Research on Adaptive Predictive Control Algorithm for Autonomous Driving

In order to alleviate the congestion between the side road and the freeway, a novel balancing control scheme is proposed based on model free adaptive predictive balancing control (MFAPBC). The proposed MFAPBC is a typical data driven control method, which merely utilize the measured input and output (I/O) data of side road and freeway to update the control input signal. Model free adaptive predictive control (MFAPC) has the advantages of model predictive control (MPC) and model free adaptive control (MFAC); that is, only the I/O data of the controlled plant are used to predict the system output sequence within the prediction horizon and to calculate the control input sequence within the control input horizon, without the controlled plant model involved. The effectiveness of the proposed MFAPBC method is test in simulation for side road and freeway system.

Robots and automated systems are increasingly being introduced to unknown and dynamic environments where they are required to handle disturbances, unmodeled dynamics, and parametric uncertainties. Robust and adaptive control strategies are required to achieve high performance in these dynamic environments. In this paper, we propose a novel adaptive model predictive controller that combines model predictive control (MPC) with an underlying $\mathcal{L}_{1}$ adaptive controller to improve trajectory tracking of a system subject to unknown and changing disturbances. The $\mathcal{L}_{1}$ adaptive controller forces the system to behave in a predefined way, as specified by a reference model. A higher-level model predictive controller then uses this reference model to calculate the optimal reference input based on a cost function, while taking into account input and state constraints. We focus on the experimental validation of the proposed approach and demonstrate its effectiveness in experiments on a quadrotor. We show that the proposed approach has a lower trajectory tracking error compared to non-predictive, adaptive approaches and a predictive, nonadaptive approach, even when external wind disturbances are applied.

Adaptive model predictive control for a class of constrained linear systems based on the comparison model

In this paper, an adaptive reduced-horizon model predictive control is proposed for autonomous parking trajectory tracking. Given the reference trajectory, the discrete linear time varying model is obtained by linearizing and discretizing along the reference trajectory point. Furthermore, the model is reformulated into a combined incremental form. Then, a standard quadratic programming problem is established, and the optimal control strategy is obtained by solving the problem online at every time instant. Meanwhiles, the prediction horizon will reduce adaptively by solving the constrained optimization problem, and it will minimize the computation time complexity of the MPC-based controller. The actual parking scenarios are co-simulated in Simulink and Carsim, which shows the effectiveness and feasibility of the proposed method.

<div class="section abstract"><div class="htmlview paragraph">To meet the traffic control demands of highway merging areas and address the accuracy error of traffic flow prediction models, a cooperative control strategy based on adaptive prediction horizon Model Predictive Control (MPC) has been proposed for variable speed limits (VSL) and dynamic hard shoulder running (HSR). Firstly, the METANET model was improved based on the characteristics of merging areas and the impact of cooperative control strategy. Secondly, to mitigate the negative impact of the METANET prediction errors on control effectiveness, a fuzzy rule-based adaptive prediction horizon controller is designed. Thirdly, a cooperative control strategy for VSL and dynamic HSR is formulated under the MPC framework, aiming to optimize Total Time Spent(TTS)and Total Travel Distance (TTD), using genetic algorithms equipped with sliding time windows for resolution. Finally, using actual traffic flow data from Changtai Highway, simulation experiments are conducted, involving four scenarios: HSR-VSL control, VSL-only control, HSR-only control, and no control. In the cooperative control scenario, both adaptive and fixed prediction horizon approaches are considered. Results show that the proposed HSR-VSL control strategy with fixed prediction horizon reduces the total travel time and mainline density by 20.02% and 10.78% respectively, outperforming single strategies (only HSR or VSL). Compared to a fixed prediction horizon, the VSL-HSR with adaptive prediction horizon delivers even better results, reducing total travel time and mainline density by 24.53% and 12.94% respectively, proving the effectiveness of the cooperative control strategy and the adaptive prediction horizon controller.</div></div>

Nonlinear model identification and adaptive model predictive control using neural networks

Compared to four-wheel independent drive and steering (4WID4WIS) mobile robots, three-wheel independent drive and steering (3WID3WIS) mobile robots are more cost-effective due to their lower cost, lighter weight, and better handling performance, even though their acceleration performance is reduced. This paper proposes a dynamic model predictive control (DMPC) controller for trajectory tracking of 3WID3WIS mobile robots to simplify the computational complexity and improve the accuracy of traditional model predictive control (MPC). The A* algorithm with a non-point mass model is used for path planning, enabling the robot to navigate quickly in narrow and constrained environments. Firstly, the kinematic model of the 3WID3WIS mobile robot is established. Then, based on this model, a DMPC trajectory tracking controller with dynamic effects is developed. By replacing MPC with DMPC, the computational complexity of MPC is reduced. During each control period, the prediction horizon is dynamically adjusted based on changes in trajectory curvature, establishing a functional relationship between trajectory curvature and prediction horizon. Subsequently, a comparative study between the proposed controller and the traditional MPC controller is conducted. Finally, the new controller is applied to address the trajectory tracking problem of the 3WID3WIS mobile robot. The experimental results show that DMPC improves the lateral trajectory tracking accuracy by 62.94% and the heading angle tracking accuracy by 34.81% compared to MPC.

