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
Deep learning for the parameter estimation of tight-binding Hamiltonians

Cacioppo, A.

University of Roma, La Sapienza, Italy, May 2020 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Learning Algorithms, Invariances, and the Real World

Zecevic, M.

Technical University of Darmstadt, Germany, April 2020 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Magnetische Röntgenmikroskopie zur Untersuchung des lokalen Stromtransports in Supraleitern

Simmendinger, J.

Universität Stuttgart, Stuttgart (und Verlag Dr. Hut, München), 2020 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Interaction of hydrogen isotopes with flexible metal-organic frameworks

Bondorf, L.

Universität Stuttgart, Stuttgart, 2020 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Advances in Latent Variable and Causal Models

Rubenstein, P.

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

ei

[BibTex]

[BibTex]


Electronics, Software and Analysis of a Bioinspired Sensorized Quadrupedal Robot
Electronics, Software and Analysis of a Bioinspired Sensorized Quadrupedal Robot

Petereit, R.

Technische Universität München, 2020 (mastersthesis)

dlg

[BibTex]


no image
Spin-Bahn-Effekte in der Vortexdynamik und kürzeste Spinwellen in Y3Fe5O12

Förster, J.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2020 (phdthesis)

mms

[BibTex]

[BibTex]

2018


no image
Instrumentation, Data, and Algorithms for Visually Understanding Haptic Surface Properties

Burka, A. L.

University of Pennsylvania, Philadelphia, USA, August 2018, Department of Electrical and Systems Engineering (phdthesis)

Abstract
Autonomous robots need to efficiently walk over varied surfaces and grasp diverse objects. We hypothesize that the association between how such surfaces look and how they physically feel during contact can be learned from a database of matched haptic and visual data recorded from various end-effectors' interactions with hundreds of real-world surfaces. Testing this hypothesis required the creation of a new multimodal sensing apparatus, the collection of a large multimodal dataset, and development of a machine-learning pipeline. This thesis begins by describing the design and construction of the Portable Robotic Optical/Tactile ObservatioN PACKage (PROTONPACK, or Proton for short), an untethered handheld sensing device that emulates the capabilities of the human senses of vision and touch. Its sensory modalities include RGBD vision, egomotion, contact force, and contact vibration. Three interchangeable end-effectors (a steel tooling ball, an OptoForce three-axis force sensor, and a SynTouch BioTac artificial fingertip) allow for different material properties at the contact point and provide additional tactile data. We then detail the calibration process for the motion and force sensing systems, as well as several proof-of-concept surface discrimination experiments that demonstrate the reliability of the device and the utility of the data it collects. This thesis then presents a large-scale dataset of multimodal surface interaction recordings, including 357 unique surfaces such as furniture, fabrics, outdoor fixtures, and items from several private and public material sample collections. Each surface was touched with one, two, or three end-effectors, comprising approximately one minute per end-effector of tapping and dragging at various forces and speeds. We hope that the larger community of robotics researchers will find broad applications for the published dataset. Lastly, we demonstrate an algorithm that learns to estimate haptic surface properties given visual input. Surfaces were rated on hardness, roughness, stickiness, and temperature by the human experimenter and by a pool of purely visual observers. Then we trained an algorithm to perform the same task as well as infer quantitative properties calculated from the haptic data. Overall, the task of predicting haptic properties from vision alone proved difficult for both humans and computers, but a hybrid algorithm using a deep neural network and a support vector machine achieved a correlation between expected and actual regression output between approximately ρ = 0.3 and ρ = 0.5 on previously unseen surfaces.

hi

Project Page [BibTex]

2018


Project Page [BibTex]


Robust Visual Augmented Reality in Robot-Assisted Surgery
Robust Visual Augmented Reality in Robot-Assisted Surgery

Forte, M.

Politecnico di Milano, Milan, Italy, July 2018, Department of Electronic, Information, and Biomedical Engineering (mastersthesis)

Abstract
The broader research objective of this line of research is to test the hypothesis that real-time stereo video analysis and augmented reality can increase safety and task efficiency in robot-assisted surgery. This master’s thesis aims to solve the first step needed to achieve this goal: the creation of a robust system that delivers the envisioned feedback to a surgeon while he or she controls a surgical robot that is identical to those used on human patients. Several approaches for applying augmented reality to da Vinci Surgical Systems have been proposed, but none of them entirely rely on a clinical robot; specifically, they require additional sensors, depend on access to the da Vinci API, are designed for a very specific task, or were tested on systems that are starkly different from those in clinical use. There has also been prior work that presents the real-world camera view and the computer graphics on separate screens, or not in real time. In other scenarios, the digital information is overlaid manually by the surgeons themselves or by computer scientists, rather than being generated automatically in response to the surgeon’s actions. We attempted to overcome the aforementioned constraints by acquiring input signals from the da Vinci stereo endoscope and providing augmented reality to the console in real time (less than 150 ms delay, including the 62 ms of inherent latency of the da Vinci). The potential benefits of the resulting system are broad because it was built to be general, rather than customized for any specific task. The entire platform is compatible with any generation of the da Vinci System and does not require a dVRK (da Vinci Research Kit) or access to the API. Thus, it can be applied to existing da Vinci Systems in operating rooms around the world.

