PichéSSayyar-RodsariBJohnsonD, et al. Nonlinear model predictive control using neural networks. IEEE Control Syst Mag2000; 20(3): 53–62.
18.
ThangavelSLuciaSPaulenR, et al. Dual robust nonlinear model predictive control: a multi-stage approach. J Process Control2018; 72: 39–51.
19.
WangYKangFWangT, et al. A robust control method for lateral stability control of in-wheel motored electric vehicle based on sideslip angle observer. Shock Vib2018; 2018: 1–11.
20.
RosoliaUBorrelliF. Learning how to autonomously race a car: a predictive control approach. IEEE Trans Control Syst Technol2019; 28(6): 2713–2719.
21.
RosoliaUZhangXBorrelliF. Data-driven predictive control for autonomous systems. Annu Rev Control Robot Auton Syst2018; 1(1): 259–285.
22.
HewingLKabzanJZeilingerMN. Cautious model predictive control using Gaussian process regression. IEEE Trans Control Syst Technol2019; 28(6): 2736–2743.
23.
KollerTBerkenkampFTurchettaM, et al. Learning-based model predictive control for safe exploration. In: IEEE conference on decision and control, Miami, FL, USA, 17–19 December 2018, pp.6059–6066. New York: IEEE.
24.
ZhangKWangJXinX, et al. A survey on learning-based model predictive control: toward path tracking control of mobile platforms. Appl Sci2022; 12(4): 1–25.
25.
LiuCLinCYTomizukaM. The convex feasible set algorithm for real time optimization in motion planning. SIAM J Control Optim2018; 56(4): 2712–2733.
26.
WischnewskiAEulerMGümüsS, et al. Tube model predictive control for an autonomous race car. Veh Syst Dyn2022; 60(9): 3151–3173.
27.
KamelMAlonso-MoraJSiegwartR, et al. Robust collision avoidance for multiple micro aerial vehicles using nonlinear model predictive control. In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS), Vancouver, BC, Canada, 24–28 September 2017.
28.
RasmussenCE. Gaussian processes in machine learning. In: BousquetOvon LuxburgURätschG (eds) Summer school on machine learning. Berlin, Heidelberg: Springer, 2003, pp.63–71.
29.
RenHShimTRyuJ, et al. Development of effective bicycle model for wide ranges of vehicle operations. SAE technical paper 2014-01-0841, 2014.
30.
PacejkaH. Tire and vehicle dynamics. Oxford: Elsevier, 2005.
31.
NguyenTLaHMLeTD, et al. Formation control and obstacle avoidance of multiple rectangular agents with limited communication ranges. IEEE Trans Control Netw Syst2016; 4(2): 680–691.
32.
BoydSPVandenbergheL. Convex optimization. Cambridge: Cambridge University Press, 2004.
33.
GrandiaRFarshidianFRanftlR, et al. Feedback MPC for torque-controlled legged robots. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), Macau, China, 3–8 November 2019, pp.4730–4737. New York: IEEE.
34.
SawmaJKhatounianFMonmassonE, et al. The effect of prediction horizons in MPC for first order linear systems. In: 2018 IEEE international conference on industrial technology (ICIT), Lyon, France, 20–22 February 2018.
