Cautious Model Predictive Control using Gaussian Process Regression

Abstract

Gaussian process (GP) regression has been widely used in supervised machine learning due to its flexibility and inherent ability to describe uncertainty in function estimation. In the context of control, it is seeing increasing use for modeling of nonlinear dynamical systems from data, as it allows the direct assessment of residual model uncertainty. We present a model predictive control (MPC) approach that integrates a nominal system with an additive nonlinear part of the dynamics modeled as a GP. Approximation techniques for propagating the state distribution are reviewed and we describe a principled way of formulating the chance constrained MPC problem, which takes into account residual uncertainties provided by the GP model to enable cautious control. Using additional approximations for efficient computation, we finally demonstrate the approach in a simulation example, as well as in a hardware implementation for autonomous racing of remote controlled race cars, highlighting improvements with regard to both performance and safety over a nominal controller.

Published in IEEE Transactions on Control Systems Technology

References in corpus (3)

• Optimization-Based Autonomous Racing of 1:43 Scale RC Cars
• Cautious NMPC with Gaussian Process Dynamics for Autonomous Miniature Race Cars
• Stochastic Model Predictive Control for Linear Systems using Probabilistic Reachable Sets

Cited by in corpus (52)

• Data-Driven Model Predictive Control with Stability and Robustness Guarantees
• Linear tracking MPC for nonlinear systems Part II: The data-driven case
• Stochastic data-driven model predictive control using Gaussian processes
• Real-Time Decision-Making for Digital Twin in Additive Manufacturing with Model Predictive Control using Time-Series Deep Neural Networks
• On Recurrent Neural Networks for learning-based control: recent results and ideas for future developments
• A robust adaptive model predictive control framework for nonlinear uncertain systems
• Machine learning for industrial sensing and control: A survey and practical perspective
• Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control
• SE(3) Koopman-MPC: Data-driven Learning and Control of Quadrotor UAVs
• Safe Control Synthesis with Uncertain Dynamics and Constraints
• Improving safety in mixed traffic: A learning-based model predictive control for autonomous and human-driven vehicle platooning
• Model Predictive Impedance Control with Gaussian Processes for Human and Environment Interaction
• Learning-Based Modeling of Human-Autonomous Vehicle Interaction for Improved Safety in Mixed-Vehicle Platooning Control
• Contextual Tuning of Model Predictive Control for Autonomous Racing
• Improved uncertainty quantification for neural networks with Bayesian last layer
• A computationally efficient robust model predictive control framework for uncertain nonlinear systems -- extended version
• Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version
• Safe Learning-Based Feedback Linearization Tracking Control for Nonlinear System with Event-Triggered Model Update
• Model Predictive Robustness of Signal Temporal Logic Predicates
• Robust offset-free constrained Model Predictive Control with Long Short-Term Memory Networks -- Extended version
• Residual Dynamics Learning for Trajectory Tracking for Multi-rotor Aerial Vehicles
• Probabilistic design of optimal sequential decision-making algorithms in learning and control
• Uncertainty-Aware Digital Twins: Robust Model Predictive Control using Time-Series Deep Quantile Learning
• Stochastic Time-Optimal Trajectory Planning for Connected and Automated Vehicles in Mixed-Traffic Merging Scenarios
• GaPT: Gaussian Process Toolkit for Online Regression with Application to Learning Quadrotor Dynamics
• Enhancing Safety in Mixed Traffic: Learning-Based Modeling and Efficient Control of Autonomous and Human-Driven Vehicles
• Learning safety in model-based Reinforcement Learning using MPC and Gaussian Processes
• Differential Dynamic Programming with Nonlinear Safety Constraints Under System Uncertainties
• Differentially Flat Learning-based Model Predictive Control Using a Stability, State, and Input Constraining Safety Filter
• Predictive control for nonlinear stochastic systems: Closed-loop guarantees with unbounded noise
• A dual-control effect preserving formulation for nonlinear output-feedback stochastic model predictive control with constraints
• Robust offset-free nonlinear model predictive control for systems learned by neural nonlinear autoregressive exogenous models
• Safe Guaranteed Exploration for Non-linear Systems
• Structured learning of safety guarantees for the control of uncertain dynamical systems
• Experimentally implemented dynamic optogenetic optimization of ATPase expression using knowledge-based and Gaussian-process-supported models
• Distributed Bayesian Online Learning for Cooperative Manipulation
• Learning Agent-based Model Predictive Control for Holistic Vehicle Performance
• A software framework for stochastic model predictive control of nonlinear continuous-time systems (GRAMPC-S)
• Experiment Design with Gaussian Process Regression with Applications to Chance-Constrained Control
• Unmatched uncertainty mitigation through neural network supported model predictive control
• Learning-Based Design of Off-Policy Gaussian Controllers: Integrating Model Predictive Control and Gaussian Process Regression
• Robust Meta-Learning of Vehicle Yaw Rate Dynamics via Conditional Neural Processes
• Online Learning and Control for Data-Augmented Quadrotor Model
• Learning-Based Shrinking Disturbance-Invariant Tubes for State- and Input-Dependent Uncertainty
• BOW: Bayesian Optimization over Windows for Motion Planning in Complex Environments
• Online Learning of Interaction Dynamics with Dual Model Predictive Control for Multi-Agent Systems Using Gaussian Processes
• Model Predictive Control of Nonlinear Latent Force Models: A Scenario-Based Approach
• A robust and adaptive MPC formulation for Gaussian process models
• A Data-Driven Distributed Control Scheme: Learning Multi-Objective Agent-Based MPC for Path-Tracking
• Improving gearshift controllers for electric vehicles with reinforcement learning
• A Contingency Model Predictive Control Framework for Safe Learning
• Learning-based synthesis of robust linear time-invariant controllers