Deep Learning Tubes for Tube MPC

by   David D. Fan, et al.

Learning-based control aims to construct models of a system to use for planning or trajectory optimization, e.g. in model-based reinforcement learning. In order to obtain guarantees of safety in this context, uncertainty must be accurately quantified. This uncertainty may come from errors in learning (due to a lack of data, for example), or may be inherent to the system. Propagating uncertainty in learned dynamics models is a difficult problem. Common approaches rely on restrictive assumptions of how distributions are parameterized or propagated in time. In contrast, in this work we propose using deep learning to obtain expressive and flexible models of how these distributions behave, which we then use for nonlinear Model Predictive Control (MPC). First, we introduce a deep quantile regression framework for control which enforces probabilistic quantile bounds and quantifies epistemic uncertainty. Next, using our method we explore three different approaches for learning tubes which contain the possible trajectories of the system, and demonstrate how to use each of them in a Tube MPC scheme. Furthermore, we prove these schemes are recursively feasible and satisfy constraints with a desired margin of probability. Finally, we present experiments in simulation on a nonlinear quadrotor system, demonstrating the practical efficacy of these ideas.


page 1

page 2


Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

We introduce a simple but effective method for managing risk in model-ba...

Probably Approximately Correct Nonlinear Model Predictive Control (PAC-NMPC)

Approaches for stochastic nonlinear model predictive control (SNMPC) typ...

Learning-enhanced Nonlinear Model Predictive Control using Knowledge-based Neural Ordinary Differential Equations and Deep Ensembles

Nonlinear model predictive control (MPC) is a flexible and increasingly ...

PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

In the present paper, we propose an extension of the Deep Planning Netwo...

Particle MPC for Uncertain and Learning-Based Control

As robotic systems move from highly structured environments to open worl...

GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts

Model predictive control (MPC) is a popular approach for trajectory opti...

Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control

Trial-and-error based reinforcement learning (RL) has seen rapid advance...

Please sign up or login with your details

Forgot password? Click here to reset