Header logo is

600 results (View BibTeX file of all listed publications)

2024

Leveraging Unpaired Data for the Creation of Controllable Digital Humans
Leveraging Unpaired Data for the Creation of Controllable Digital Humans

Sanyal, S.

Max Planck Institute for Intelligent Systems and Eberhard Karls Universität Tübingen, September 2024 (phdthesis) To be published

Abstract
Digital humans have grown increasingly popular, offering transformative potential across various fields such as education, entertainment, and healthcare. They enrich user experiences by providing immersive and personalized interactions. Enhancing these experiences involves making digital humans controllable, allowing for manipulation of aspects like pose and appearance, among others. Learning to create such controllable digital humans necessitates extensive data from diverse sources. This includes 2D human images alongside their corresponding 3D geometry and texture, 2D images showcasing similar appearances across a wide range of body poses, etc., for effective control over pose and appearance. However, the availability of such “paired data” is limited, making its collection both time-consuming and expensive. Despite these challenges, there is an abundance of unpaired 2D images with accessible, inexpensive labels—such as identity, type of clothing, appearance of clothing, etc. This thesis capitalizes on these affordable labels, employing informed observations from “unpaired data” to facilitate the learning of controllable digital humans through reconstruction, transposition, and generation processes. The presented methods—RingNet, SPICE, and SCULPT—each tackles different aspects of controllable digital human modeling. RingNet (Sanyal et al. [2019]) exploits the consistent facial geometry across different images of the same individual to estimate 3D face shapes and poses without 2D-to-3D supervision. This method illustrates how leveraging the inherent properties of unpaired images—such as identity consistency—can circumvent the need for expensive paired datasets. Similarly, SPICE (Sanyal et al. [2021]) employs a self-supervised learning framework that harnesses unpaired images to generate realistic transpositions of human poses by understanding the underlying 3D body structure and maintaining consistency in body shape and appearance features across different poses. Finally, SCULPT (Sanyal et al. [2024] generates clothed and textured 3D meshes by integrating insights from unpaired 2D images and medium-sized 3D scans. This process employs an unpaired learning approach, conditioning texture and geometry generation on attributes easily derived from data, like the type and appearance of clothing. In conclusion, this thesis highlights how unpaired data and innovative learning techniques can address the challenges of data scarcity and high costs in developing controllable digital humans by advancing reconstruction, transposition, and generation techniques.

ps

[BibTex]

2024

ps Sanyal, S. Leveraging Unpaired Data for the Creation of Controllable Digital Humans Max Planck Institute for Intelligent Systems and Eberhard Karls Universität Tübingen, September 2024 (phdthesis) To be published

[BibTex]

Realistic Digital Human Characters: Challenges, Models and Algorithms
Realistic Digital Human Characters: Challenges, Models and Algorithms

Osman, A. A. A.

University of Tübingen, September 2024 (phdthesis)

Abstract
Statistical models for the body, head, and hands are essential in various computer vision tasks. However, popular models like SMPL, MANO, and FLAME produce unrealistic deformations due to inherent flaws in their modeling assumptions and how they are trained, which have become standard practices in constructing models for the body and its parts. This dissertation addresses these limitations by proposing new modeling and training algorithms to improve the realism and generalization of current models. We introduce a new model, STAR (Sparse Trained Articulated Human Body Regressor), which learns a sparse representation of the human body deformations, significantly reducing the number of model parameters compared to models like SMPL. This approach ensures that deformations are spatially localized, leading to more realistic deformations. STAR also incorporates shape-dependent pose deformations, accounting for variations in body shape to enhance overall model accuracy and realism. Additionally, we present a novel federated training algorithm for developing a comprehensive suite of models for the body and its parts. We train an expressive body model, SUPR (Sparse Unified Part-Based Representation), on a federated dataset of full-body scans, including detailed scans of the head, hands, and feet. We then separate SUPR into a full suite of state-of-the-art models for the head, hands, and foot. The new foot model captures complex foot deformations, addressing challenges related to foot shape, pose, and ground contact dynamics. The dissertation concludes by introducing AVATAR (Articulated Virtual Humans Trained By Bayesian Inference From a Single Scan), a novel, data-efficient training algorithm. AVATAR allows the creation of personalized, high-fidelity body models from a single scan by framing model construction as a Bayesian inference problem, thereby enabling training from small-scale datasets while reducing the risk of overfitting. These advancements push the state of the art in human body modeling and training techniques, making them more accessible for broader research and practical applications.

ps

[BibTex]

no image
Advances in Probabilistic Methods for Deep Learning

Immer, A.

