Learning-based nonlinear model predictive control with accurate uncertainty compensation

Xie, Jingjie; Zhao, Xiaowei; Dong, Hongyang

doi:10.1007/s11071-021-06522-z

Cited by 6 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, the prediction accuracy of the model is not satisfactory. The uncertainty in the system arises from unmodeled nonlinearities or external disturbances and are contained in a finite set of dependent states [25]. Therefore, the uncertainty set is obtained from the data by using GP regression [80,81] or reinforcement learning [82,83], and then a dynamic model is formed with additional uncertainties.…”

Section: Data-driven Prediction Modelsmentioning

confidence: 99%

“…It handles system constraints, optimizes performance with respect to a cost function, uses statistical identification tools to learn model uncertainties, and provably converges. Afterwards, the LB-MPC method was researched [22][23][24], and different schemes were designed [25,26]. There are various ML techniques that have been explored and applied to MPC, such as regression learning [27], reinforcement learning [28], and deep learning [29,30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms

et al. 2022

View full text Add to dashboard Cite

The learning-based model predictive control (LB-MPC) is an effective and critical method to solve the path tracking problem in mobile platforms under uncertain disturbances. It is well known that the machine learning (ML) methods use the historical and real-time measurement data to build data-driven prediction models. The model predictive control (MPC) provides an integrated solution for control systems with interactive variables, complex dynamics, and various constraints. The LB-MPC combines the advantages of ML and MPC. In this work, the LB-MPC technique is summarized, and the application of path tracking control in mobile platforms is discussed by considering three aspects, namely, learning and optimizing the prediction model, the controller design, and the controller output under uncertain disturbances. Furthermore, some research challenges faced by LB-MPC for path tracking control in mobile platforms are discussed.

show abstract

Section: Data-driven Prediction Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The adaptive optimal control problem of discrete nonlinear systems under random disturbances proves the algorithm's convergence in each prediction horizon and the Lyapunov stability of the closed-loop control system. In previous works, 113,115 the proposed LBNMPC strategy decouples the robustness and performance requirements by using an additional learning model and introducing it into the MPC framework together with the nominal model. The nominal model guarantees the safety and stability of the closed-loop system.…”

Section: Stability Of Lb-nmpcmentioning

confidence: 99%

Emerging methodologies in stability and optimization problems of learning‐based nonlinear model predictive control: A survey

Meng

Shen

Karimi

2022

Circuit Theory & Apps

View full text Add to dashboard Cite

Since last 40 years, the theory and technology of model predictive control (MPC) have been developed rapidly. However, nonlinear MPC still faces difficulties such as high online computational complexity and inability to accurately model the system. In order to improve or solve the problems mentioned above of MPC, recent researches have deepened the learning‐based control. The learned method can model unknown or highly uncertain nonlinearities. And the emergence of efficient algorithms has greatly improved the feasibility of computing. Stability is at the heart of control design. Learning‐based nonlinear model predictive control (LB‐NMPC) has achieved systematic research results in the past 10 years. But the stability of LB‐NMPC is still an open question that has not been fully addressed in the literature. This review mainly summarizes the latest research progress of LB‐NMPC. More specifically, the uncertainty and online optimization problems of the considered systems are investigated mainly focusing on the use of learning techniques. At the same time, the research hotspots such as the control stability and constraint satisfaction of LB‐NMPC are briefly discussed. Finally, the application of LB‐NMPC technology in integrated circuits, path tracking control, and other fields is reviewed, which provides a reference for the research and application of LB‐NMPC.

show abstract

On Real-time Cooperative Trajectory Planning of Aerial-ground Systems

Huang,

Chen,

Zhang

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

Cooperative trajectory planning of aerial-ground systems is a fundamental and challenging problem, which aims to leverage the aerial information to assist the ground tasks. Existing methods often suffer from suboptimal trajectories or computation burden. In this paper, we address cooperative trajectory planning of aerial-ground systems in which an unmanned ground vehicle (UGV) plans its local trajectory in real-time with the assistance of an unmanned aerial vehicle (UAV). Firstly, the UAV generates guidance trajectory using nonlinear model predictive control (NMPC), which considers the obstacle distribution density as a factor reflecting the coupling effect of multiple obstacles on the UGV, thereby avoiding local minima problem and improving the feasibility of the planned trajectory. Secondly, a null-space-based behavioral control (NSBC) framework is employed to merge the guidance trajectory into the UGV’s own planned one as a task. Finally, an event triggering task supervisor is developed for the UGV to decide the priorities of all tasks, which reduces the switching frequency of task priorities brought by traditional rule-based task supervisors. Both simulation and experiment results show that the proposed approach has superior trajectory planning performance in terms of trajectory error, on-line computation time and the success rate of task execution.

show abstract

Learning-based nonlinear model predictive control with accurate uncertainty compensation

Cited by 6 publications

References 50 publications

A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms

A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms

Emerging methodologies in stability and optimization problems of learning‐based nonlinear model predictive control: A survey

On Real-time Cooperative Trajectory Planning of Aerial-ground Systems

Contact Info

Product

Resources

About