hi

Project Page [BibTex]

Project Page [BibTex]


Colloidal Chemical Nanomotors
Colloidal Chemical Nanomotors

Alarcon-Correa, M.

Colloidal Chemical Nanomotors, pages: 150, Cuvillier Verlag, MPI-IS , June 2018 (phdthesis)

Abstract
Synthetic sophisticated nanostructures represent a fundamental building block for the development of nanotechnology. The fabrication of nanoparticles complex in structure and material composition is key to build nanomachines that can operate as man-made nanoscale motors, which autonomously convert external energy into motion. To achieve this, asymmetric nanoparticles were fabricated combining a physical vapor deposition technique known as NanoGLAD and wet chemical synthesis. This thesis primarily concerns three complex colloidal systems that have been developed: i)Hollow nanocup inclusion complexes that have a single Au nanoparticle in their pocket. The Au particle can be released with an external trigger. ii)The smallest self-propelling nanocolloids that have been made to date, which give rise to a local concentration gradient that causes enhanced diffusion of the particles. iii)Enzyme-powered pumps that have been assembled using bacteriophages as biological nanoscaffolds. This construct also can be used for enzyme recovery after heterogeneous catalysis.

pf

[BibTex]

[BibTex]


Model-based Optical Flow: Layers, Learning, and Geometry
Model-based Optical Flow: Layers, Learning, and Geometry

Wulff, J.

Tuebingen University, April 2018 (phdthesis)

Abstract
The estimation of motion in video sequences establishes temporal correspondences between pixels and surfaces and allows reasoning about a scene using multiple frames. Despite being a focus of research for over three decades, computing motion, or optical flow, remains challenging due to a number of difficulties, including the treatment of motion discontinuities and occluded regions, and the integration of information from more than two frames. One reason for these issues is that most optical flow algorithms only reason about the motion of pixels on the image plane, while not taking the image formation pipeline or the 3D structure of the world into account. One approach to address this uses layered models, which represent the occlusion structure of a scene and provide an approximation to the geometry. The goal of this dissertation is to show ways to inject additional knowledge about the scene into layered methods, making them more robust, faster, and more accurate. First, this thesis demonstrates the modeling power of layers using the example of motion blur in videos, which is caused by fast motion relative to the exposure time of the camera. Layers segment the scene into regions that move coherently while preserving their occlusion relationships. The motion of each layer therefore directly determines its motion blur. At the same time, the layered model captures complex blur overlap effects at motion discontinuities. Using layers, we can thus formulate a generative model for blurred video sequences, and use this model to simultaneously deblur a video and compute accurate optical flow for highly dynamic scenes containing motion blur. Next, we consider the representation of the motion within layers. Since, in a layered model, important motion discontinuities are captured by the segmentation into layers, the flow within each layer varies smoothly and can be approximated using a low dimensional subspace. We show how this subspace can be learned from training data using principal component analysis (PCA), and that flow estimation using this subspace is computationally efficient. The combination of the layered model and the low-dimensional subspace gives the best of both worlds, sharp motion discontinuities from the layers and computational efficiency from the subspace. Lastly, we show how layered methods can be dramatically improved using simple semantics. Instead of treating all layers equally, a semantic segmentation divides the scene into its static parts and moving objects. Static parts of the scene constitute a large majority of what is shown in typical video sequences; yet, in such regions optical flow is fully constrained by the depth structure of the scene and the camera motion. After segmenting out moving objects, we consider only static regions, and explicitly reason about the structure of the scene and the camera motion, yielding much better optical flow estimates. Furthermore, computing the structure of the scene allows to better combine information from multiple frames, resulting in high accuracies even in occluded regions. For moving regions, we compute the flow using a generic optical flow method, and combine it with the flow computed for the static regions to obtain a full optical flow field. By combining layered models of the scene with reasoning about the dynamic behavior of the real, three-dimensional world, the methods presented herein push the envelope of optical flow computation in terms of robustness, speed, and accuracy, giving state-of-the-art results on benchmarks and pointing to important future research directions for the estimation of motion in natural scenes.

ps

Official link DOI Project Page [BibTex]


no image
A virtual reality environment for experiments in assistive robotics and neural interfaces

Bustamante, S.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2018 (mastersthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Optimal Trajectory Generation and Learning Control for Robot Table Tennis

Koc, O.