Automatic canal control is essential to improve water utilization efficiency in irrigation districts. Water level error in the model used by the control algorithm significantly impacts performance. The integrator delay model, which has a linear structure, is widely used in multi-input/multioutput control algorithms, including linear-quadratic control and model predictive control. However, the integrator delay model is suboptimal for large irrigation districts; the canals are long, the flows are large, there are many scattered offtakes, and the operating conditions vary. We developed an adaptive predictive control mode for the Qinhan Canal in Ningxia Province, China. We used a segment integrator delay model for this large irrigation district and employed a differential evolution algorithm for online system identification; this minimizes error. We analyzed and controlled for various uncertainties (i.e., flow observation noise, geometric and hydraulic parameter errors, and accidental interference with the automatic control system). Simulations indicated that the water level fitting errors were significantly reduced compared with the original model, and water level regulation was significantly improved, especially in terms of the maximum absolute error. Adaptive predictive control was better than linear-quadratic control and model predictive control approach for water level. Adaptive predictive control coped well with several uncertainties. The main factors affecting water level control were the flow observation and gate opening control accuracy, and the extent of real-time data coverage. These features require careful attention when automating and modernizing irrigation districts.

This paper develops methodologies and techniques for the design, analysis and implementation of a model reference adaptive predictive temperature controller for a variable frequency oil-cooling machine, suited for cooling high-speed machine tools. The oil-cooling process is modeled experimentally as a first-order system model with a time-delay, and its system parameters are identified using the recursive least-square method. Based on this model, a model-reference adaptive predictive controller is proposed for achieving set-point tracking and disturbance rejection. A real-time model-reference adaptive predictive control algorithm is then presented and implemented utilizing a standalone digital signal processor TMS320F243 from Texas Instruments. The experimental results show that the proposed control method is proven capable of giving satisfactory performance under set-point changes, fixed loads and load changes.

The article discusses the problems of development of the system of adaptive predictive control of pellets heat treatment with online estimation of parameters of the process model. Due to nonstationarity in time of the process parameters caused by fluctuations of particle size distribution and fractional void of the layer, changes in the process equipment characteristics and the presence of noise in measurement channels, the existing automation systems of pellets heat treatment do not always allow to solve the problem of stabilization temperature profile in the pellets layer, as well as reduce the specific consumption of energy. To overcome these disadvantages the recursive least squares algorithm is proposed to use for estimating the parameters of process model which subsequently is the base for calculating the manipulated variable (the gas flow to the burner of the leading side of the indurating machine) with using the methods of Model Predictive Control theory that provides maintenance of a preset temperature regime of pellets indurating under conditions of uncontrolled disturbances. In accordance with the described approach it is suggested the variant of the structure of the system of adaptive predictive control of the temperature regime of pellets indurating in the separate gas-air chamber of indurating machine, and the simulation of this system was performed in Simulink package with the use of real data about the dependence of temperature in the heart of firing zone from gas consumption on the burner of leading side, which were obtained in a mode of passive experiment at the indurating machine OK-324 of JSC «Central GOK (ME)». The resulting system has demonstrated the high quality of the online estimation of parameters and sufficient convergence rate for conditions of pellets heat treatment. The obtained results allow us to recommend the developed method of formation of adaptive predictive control for automation of pellets heat treatment.

The performance of the path tracking control system is poor when vehicles navigate under extreme conditions of high speed and large curvature due to the uncertainty of vehicle model parameters, modeling errors and disturbances. To address this issue, this paper introduces a Linear Model Predictive Controller (GP‐SOMPC) based on Gaussian Process (GP) and Snake Optimizer (SO) to achieve high‐performance trajectory tracking control under large curvatures through learning. This algorithm adopts a two‐degree‐of‐freedom vehicle dynamics model and models disturbances and unmodeled dynamics as Gaussian Processes (GP) using collected experimental data. Additionally, an Adaptive Weighting Coefficient Model Predictive Controller based on the Snake Optimizer (SO) method is presented to improve the poor adaptation of vehicle trajectory tracking accuracy according to reference path curvature under fixed weighting coefficients in traditional Model Predictive Control (MPC), which results in inadequate trajectory tracking precision. The simulation experiments have verified that the proposed GP‐SOMPC algorithm can enhance trajectory tracking precision under high‐speed, large curvature conditions and exhibits good adaptability to variations in path curvature.