ETH Zurich, Switzerland, September 2024, CLS PhD Program (phdthesis)

ei

[BibTex]

ei Immer, A. Advances in Probabilistic Methods for Deep Learning ETH Zurich, Switzerland, September 2024, CLS PhD Program (phdthesis)

[BibTex]

no image
Engineering and Evaluating Naturalistic Vibrotactile Feedback for Telerobotic Assembly

Gong, Y.

University of Stuttgart, Stuttgart, Germany, August 2024, Faculty of Design, Production Engineering and Automotive Engineering (phdthesis)

Abstract
Teleoperation allows workers on a construction site to assemble pre-fabricated building components by controlling powerful machines from a safe distance. However, teleoperation's primary reliance on visual feedback limits the operator's efficiency in situations with stiff contact or poor visibility, compromising their situational awareness and thus increasing the difficulty of the task; it also makes construction machines more difficult to learn to operate. To bridge this gap, we propose that reliable, economical, and easy-to-implement naturalistic vibrotactile feedback could improve telerobotic control interfaces in construction and other application areas such as surgery. This type of feedback enables the operator to feel the natural vibrations experienced by the robot, which contain crucial information about its motions and its physical interactions with the environment. This dissertation explores how to deliver naturalistic vibrotactile feedback from a robot's end-effector to the hand of an operator performing telerobotic assembly tasks; furthermore, it seeks to understand the effects of such haptic cues. The presented research can be divided into four parts. We first describe the engineering of AiroTouch, a naturalistic vibrotactile feedback system tailored for use on construction sites but suitable for many other applications of telerobotics. Then we evaluate AiroTouch and explore the effects of the naturalistic vibrotactile feedback it delivers in three user studies conducted either in laboratory settings or on a construction site. We begin this dissertation by developing guidelines for creating a haptic feedback system that provides high-quality naturalistic vibrotactile feedback. These guidelines include three sections: component selection, component placement, and system evaluation. We detail each aspect with the parameters that need to be considered. Based on these guidelines, we adapt widely available commercial audio equipment to create our system called AiroTouch, which measures the vibration experienced by each robot tool with a high-bandwidth three-axis accelerometer and enables the user to feel this vibration in real time through a voice-coil actuator. Accurate haptic transmission is achieved by optimizing the positions of the system's off-the-shelf sensors and actuators and is then verified through measurements. The second part of this thesis presents our initial validation of AiroTouch. We explored how adding this naturalistic type of vibrotactile feedback affects the operator during small-scale telerobotic assembly. Due to the limited accessibility of teleoperated robots and to maintain safety, we conducted a user study in lab with a commercial bimanual dexterous teleoperation system developed for surgery (Intuitive da Vinci Si). Thirty participants used this robot equipped with AiroTouch to assemble a small stiff structure under three randomly ordered haptic feedback conditions: no vibrations, one-axis vibrations, and summed three-axis vibrations. The results show that participants learn to take advantage of both tested versions of the haptic feedback in the given tasks, as significantly lower vibrations and forces are observed in the second trial. Subjective responses indicate that naturalistic vibrotactile feedback increases the realism of the interaction and reduces the perceived task duration, task difficulty, and fatigue. To test our approach on a real construction site, we enhanced AiroTouch using wireless signal-transmission technologies and waterproofing, and then we adapted it to a mini-crane construction robot. A study was conducted to evaluate how naturalistic vibrotactile feedback affects an observer's understanding of telerobotic assembly performed by this robot on a construction site. Seven adults without construction experience observed a mix of manual and autonomous assembly processes both with and without naturalistic vibrotactile feedback. Qualitative analysis of their survey responses and interviews indicates that all participants had positive responses to this technology and believed it would be beneficial for construction activities. Finally, we evaluated the effects of naturalistic vibrotactile feedback provided by wireless AiroTouch during live teleoperation of the mini-crane. Twenty-eight participants remotely controlled the mini-crane to complete three large-scale assembly-related tasks in lab, both with and without this type of haptic feedback. Our results show that naturalistic vibrotactile feedback enhances the participants' awareness of both robot motion and contact between the robot and other objects, particularly in scenarios with limited visibility. These effects increase participants' confidence when controlling the robot. Moreover, there is a noticeable trend of reduced vibration magnitude in the conditions where this type of haptic feedback is provided. The primary contribution of this dissertation is the clear explanation of details that are essential for the effective implementation of naturalistic vibrotactile feedback. We demonstrate that our accessible, audio-based approach can enhance user performance and experience during telerobotic assembly in construction and other application domains. These findings lay the foundation for further exploration of the potential benefits of incorporating haptic cues to enhance user experience during teleoperation.