Technical University Darmstadt, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Distribution-Dissimilarities in Machine Learning

Simon-Gabriel, C. J.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Pattern forming systems under confinement

Maihöfer, Michael

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Effective interactions between colloidal particles in critical solvents

Labbe-Laurent, M.

Universität Stuttgart, Stuttgart, 2018 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Domain Adaptation Under Causal Assumptions

Lechner, T.

Eberhard Karls Universität Tübingen, Germany, 2018 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
A Causal Perspective on Deep Representation Learning

Suter, R.

ETH Zurich, 2018 (mastersthesis)

ei

[BibTex]


no image
Non-equilibrium dynamics of a binary solvent around heated colloidal particles

Wilke, Moritz

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Probabilistic Approaches to Stochastic Optimization

Mahsereci, M.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei pn

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Reinforcement Learning for High-Speed Robotics with Muscular Actuation

Guist, S.

Ruprecht-Karls-Universität Heidelberg , 2018 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Monte Carlo study of colloidal structure formation at fluid interfaces

Meiler, Tim

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Electrolyte solutions and simple fluids at curved walls

Reindl, A.

Universität Stuttgart, Stuttgart, 2018 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Probabilistic Ordinary Differential Equation Solvers — Theory and Applications

Schober, M.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei pn

[BibTex]

[BibTex]


no image
A machine learning approach to taking EEG-based computer interfaces out of the lab

Jayaram, V.

Graduate Training Centre of Neuroscience, IMPRS, Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Surface structure of liquid crystals

Sattler, Alexander

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Dynamics of an active particle in confined viscous flows

Pöhnl, Ruben

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
XMCD investigations on new hard magnetic systems

Chen, Y.

Universität Stuttgart, Stuttgart, 2018 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Electrostatic interaction between colloids with constant surface potentials at fluid interfaces

Bebon, Rick

Universität Stuttgart, Stuttgart, 2018 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
High-Resolution X-ray Ptychography for Magnetic Imaging

Bykova, I.

Universität Stuttgart, Stuttgart, 2018 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2014


no image
Pole Balancing with Apollo

Holger Kaden

Eberhard Karls Universität Tübingen, December 2014 (mastersthesis)

am

[BibTex]

2014


[BibTex]


no image
Modeling the polygenic architecture of complex traits

Rakitsch, Barbara

Eberhard Karls Universität Tübingen, November 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Learning Coupling Terms for Obstacle Avoidance

Rai, A.

École polytechnique fédérale de Lausanne, August 2014 (mastersthesis)

am

Project Page [BibTex]

Project Page [BibTex]


no image
Object Tracking in Depth Images Using Sigma Point Kalman Filters

Issac, J.

Karlsruhe Institute of Technology, July 2014 (mastersthesis)

am

Project Page [BibTex]

Project Page [BibTex]


Modeling the Human Body in 3D: Data Registration and Human Shape Representation
Modeling the Human Body in 3D: Data Registration and Human Shape Representation

Tsoli, A.

Brown University, Department of Computer Science, May 2014 (phdthesis)

ps

pdf [BibTex]

pdf [BibTex]


no image
A Novel Causal Inference Method for Time Series

Shajarisales, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (mastersthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
A global analysis of extreme events and consequences for the terrestrial carbon cycle

Zscheischler, J.

Diss. No. 22043, ETH Zurich, Switzerland, ETH Zurich, Switzerland, 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Learning objective functions for autonomous motion generation

Kalakrishnan, M.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Wetting phenomena in electrolyte solutions

Ibagon, I.

Universität Stuttgart, Stuttgart, 2014 (phdthesis)

icm

link (url) [BibTex]

link (url) [BibTex]


no image
Development of advanced methods for improving astronomical images

Schmeißer, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
The Feasibility of Causal Discovery in Complex Systems: An Examination of Climate Change Attribution and Detection

Lacosse, E.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Causal Discovery in the Presence of Time-Dependent Relations or Small Sample Size

Huang, B.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei

[BibTex]

[BibTex]


Deep apprenticeship learning for playing video games
Deep apprenticeship learning for playing video games

Bogdanovic, M.

University of Oxford, 2014 (mastersthesis)

[BibTex]