Safe and efficient motion planning in unknown, cluttered environments is a critical challenge for autonomous robots. This paper introduces a meta-learning-enhanced motion planning framework that integrates multi-scale risk prediction with adaptive model predictive control (MPC) to address this challenge. In this work, we propose a unified meta-learned model for signed distance function prediction, termed Meta-SDF-a single neural network that learns generic geometric priors from diverse obstacle types during offline training. At runtime, the Meta-SDF rapidly adapts to novel, unseen obstacles using only a small amount of point cloud data, without prior knowledge of obstacle geometry. For online planning, we develop a risk-aware adaptive MPC framework augmented with control barrier functions (CBFs), where safety constraints are derived from the adapted Meta-SDF. A key innovation is a multi-scale risk prediction mechanism that evaluates collision risk across short-, mid-, and long-term horizons within the MPC prediction window. This risk metric dynamically guides an adaptive strategy that adjusts both the MPC solving frequency and prediction horizon: high-risk scenarios trigger high-frequency solving with a shortened horizon for reactive obstacle avoidance, while low-risk scenarios employ lower-frequency solving with an extended horizon for efficient goal-directed planning. Simulation experiments demonstrate the efficacy of the proposed framework.

In this paper, a learning-based predictive control (LPC) scheme is proposed for adaptive optimal control of discrete-time nonlinear systems under stochastic disturbances. The proposed LPC scheme is different from conventional model predictive control (MPC), which uses open-loop optimization or simplified closed-loop optimal control techniques in each horizon. In LPC, the control task in each horizon is formulated as a closed-loop nonlinear optimal control problem and a finite-horizon iterative reinforcement learning (RL) algorithm is developed to obtain the closed-loop optimal/suboptimal solutions. Therefore, in LPC, RL and adaptive dynamic programming (ADP) are used as a new class of closed-loop learning-based optimization techniques for nonlinear predictive control with stochastic disturbances. Moreover, LPC also decomposes the infinite-horizon optimal control problem in previous RL and ADP methods into a series of finite horizon problems, so that the computational costs are reduced and the learning efficiency can be improved. Convergence of the finite-horizon iterative RL algorithm in each prediction horizon and the Lyapunov stability of the closed-loop control system are proved. Moreover, by using successive policy updates between adjoint time horizons, LPC also has lower computational costs than conventional MPC which has independent optimization procedures between two different prediction horizons. Simulation results illustrate that compared with conventional nonlinear MPC as well as ADP, the proposed LPC scheme can obtain a better performance both in terms of policy optimality and computational efficiency.

For continuously changing road conditions and vehicle operating states, the exactitude of vehicle path tracking has not been secured by model predictive control based on linear lateral stiffness. An amended square root cubature Kalman filter method based on the minimization of a new covariance of interest is proposed to calculate the tire lateral deflection force in real time. The ratio of the estimated tire force to the linear tire force was used as a ratio to adjust the lateral deflection stiffness, and an adaptive model predictive controller was built based on the vehicle path-tracking error model to correct the tire lateral deflection stiffness. Finally, an analysis based on the joint CarSim and Simulink simulation platform shows that compared to a conventional model predictive control (MPC) controller, a trajectory-following controller built based on this method can effectively reduce the lateral distance error and heading error of an autonomous vehicle. Especially under low adhesion conditions, the conventional MPC controllers will demonstrate large instability during trajectory tracking due to the deviation of the linear tire force calculation results, whereas the adaptive model predictive control (AMPC) controllers can correct the side deflection stiffness by estimating the tire force and still achieve stable and effective tracking of the target trajectory. This suggests that the proposed algorithm can improve the effectiveness of trajectory tracking control for autonomous vehicles, which is an important reference value for the optimization of autonomous vehicle control systems.

Intelligent vehicle trajectory tracking exhibits problems such as low adaptability, low tracking accuracy, and poor robustness in complex driving environments with uncertain road conditions. Therefore, an improved method of adaptive model predictive control (AMPC) for trajectory tracking was designed in this study to increase the corresponding tracking accuracy and driving stability of intelligent vehicles under uncertain and complex working conditions. First, based on the unscented Kalman filter, longitudinal speed, yaw speed, and lateral acceleration were considered as the observed variables of the measurement equation to estimate the lateral force of the front and rear tires accurately in real time. Subsequently, an adaptive correction estimation strategy for tire cornering stiffness was designed, an AMPC method was established, and a dynamic prediction time-domain adaptive model was constructed for optimization according to vehicle speed and road adhesion conditions. The improved AMPC method for trajectory tracking was then realized. Finally, the control effectiveness and trajectory tracking accuracy of the proposed AMPC technique were verified via co-simulation using CarSim and MATLAB/Simulink. From the results, a low lateral position error and heading angle error in trajectory tracking were obtained under different vehicle driving conditions and road adhesion conditions, producing high trajectory-tracking control accuracy. Thus, this work provides an important reference for improving the adaptability, robustness, and optimization of intelligent vehicle tracking control systems.