hi

Project Page [BibTex]

hi Gong, Y. Engineering and Evaluating Naturalistic Vibrotactile Feedback for Telerobotic Assembly University of Stuttgart, Stuttgart, Germany, August 2024, Faculty of Design, Production Engineering and Automotive Engineering (phdthesis)

Project Page [BibTex]

no image
A Measure-Theoretic Axiomatisation of Causality and Kernel Regression

Park, J.

University of Tübingen, Germany, July 2024 (phdthesis)

ei

[BibTex]

ei Park, J. A Measure-Theoretic Axiomatisation of Causality and Kernel Regression University of Tübingen, Germany, July 2024 (phdthesis)

[BibTex]

Modelling Dynamic 3D Human-Object Interactions: From Capture to Synthesis
Modelling Dynamic 3D Human-Object Interactions: From Capture to Synthesis

Taheri, O.

University of Tübingen, July 2024 (phdthesis) To be published

Abstract
Modeling digital humans that move and interact realistically with virtual 3D worlds has emerged as an essential research area recently, with significant applications in computer graphics, virtual and augmented reality, telepresence, the Metaverse, and assistive technologies. In particular, human-object interaction, encompassing full-body motion, hand-object grasping, and object manipulation, lies at the core of how humans execute tasks and represents the complex and diverse nature of human behavior. Therefore, accurate modeling of these interactions would enable us to simulate avatars to perform tasks, enhance animation realism, and develop applications that better perceive and respond to human behavior. Despite its importance, this remains a challenging problem, due to several factors such as the complexity of human motion, the variance of interaction based on the task, and the lack of rich datasets capturing the complexity of real-world interactions. Prior methods have made progress, but limitations persist as they often focus on individual aspects of interaction, such as body, hand, or object motion, without considering the holistic interplay among these components. This Ph.D. thesis addresses these challenges and contributes to the advancement of human-object interaction modeling through the development of novel datasets, methods, and algorithms.

ps

[BibTex]

ps Taheri, O. Modelling Dynamic 3D Human-Object Interactions: From Capture to Synthesis University of Tübingen, July 2024 (phdthesis) To be published

[BibTex]

no image
Advancing Normalising Flows to Model Boltzmann Distributions

Stimper, V.

University of Cambridge, UK, Cambridge, June 2024, (Cambridge-Tübingen-Fellowship-Program) (phdthesis)

ei

[BibTex]

ei Stimper, V. Advancing Normalising Flows to Model Boltzmann Distributions University of Cambridge, UK, Cambridge, June 2024, (Cambridge-Tübingen-Fellowship-Program) (phdthesis)

[BibTex]

no image
Koopman Spectral Analysis Uncovers the Temporal Structure of Spontaneous Neural Events

Shao, K., Xu, Y., Logothetis, N., Shen, Z., Besserve, M.

Computational and Systems Neuroscience Meeting (COSYNE), March 2024 (poster)

ei

link (url) [BibTex]

ei Shao, K., Xu, Y., Logothetis, N., Shen, Z., Besserve, M. Koopman Spectral Analysis Uncovers the Temporal Structure of Spontaneous Neural Events Computational and Systems Neuroscience Meeting (COSYNE), March 2024 (poster)

link (url) [BibTex]

no image
Identifiable Causal Representation Learning

von Kügelgen, J.

