Learning Based MPC for Autonomous Driving Using a Low Dimensional Residual Model

In this paper, a learning based Model Predictive Control (MPC) using a low dimensional residual model is proposed for autonomous driving. One of the critical challenge in autonomous driving is the complexity of vehicle dynamics, which impedes the formulation of accurate vehicle model. Inaccurate vehicle model can significantly impact the performance of MPC controller. To address this issue, this paper decomposes the nominal vehicle model into invariable and variable elements. The accuracy of invariable elements are ensured by calibration, while the deviations in the variable elements are learned by a low-dimensional residual model. The features of residual model are selected as the physical variables most correlated with nominal model errors. Physical constraints among these features are formulated to explicitly define the valid region within the feature space. The formulated model and constraints are incorporated into the MPC framework and validated through both simulation and real vehicle experiments. The results indicate that the proposed method significantly enhances the model accuracy and controller performance.

Authors

• Yaoyu Li
• Chaosheng Huang
• Dongsheng Yang
• Wenbo Liu
• Jun Li

Keywords

• Accuracy
• Predictive models
• Aerospace electronics
• Complexity theory
• Calibration
• Vehicle dynamics
• Robotics and automation
• Autonomous vehicles
• Predictive control
• Dimensional Model
• Model Predictive Control
• Low-dimensional Model
• Prediction Model
• Feature Model
• Feature Space
• Error Model
• Simulation Experiments
• Control Performance
• Physical Constraints
• Physical Variables
• Nominal Model
• Model Predictive Control Framework
• Training Set
• Dimensional Space
• Control Input
• Feature Dimension
• High-dimensional Feature
• Tyre Forces
• Lateral Force
• Front Wheel
• Lateral Tyre Forces
• Nominal Control
• Sideslip Angle
• Longitudinal Force
• Tyre Wear
• Key Metrics
• Tyre Model
• Model learning
• autonomous driving