Header logo is


2020


Bayesian Optimization in Robot Learning - Automatic Controller Tuning and Sample-Efficient Methods
Bayesian Optimization in Robot Learning - Automatic Controller Tuning and Sample-Efficient Methods

Marco-Valle, A.

University of Tübingen, June 2020 (thesis)

Abstract
The problem of designing controllers to regulate dynamical systems has been studied by engineers during the past millennia. Ever since, suboptimal performance lingers in many closed loops as an unavoidable side effect of manually tuning the parameters of the controllers. Nowadays, industrial settings remain skeptic about data-driven methods that allow one to automatically learn controller parameters. In the context of robotics, machine learning (ML) keeps growing its influence on increasing autonomy and adaptability, for example to aid automating controller tuning. However, data-hungry ML methods, such as standard reinforcement learning, require a large number of experimental samples, prohibitive in robotics, as hardware can deteriorate and break. This brings about the following question: Can manual controller tuning, in robotics, be automated by using data-efficient machine learning techniques? In this thesis, we tackle the question above by exploring Bayesian optimization (BO), a data-efficient ML framework, to buffer the human effort and side effects of manual controller tuning, while retaining a low number of experimental samples. We focus this work in the context of robotic systems, providing thorough theoretical results that aim to increase data-efficiency, as well as demonstrations in real robots. Specifically, we present four main contributions. We first consider using BO to replace manual tuning in robotic platforms. To this end, we parametrize the design weights of a linear quadratic regulator (LQR) and learn its parameters using an information-efficient BO algorithm. Such algorithm uses Gaussian processes (GPs) to model the unknown performance objective. The GP model is used by BO to suggest controller parameters that are expected to increment the information about the optimal parameters, measured as a gain in entropy. The resulting “automatic LQR tuning” framework is demonstrated on two robotic platforms: A robot arm balancing an inverted pole and a humanoid robot performing a squatting task. In both cases, an existing controller is automatically improved in a handful of experiments without human intervention. BO compensates for data scarcity by means of the GP, which is a probabilistic model that encodes prior assumptions about the unknown performance objective. Usually, incorrect or non-informed assumptions have negative consequences, such as higher number of robot experiments, poor tuning performance or reduced sample-efficiency. The second to fourth contributions presented herein attempt to alleviate this issue. The second contribution proposes to include the robot simulator into the learning loop as an additional information source for automatic controller tuning. While doing a real robot experiment generally entails high associated costs (e.g., require preparation and take time), simulations are cheaper to obtain (e.g., they can be computed faster). However, because the simulator is an imperfect model of the robot, its information is biased and could have negative repercussions in the learning performance. To address this problem, we propose “simu-vs-real”, a principled multi-fidelity BO algorithm that trades off cheap, but inaccurate information from simulations with expensive and accurate physical experiments in a cost-effective manner. The resulting algorithm is demonstrated on a cart-pole system, where simulations and real experiments are alternated, thus sparing many real evaluations. The third contribution explores how to adequate the expressiveness of the probabilistic prior to the control problem at hand. To this end, the mathematical structure of LQR controllers is leveraged and embedded into the GP, by means of the kernel function. Specifically, we propose two different “LQR kernel” designs that retain the flexibility of Bayesian nonparametric learning. Simulated results indicate that the LQR kernel yields superior performance than non-informed kernel choices when used for controller learning with BO. Finally, the fourth contribution specifically addresses the problem of handling controller failures, which are typically unavoidable in practice while learning from data, specially if non-conservative solutions are expected. Although controller failures are generally problematic (e.g., the robot has to be emergency-stopped), they are also a rich information source about what should be avoided. We propose “failures-aware excursion search”, a novel algorithm for Bayesian optimization under black-box constraints, where failures are limited in number. Our results in numerical benchmarks indicate that by allowing a confined number of failures, better optima are revealed as compared with state-of-the-art methods. The first contribution of this thesis, “automatic LQR tuning”, lies among the first on applying BO to real robots. While it demonstrated automatic controller learning from few experimental samples, it also revealed several important challenges, such as the need of higher sample-efficiency, which opened relevant research directions that we addressed through several methodological contributions. Summarizing, we proposed “simu-vs-real”, a novel BO algorithm that includes the simulator as an additional information source, an “LQR kernel” design that learns faster than standard choices and “failures-aware excursion search”, a new BO algorithm for constrained black-box optimization problems, where the number of failures is limited.

ics

Repository (Universitätsbibliothek) - University of Tübingen PDF DOI [BibTex]


no image
Advances in Latent Variable and Causal Models

Rubenstein, P.

University of Cambridge, UK, 2020, (Cambridge-Tuebingen-Fellowship) (phdthesis)

ei

[BibTex]

[BibTex]

2009


no image
Kernel Learning Approaches for Image Classification

Gehler, PV.