University of Cambridge, UK, Cambridge, February 2024, (Cambridge-Tübingen-Fellowship) (phdthesis)

ei

[BibTex]

ei von Kügelgen, J. Identifiable Causal Representation Learning University of Cambridge, UK, Cambridge, February 2024, (Cambridge-Tübingen-Fellowship) (phdthesis)

[BibTex]

Creating a Haptic Empathetic Robot Animal That Feels Touch and Emotion
Creating a Haptic Empathetic Robot Animal That Feels Touch and Emotion

Burns, R.

University of Tübingen, Tübingen, Germany, February 2024, Department of Computer Science (phdthesis)

Abstract
Social touch, such as a hug or a poke on the shoulder, is an essential aspect of everyday interaction. Humans use social touch to gain attention, communicate needs, express emotions, and build social bonds. Despite its importance, touch sensing is very limited in most commercially available robots. By endowing robots with social-touch perception, one can unlock a myriad of new interaction possibilities. In this thesis, I present my work on creating a Haptic Empathetic Robot Animal (HERA), a koala-like robot for children with autism. I demonstrate the importance of establishing design guidelines based on one's target audience, which we investigated through interviews with autism specialists. I share our work on creating full-body tactile sensing for the NAO robot using low-cost, do-it-yourself (DIY) methods, and I introduce an approach to model long-term robot emotions using second-order dynamics.

hi

Project Page [BibTex]

hi Burns, R. Creating a Haptic Empathetic Robot Animal That Feels Touch and Emotion University of Tübingen, Tübingen, Germany, February 2024, Department of Computer Science (phdthesis)

Project Page [BibTex]

Self- and Interpersonal Contact in 3D Human Mesh Reconstruction
Self- and Interpersonal Contact in 3D Human Mesh Reconstruction

Müller, L.

University of Tübingen, Tübingen, 2024 (phdthesis)

