Learning Agent-based Model Predictive Control for Holistic Vehicle Performance

Jiaming Zhong, Reza Valiollahi Mehrizi, Mohammad Pirani, Chao Yu, Alireza Kasaiezadeh, Yash Vardhan Pant, Amir Khajepour · N/A · 2026

Summary

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance.

Abstract Summary

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance. However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, which is too idealistic for actual implementation. This research proposes a novel practical hybrid control scheme - learning agent-based MPC (LAMPC), combining the model-based AMPC approach and data-based learning methods to improve the holistic vehicle performance for multi-agent systems. The Gaussian process regression (GPR) enhanced by an online data management strategy serves as the learning core to predict unknown contributions. A novel multi-step prediction mechanism leverages the GPR learning potential along the horizon. The predicted mean, representing the learned unknown contributions, completes the system model in the MPC for more accurate control. Meanwhile, a stochastic framework is formulated to guarantee control safety and feasibility using soft chance constraints based on the prediction variance. Both simulations and experiments show that, with the learning capability, LAMPC outperforms the traditional AMPC. LAMPC can achieve higher tracking performance in well-learned scenarios and always guarantee constraint satisfaction even in less-learned scenarios. Moreover, the proposed hybrid control scheme is efficient for real-time implementation and is flexible to any control agent topology.

Key Points

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance.
However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, which is too idealistic for actual implementation.
This research proposes a novel practical hybrid control scheme - learning agent-based MPC (LAMPC), combining the model-based AMPC approach and data-based learning methods to improve the holistic vehicle performance for multi-agent systems.
The Gaussian process regression (GPR) enhanced by an online data management strategy serves as the learning core to predict unknown contributions.
A novel multi-step prediction mechanism leverages the GPR learning potential along the horizon

Preliminaries

The concept of AMPC proposed in [ tang2021agent ] adopts a two-stage approach: the first stage models vehicle behavior under net forces and moments $U_{CG}$ at the vehicle center of gravity (CG), and the second stage captures the actuator dynamics from control inputs $U_{i}$ to $U_{CG}$.

Controller Design

The overall structure of the proposed LAMPC scheme is shown in Fig. 1 . The learning process consists of data preparation, data management, and GPR learning. The predicted mean and variance from GPR will finally be used to reconstruct the model-based stochastic AMPC. Data preparation first pairs the outputs and inputs at the previous step as a new data point for the dataset.

Unknown contributions to vehicle dynamics will be estimated as the outputs. Inputs are measurements or vehicle states determined by model selection methods.

Controller Design — Learning Agent-based Model Predictive Control for Holistic Vehicle Performance — Fig. 4: Simulation results of a DLC in the less-learned scenario.

Example: Vehicle Stability Control

System matrices in ( 1 ) for vehicle stability control are, where, $u$ and $v$ denote the longitudinal and lateral speed, respectively. $r$ denotes the yaw rate. $F_{yCG}$ and $M_{zCG}$ denote the net forces and moments at the vehicle CG, respectively. $m$ and $I_{z}$ denote the curb weight and yaw inertia, respectively. Four agents are considered in this example as in Table I .

The Rear differential torque (RDT) is the controllable agent with the designed controller.

Example: Vehicle Stability Control — Learning Agent-based Model Predictive Control for Holistic Vehicle Performance — Fig. 5: Optimization results in the less-learned DLC at T=5.75 and T=10.80.

Real-time Implementation and Results

Based on the above example, simulation and experimental studies were conducted to demonstrate the features of the proposed LAMPC control scheme. The controller is developed in Matlab/Simulink with parameters shown in Table II . A high-fidelity calibrated Carsim model of this vehicle from a previous experimental study [ hashemi2020vehicle ] is adopted for simulations, with the controller running at a frequency of 20Hz.

Sources and Demonstrations

Figures are reproduced from Zhong et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.