DMPC: a data-and model-driven approach to predictive control
From MaRDI portal
Publication:2665368
Abstract: This work presents DMPC (Data-and Model-Driven Predictive Control) to solve control problems in which some of the constraints or parts of the objective function are known, while others are entirely unknown to the controller. It is assumed that there is an exogenous ``black box system, e.g. a machine learning technique, that predicts the value of the unknown functions for a given trajectory. DMPC (1) provides an approach to merge both the model-based and black-box systems; (2) can cope with very little data and is sample efficient, building its solutions based on recently generated trajectories; and (3) improves its cost in each iteration until converging to an optimal trajectory, typically needing only a few trials even for nonlinear dynamics and objectives. Theoretical analysis of the algorithm is presented, proving that the quality of the trajectory does not worsen with each new iteration, as well as providing bounds on the complexity. We apply the DMPC algorithm to the motion planning of an autonomous vehicle with nonlinear dynamics.
Recommendations
- Online data-enabled predictive control
- Input-mapping based data-driven model predictive control for unknown linear systems with bounded disturbances
- Robust learning-based MPC for nonlinear constrained systems
- Dual adaptive model predictive control
- Data-driven model predictive control design for offset-free tracking of nonlinear systems
Cites work
- An auto-generated real-time iteration algorithm for nonlinear MPC in the microsecond range
- An exact geometry-based algorithm for path planning
- Control Barrier Function Based Quadratic Programs for Safety Critical Systems
- Finite time LTI system identification
- Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control Framework
- Probabilistic guarantees for safe deep reinforcement learning
Cited in
(7)- Learning-based model predictive current control for synchronous machines: an LSTM approach
- Online data-enabled predictive control
- On the universal transformation of data-driven models to control systems
- 基于驱动因素控制的DFCGM(1,N) 及其拓展模型构建与应用
- Data‐enabled predictive control for quadcopters
- Input-mapping based data-driven model predictive control for unknown linear systems with bounded disturbances
- Time-coordinated motion planning for multiple unmanned vehicles using distributed model predictive control and sequential convex programming
This page was built for publication: DMPC: a data-and model-driven approach to predictive control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2665368)