Abstract
The ability to perceive tactile stimuli is of substantial importance for human beings in establishing a connection with the surrounding world. Humans rely on the sense of touch to navigate their environment and to engage in interactions with both themselves and other people. The field of computer vision has made great progress in estimating a person’s body pose and shape from an image, however, the investigation of self- and interpersonal contact has received little attention despite its considerable significance. Estimating contact from images is a challenging endeavor because it necessitates methodologies capable of predicting the full 3D human body surface, i.e. an individual’s pose and shape. The limitations of current methods become evident when considering the two primary datasets and labels employed within the community to supervise the task of human pose and shape estimation. First, the widely used 2D joint locations lack crucial information for representing the entire 3D body surface. Second, in datasets of 3D human bodies, e.g. collected from motion capture systems or body scanners, contact is usually avoided, since it naturally leads to occlusion which complicates data cleaning and can break the data processing pipelines. In this thesis, we first address the problem of estimating contact that humans make with themselves from RGB images. To do this, we introduce two novel methods that we use to create new datasets tailored for the task of human mesh estimation for poses with self-contact. We create (1) 3DCP, a dataset of 3D body scan and motion capture data of humans in poses with self-contact and (2) MTP, a dataset of images taken in the wild with accurate 3D reference data using pose mimicking. Next, we observe that 2D joint locations can be readily labeled at scale given an image, however, an equivalent label for self-contact does not exist. Consequently, we introduce (3) distrecte self-contact (DSC) annotations indicating the pairwise contact of discrete regions on the human body. We annotate three existing image datasets with discrete self-contact and use these labels during mesh optimization to bring body parts supposed to touch into contact. Then we train TUCH, a human mesh regressor, on our new datasets. When evaluated on the task of human body pose and shape estimation on public benchmarks, our results show that knowing about self-contact not only improves mesh estimates for poses with self-contact, but also for poses without self-contact. Next, we study contact humans make with other individuals during close social interaction. Reconstructing these interactions in 3D is a significant challenge due to the mutual occlusion. Furthermore, the existing datasets of images taken in the wild with ground-truth contact labels are of insufficient size to facilitate the training of a robust human mesh regressor. In this work, we employ a generative model, BUDDI, to learn the joint distribution of 3D pose and shape of two individuals during their interaction and use this model as prior during an optimization routine. To construct training data we leverage pre-existing datasets, i.e. motion capture data and Flickr images with discrete contact annotations. Similar to discrete self-contact labels, we utilize discrete human- human contact to jointly fit two meshes to detected 2D joint locations. The majority of methods for generating 3D humans focus on the motion of a single person and operate on 3D joint locations. While these methods can effectively generate motion, their representation of 3D humans is not sufficient for physical contact since they do not model the body surface. Our approach, in contrast, acts on the pose and shape parameters of a human body model, which enables us to sample 3D meshes of two people. We further demonstrate how the knowledge of human proxemics, incorporated in our model, can be used to guide an optimization routine. For this, in each optimization iteration, BUDDI takes the current mesh and proposes a refinement that we subsequently consider in the objective function. This procedure enables us to go beyond state of the art by forgoing ground-truth discrete human-human contact labels during optimization. Self- and interpersonal contact happen on the surface of the human body, however, the majority of existing art tends to predict bodies with similar, “average” body shape. This is due to a lack of training data of paired images taken in the wild and ground- truth 3D body shape and because 2D joint locations are not sufficient to explain body shape. The most apparent solution would be to collect body scans of people together with their photos. This is, however, a time-consuming and cost-intensive process that lacks scalability. Instead, we leverage the vocabulary humans use to describe body shape. First, we ask annotators to label how much a word like “tall” or “long legs” applies to a human body. We gather these ratings for rendered meshes of various body shapes, for which we have ground-truth body model shape parameters, and for images collected from model agency websites. Using this data, we learn a shape-to-attribute (A2S) model that predicts body shape ratings from body shape parameters. Then we train a human mesh regressor, SHAPY, on the model agency images wherein we supervise body shape via attribute annotations using A2S. Since no suitable test set of diverse 3D ground-truth body shape with images taken in natural settings exists, we introduce Human Bodies in the Wild (HBW). This novel dataset contains photographs of individuals together with their body scan. Our model predicts more realistic body shapes from an image and quantitatively improves body shape estimation on this new benchmark. In summary, we present novel datasets, optimization methods, a generative model, and regressors to advance the field of 3D human pose and shape estimation. Taken together, these methods open up ways to obtain more accurate and realistic 3D mesh estimates from images with multiple people in self- and mutual contact poses and with diverse body shapes. This line of research also enables generative approaches to create more natural, human-like avatars. We believe that knowing about self- and human-human contact through computer vision has wide-ranging implications in other fields as for example robotics, fitness, or behavioral science.

ps

[BibTex]

ps Müller, L. Self- and Interpersonal Contact in 3D Human Mesh Reconstruction University of Tübingen, Tübingen, 2024 (phdthesis)

[BibTex]

Natural Language Control for 3D Human Motion Synthesis
Natural Language Control for 3D Human Motion Synthesis

Petrovich, M.

LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS, 2024 (phdthesis)

Abstract
3D human motions are at the core of many applications in the film industry, healthcare, augmented reality, virtual reality and video games. However, these applications often rely on expensive and time-consuming motion capture data. The goal of this thesis is to explore generative models as an alternative route to obtain 3D human motions. More specifically, our aim is to allow a natural language interface as a means to control the generation process. To this end, we develop a series of models that synthesize realistic and diverse motions following the semantic inputs. In our first contribution, described in Chapter 3, we address the challenge of generating human motion sequences conditioned on specific action categories. We introduce ACTOR, a conditional variational autoencoder (VAE) that learns an action-aware latent representation for human motions. We show significant gains over existing methods thanks to our new Transformer-based VAE formulation, encoding and decoding SMPL pose sequences through a single motion-level embedding. In our second contribution, described in Chapter 4, we go beyond categorical actions, and dive into the task of synthesizing diverse 3D human motions from textual descriptions allowing a larger vocabulary and potentially more fine-grained control. Our work stands out from previous research by not deterministically generating a single motion sequence, but by synthesizing multiple, varied sequences from a given text. We propose TEMOS, building on our VAE-based ACTOR architecture, but this time integrating a pretrained text encoder to handle large-vocabulary natural language inputs. In our third contribution, described in Chapter 5, we address the adjacent task of text-to-3D human motion retrieval, where the goal is to search in a motion collection by querying via text. We introduce a simple yet effective approach, named TMR, building on our earlier model TEMOS, by integrating a contrastive loss to enhance the structure of the cross-modal latent space. Our findings emphasize the importance of retaining the motion generation loss in conjunction with contrastive training for improved results. We establish a new evaluation benchmark and conduct analyses on several protocols. In our fourth contribution, described in Chapter 6, we introduce a new problem termed as “multi-track timeline control” for text-driven 3D human motion synthesis. Instead of a single textual prompt, users can organize multiple prompts in temporal intervals that may overlap. We introduce STMC, a test-time denoising method that can be integrated with any pre-trained motion diffusion model. Our evaluations demonstrate that our method generates motions that closely match the semantic and temporal aspects of the input timelines. In summary, our contributions in this thesis are as follows: (i) we develop a generative variational autoencoder, ACTOR, for action-conditioned generation of human motion sequences, (ii) we introduce TEMOS, a text-conditioned generative model that synthesizes diverse human motions from textual descriptions, (iii) we present TMR, a new approach for text-to-3D human motion retrieval, (iv) we propose STMC, a method for timeline control in text-driven motion synthesis, enabling the generation of detailed and complex motions.