Biologische Kybernetik, Universität des Saarlandes, Saarbrücken, Germany, October 2009 (phdthesis)

Abstract
This thesis extends the use of kernel learning techniques to specific problems of image classification. Kernel learning is a paradigm in the field of machine learning that generalizes the use of inner products to compute similarities between arbitrary objects. In image classification one aims to separate images based on their visual content. We address two important problems that arise in this context: learning with weak label information and combination of heterogeneous data sources. The contributions we report on are not unique to image classification, and apply to a more general class of problems. We study the problem of learning with label ambiguity in the multiple instance learning framework. We discuss several different image classification scenarios that arise in this context and argue that the standard multiple instance learning requires a more detailed disambiguation. Finally we review kernel learning approaches proposed for this problem and derive a more efficient algorithm to solve them. The multiple kernel learning framework is an approach to automatically select kernel parameters. We extend it to its infinite limit and present an algorithm to solve the resulting problem. This result is then applied in two directions. We show how to learn kernels that adapt to the special structure of images. Finally we compare different ways of combining image features for object classification and present significant improvements compared to previous methods.

ei

PDF [BibTex]

2009


PDF [BibTex]


no image
Kernel Methods in Computer Vision:Object Localization, Clustering,and Taxonomy Discovery

Blaschko, MB.

Biologische Kybernetik, Technische Universität Berlin, Berlin, Germany, March 2009 (phdthesis)

ei

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Motor Control and Learning in Table Tennis

Mülling, K.

Eberhard Karls Universität Tübingen, Gerrmany, 2009 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
Hierarchical Clustering and Density Estimation Based on k-nearest-neighbor graphs

Drewe, P.

Eberhard Karls Universität Tübingen, Germany, 2009 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
Learning with Structured Data: Applications to Computer Vision

Nowozin, S.

Technische Universität Berlin, Germany, 2009 (phdthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
From Differential Equations to Differential Geometry: Aspects of Regularisation in Machine Learning

Steinke, F.

Universität des Saarlandes, Saarbrücken, Germany, 2009 (phdthesis)

ei

PDF [BibTex]

2007


no image
Some Theoretical Aspects of Human Categorization Behavior: Similarity and Generalization

Jäkel, F.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, November 2007, passed with "ausgezeichnet", summa cum laude, published online (phdthesis)

ei

PDF [BibTex]

2007


PDF [BibTex]


no image
Statistical Learning Theory Approaches to Clustering

Jegelka, S.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, November 2007 (diplomathesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Error Correcting Codes for the P300 Visual Speller

Biessmann, F.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, July 2007 (diplomathesis)

Abstract
The aim of brain-computer interface (BCI) research is to establish a communication system based on intentional modulation of brain activity. This is accomplished by classifying patterns of brain ac- tivity, volitionally induced by the user. The BCI presented in this study is based on a classical paradigm as proposed by (Farwell and Donchin, 1988), the P300 visual speller. Recording electroencephalo- grams (EEG) from the scalp while presenting letters successively to the user, the speller can infer from the brain signal which letter the user was focussing on. Since EEG recordings are noisy, usually many repetitions are needed to detect the correct letter. The focus of this study was to improve the accuracy of the visual speller applying some basic principles from information theory: Stimulus sequences of the speller have been modified into error-correcting codes. Additionally a language model was incorporated into the probabilistic letter de- coder. Classification of single EEG epochs was less accurate using error correcting codes. However, the novel code could compensate for that such that overall, letter accuracies were as high as or even higher than for classical stimulus codes. In particular at high noise levels, error-correcting decoding achieved higher letter accuracies.

ei

PDF [BibTex]

PDF [BibTex]


no image
Nonparametric Bayesian Discrete Latent Variable Models for Unsupervised Learning

Görür, D.

Biologische Kybernetik, Technische Universität Berlin, Berlin, Germany, April 2007, published online (phdthesis)

ei

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Applications of Kernel Machines to Structured Data

Eichhorn, J.

Biologische Kybernetik, Technische Universität Berlin, Berlin, Germany, March 2007, passed with "sehr gut", published online (phdthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
A priori Knowledge from Non-Examples

Sinz, FH.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, March 2007 (diplomathesis)

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Machine Learning for Mass Production and Industrial Engineering

Pfingsten, T.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, February 2007 (phdthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Development of a Brain-Computer Interface Approach Based on Covert Attention to Tactile Stimuli

Raths, C.

University of Tübingen, Germany, University of Tübingen, Germany, January 2007 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
A Machine Learning Approach for Estimating the Attenuation Map for a Combined PET/MR Scanner

Hofmann, M.

Biologische Kybernetik, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany, 2007 (diplomathesis)

ei

[BibTex]

[BibTex]