Model-based deep learning: On the intersection of deep learning and optimization
Decision making algorithms are used in a multitude of different applications. Conventional
approaches for designing decision algorithms employ principled and simplified modelling …
approaches for designing decision algorithms employ principled and simplified modelling …
A tutorial on derivative-free policy learning methods for interpretable controller representations
JA Paulson, F Sorourifar… - 2023 American Control …, 2023 - ieeexplore.ieee.org
This paper provides a tutorial overview of recent advances in learning control policy
representations for complex systems. We focus on control policies that are determined by …
representations for complex systems. We focus on control policies that are determined by …
Adaptive-control-oriented meta-learning for nonlinear systems
Real-time adaptation is imperative to the control of robots operating in complex, dynamic
environments. Adaptive control laws can endow even nonlinear systems with good trajectory …
environments. Adaptive control laws can endow even nonlinear systems with good trajectory …
Learning model predictive controllers with real-time attention for real-world navigation
Despite decades of research, existing navigation systems still face real-world challenges
when deployed in the wild, eg, in cluttered home environments or in human-occupied public …
when deployed in the wild, eg, in cluttered home environments or in human-occupied public …
The differentiable cross-entropy method
Abstract We study the Cross-Entropy Method (CEM) for the non-convex optimization of a
continuous and parameterized objective function and introduce a differentiable variant that …
continuous and parameterized objective function and introduce a differentiable variant that …
Coco: Online mixed-integer control via supervised learning
Many robotics problems, from robot motion planning to object manipulation, can be modeled
as mixed-integer convex program (MICPs). However, state-of-the-art algorithms are still …
as mixed-integer convex program (MICPs). However, state-of-the-art algorithms are still …
Control-oriented meta-learning
Real-time adaptation is imperative to the control of robots operating in complex, dynamic
environments. Adaptive control laws can endow even nonlinear systems with good trajectory …
environments. Adaptive control laws can endow even nonlinear systems with good trajectory …
Learning mixed-integer convex optimization strategies for robot planning and control
Mixed-integer convex programming (MICP) has seen significant algorithmic and hardware
improvements with several orders of magnitude solve time speedups compared to 25 years …
improvements with several orders of magnitude solve time speedups compared to 25 years …
Learning convex optimization models
A convex optimization model predicts an output from an input by solving a convex
optimization problem. The class of convex optimization models is large, and includes as …
optimization problem. The class of convex optimization models is large, and includes as …
Learning-based moving horizon estimation through differentiable convex optimization layers
S Muntwiler, KP Wabersich… - Learning for Dynamics …, 2022 - proceedings.mlr.press
To control a dynamical system it is essential to obtain an accurate estimate of the current
system state based on uncertain sensor measurements and existing system knowledge. An …
system state based on uncertain sensor measurements and existing system knowledge. An …