Machine Learning and System Identification for Estimation in Physical Systems

Abstract

In this thesis, we draw inspiration from both classical system identification and modern machine learning in order to solve estimation problems for real-world, physical systems. The main approach to estimation and learning adopted is optimization based. Concepts such as regularization will be utilized for encoding of prior knowledge and basis-function expansions will be used to add nonlinear modeling power while keeping data requirements practical. The thesis covers a wide range of applications, many inspired by applications within robotics, but also extending outside this already wide field. Usage of the proposed methods and algorithms are in many cases illustrated in the real-world applications that motivated the research. Topics covered include dynamics modeling and estimation, model-based reinforcement learning, spectral estimation, friction modeling and state estimation and calibration in robotic machining. In the work on modeling and identification of dynamics, we develop regularization strategies that allow us to incorporate prior domain knowledge into flexible, overparameterized models. We make use of classical control theory to gain insight into training and regularization while using flexible tools from modern deep learning. A particular focus of the work is to allow use of modern methods in scenarios where gathering data is associated with a high cost. In the robotics-inspired parts of the thesis, we develop methods that are practically motivated and ensure that they are implementable also outside the research setting. We demonstrate this by performing experiments in realistic settings and providing open-source implementations of all proposed methods and algorithms.

184 pages, PhD thesis, Lund University, 2018

References in corpus (8)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• On the difficulty of training Recurrent Neural Networks
• Trust Region Policy Optimization
• Hand-Eye Calibration
• On the loss landscape of a class of deep neural networks with no bad local valleys
• Automatic differentiation in ML: Where we are and where we should be going
• Practical Gauss-Newton Optimisation for Deep Learning
• Tangent-Space Regularization for Neural-Network Models of Dynamical Systems