Optimization of the Model Predictive Control Update Interval Using Reinforcement Learning

by   Eivind Bøhn, et al.

In control applications there is often a compromise that needs to be made with regards to the complexity and performance of the controller and the computational resources that are available. For instance, the typical hardware platform in embedded control applications is a microcontroller with limited memory and processing power, and for battery powered applications the control system can account for a significant portion of the energy consumption. We propose a controller architecture in which the computational cost is explicitly optimized along with the control objective. This is achieved by a three-part architecture where a high-level, computationally expensive controller generates plans, which a computationally simpler controller executes by compensating for prediction errors, while a recomputation policy decides when the plan should be recomputed. In this paper, we employ model predictive control (MPC) as the high-level plan-generating controller, a linear state feedback controller as the simpler compensating controller, and reinforcement learning (RL) to learn the recomputation policy. Simulation results for two examples showcase the architecture's ability to improve upon the MPC approach and find reasonable compromises weighing the performance on the control objective and the computational resources expended.


page 1

page 2

page 3

page 4


Optimization of the Model Predictive Control Meta-Parameters Through Reinforcement Learning

Model predictive control (MPC) is increasingly being considered for cont...

A Passive Navigation Planning Algorithm for Collision-free Control of Mobile Robots

Path planning and collision avoidance are challenging in complex and hig...

On the improvement of model-predictive controllers

This article investigates synthetic model-predictive control (MPC) probl...

Combining model-predictive control and predictive reinforcement learning for stable quadrupedal robot locomotion

Stable gait generation is a crucial problem for legged robot locomotion ...

Learning-based MPC from Big Data Using Reinforcement Learning

This paper presents an approach for learning Model Predictive Control (M...

Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control

Optimizing prices for energy demand response requires a flexible control...

Shield Model Predictive Path Integral: A Computationally Efficient Robust MPC Approach Using Control Barrier Functions

Model Predictive Path Integral (MPPI) control is a type of sampling-base...

Please sign up or login with your details

Forgot password? Click here to reset