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.



There are no comments yet.


page 1

page 2


Approximate Robust NMPC using Reinforcement Learning

We present a Reinforcement Learning-based Robust Nonlinear Model Predict...

Particle MPC for Uncertain and Learning-Based Control

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

Linear model predictive safety certification for learning-based control

While it has been repeatedly shown that learning-based controllers can p...

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...

Variational Inference MPC for Bayesian Model-based Reinforcement Learning

In recent studies on model-based reinforcement learning (MBRL), incorpor...

Reactive Navigation under Non-Parametric Uncertainty through Hilbert Space Embedding of Probabilistic Velocity Obstacles

The probabilistic velocity obstacle (PVO) extends the concept of velocit...

Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control

Trial-and-error based reinforcement learning (RL) has seen rapid advance...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.