ps

Thesis [BibTex]

ps Petrovich, M. Natural Language Control for 3D Human Motion Synthesis LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS, 2024 (phdthesis)

Thesis [BibTex]

2023

no image
Navigating the Ocean of Biases: Political Bias Attribution in Language Models via Causal Structures

Jenny, D.

ETH Zurich, Switzerland, November 2023, external supervision (thesis)

ei

[BibTex]

2023

ei Jenny, D. Navigating the Ocean of Biases: Political Bias Attribution in Language Models via Causal Structures ETH Zurich, Switzerland, November 2023, external supervision (thesis)

[BibTex]

no image
Gesture-Based Nonverbal Interaction for Exercise Robots

Mohan, M.

University of Tübingen, Tübingen, Germany, October 2023, Department of Computer Science (phdthesis)

Abstract
When teaching or coaching, humans augment their words with carefully timed hand gestures, head and body movements, and facial expressions to provide feedback to their students. Robots, however, rarely utilize these nuanced cues. A minimally supervised social robot equipped with these abilities could support people in exercising, physical therapy, and learning new activities. This thesis examines how the intuitive power of human gestures can be harnessed to enhance human-robot interaction. To address this question, this research explores gesture-based interactions to expand the capabilities of a socially assistive robotic exercise coach, investigating the perspectives of both novice users and exercise-therapy experts. This thesis begins by concentrating on the user's engagement with the robot, analyzing the feasibility of minimally supervised gesture-based interactions. This exploration seeks to establish a framework in which robots can interact with users in a more intuitive and responsive manner. The investigation then shifts its focus toward the professionals who are integral to the success of these innovative technologies: the exercise-therapy experts. Roboticists face the challenge of translating the knowledge of these experts into robotic interactions. We address this challenge by developing a teleoperation algorithm that can enable exercise therapists to create customized gesture-based interactions for a robot. Thus, this thesis lays the groundwork for dynamic gesture-based interactions in minimally supervised environments, with implications for not only exercise-coach robots but also broader applications in human-robot interaction.

hi

Project Page [BibTex]

hi Mohan, M. Gesture-Based Nonverbal Interaction for Exercise Robots University of Tübingen, Tübingen, Germany, October 2023, Department of Computer Science (phdthesis)

Project Page [BibTex]

no image
Learning and Testing Powerful Hypotheses

Kübler, J. M.

University of Tübingen, Germany, July 2023 (phdthesis)

ei

[BibTex]

ei Kübler, J. M. Learning and Testing Powerful Hypotheses University of Tübingen, Germany, July 2023 (phdthesis)

[BibTex]

no image
Learning Identifiable Representations: Independent Influences and Multiple Views

Gresele, L.

University of Tübingen, Germany, June 2023 (phdthesis)

ei

[BibTex]

no image
Learning with and for discrete optimization

Paulus, M.

ETH Zurich, Switzerland, May 2023, CLS PhD Program (phdthesis)

ei

[BibTex]

ei Paulus, M. Learning with and for discrete optimization ETH Zurich, Switzerland, May 2023, CLS PhD Program (phdthesis)

[BibTex]

no image
Object-Level Dynamic Scene Reconstruction With Physical Plausibility From RGB-D Images

Strecke, M. F.

