Learning-based model predictive control: Toward safe learning in control

L Hewing, KP Wabersich, M Menner… - Annual Review of …, 2020 - annualreviews.org
Recent successes in the field of machine learning, as well as the availability of increased
sensing and computational capabilities in modern control systems, have led to a growing …

Industrial data science–a review of machine learning applications for chemical and process industries

M Mowbray, M Vallerio, C Perez-Galvan… - Reaction Chemistry & …, 2022 - pubs.rsc.org
In the literature, machine learning (ML) and artificial intelligence (AI) applications tend to
start with examples that are irrelevant to process engineers (eg classification of images …

Deep reinforcement learning in a handful of trials using probabilistic dynamics models

K Chua, R Calandra, R McAllister… - Advances in neural …, 2018 - proceedings.neurips.cc
Abstract Model-based reinforcement learning (RL) algorithms can attain excellent sample
efficiency, but often lag behind the best model-free algorithms in terms of asymptotic …

Dynamics-aware unsupervised discovery of skills

A Sharma, S Gu, S Levine, V Kumar… - arxiv preprint arxiv …, 2019 - arxiv.org
Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model
for the dynamics of the environment. A good model can potentially enable planning …

Learning-based model predictive control for safe exploration

T Koller, F Berkenkamp, M Turchetta… - 2018 IEEE conference …, 2018 - ieeexplore.ieee.org
Learning-based methods have been successful in solving complex control tasks without
significant prior knowledge about the system. However, these methods typically do not …

Cautious model predictive control using gaussian process regression

L Hewing, J Kabzan… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
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 …

[PDF][PDF] DeepMPC: Learning deep latent features for model predictive control.

I Lenz, RA Knepper, A Saxena - Robotics: Science and …, 2015 - roboticsproceedings.org
Designing controllers for tasks with complex nonlinear dynamics is extremely challenging,
time-consuming, and in many cases, infeasible. This difficulty is exacerbated in tasks such …

Mechanistic artificial intelligence (mechanistic-AI) for modeling, design, and control of advanced manufacturing processes: Current state and perspectives

M Mozaffar, S Liao, X **e, S Saha, C Park, J Cao… - Journal of Materials …, 2022 - Elsevier
Today's manufacturing processes are pushed to their limits to generate products with ever-
increasing quality at low costs. A prominent hurdle on this path arises from the multiscale …

MLCAD: A survey of research in machine learning for CAD keynote paper

M Rapp, H Amrouch, Y Lin, B Yu… - … on Computer-Aided …, 2021 - ieeexplore.ieee.org
Due to the increasing size of integrated circuits (ICs), their design and optimization phases
(ie, computer-aided design, CAD) grow increasingly complex. At design time, a large design …

Model learning for robot control: a survey

D Nguyen-Tuong, J Peters - Cognitive processing, 2011 - Springer
Abstract Models are among the most essential tools in robotics, such as kinematics and
dynamics models of the robot's own body and controllable external objects. It is widely …