Eberhard Karls Universität Tübingen, Tübingen, 2023 (phdthesis)

Abstract
Humans have the remarkable ability to perceive and interact with objects in the world around them. They can easily segment objects from visual data and have an intuitive understanding of how physics influences objects. By contrast, robots are so far often constrained to tailored environments for a specific task, due to their inability to reconstruct a versatile and accurate scene representation. In this thesis, we combine RGB-D video data with background knowledge of real-world physics to develop such a representation for robots.

Our contributions can be separated into two main parts: a dynamic object tracking tool and optimization frameworks that allow for improving shape reconstructions based on physical plausibility. The dynamic object tracking tool "EM-Fusion" detects, segments, reconstructs, and tracks objects from RGB-D video data. We propose a probabilistic data association approach for attributing the image pixels to the different moving objects in the scene. This allows us to track and reconstruct moving objects and the background scene with state-of-the art accuracy and robustness towards occlusions.

We investigate two ways of further optimizing the reconstructed shapes of moving objects based on physical plausibility. The first of these, "Co-Section", includes physical plausibility by reasoning about the empty space around an object. We observe that no two objects can occupy the same space at the same time and that the depth images in the input video provide an estimate of observed empty space. Based on these observations, we propose intersection and hull constraints, which we combine with the observed surfaces in a global optimization approach. Compared to EM-Fusion, which only reconstructs the observed surface, Co-Section optimizes watertight shapes. These watertight shapes provide a rough estimate of unseen surfaces and could be useful as initialization for further refinement, e.g., by interactive perception. In the second optimization approach, "DiffSDFSim", we reason about object shapes based on physically plausible object motion. We observe that object trajectories after collisions depend on the object's shape, and extend a differentiable physics simulation for optimizing object shapes together with other physical properties (e.g., forces, masses, friction) based on the motion of the objects and their interactions. Our key contributions are using signed distance function models for representing shapes and a novel method for computing gradients that models the dependency of the time of contact on object shapes. We demonstrate that our approach recovers target shapes well by fitting to target trajectories and depth observations. Further, the ground-truth trajectories are recovered well in simulation using the resulting shape and physical properties. This enables predictions about the future motion of objects by physical simulation.

We anticipate that our contributions can be useful building blocks in the development of 3D environment perception for robots. The reconstruction of individual objects as in EM-Fusion is a key ingredient required for interactions with objects. Completed shapes as the ones provided by Co-Section provide useful cues for planning interactions like grasping of objects. Finally, the recovery of shape and other physical parameters using differentiable simulation as in DiffSDFSim allows simulating objects and thus predicting the effects of interactions. Future work might extend the presented works for interactive perception of dynamic environments by comparing these predictions with observed real-world interactions to further improve the reconstructions and physical parameter estimations.

ev

link (url) DOI [BibTex]

no image
Wave front shaping with zone plates: Fabrication and characterization of lenses for soft x-ray applications from standard to singular optics

Baluktsian, M.

Universität Stuttgart, Stuttgart (und Verlag Dr. Hut, München), 2023 (phdthesis)

mms

link (url) [BibTex]

no image
Static and dynamic investigation of magnonic systems: materials, applications and modeling

Schulz, Frank Martin Ernst

Universität Stuttgart, Stuttgart, 2023 (phdthesis)

mms

link (url) DOI [BibTex]

mms Schulz, Frank Martin Ernst Static and dynamic investigation of magnonic systems: materials, applications and modeling Universität Stuttgart, Stuttgart, 2023 (phdthesis)

link (url) DOI [BibTex]

2022

no image
Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)

Biester, L., Demszky, D., Jin, Z., Sachan, M., Tetreault, J., Wilson, S., Xiao, L., Zhao, J.

Association for Computational Linguistics, December 2022 (proceedings)

ei

link (url) [BibTex]

2022

ei Biester, L., Demszky, D., Jin, Z., Sachan, M., Tetreault, J., Wilson, S., Xiao, L., Zhao, J. Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI) Association for Computational Linguistics, December 2022 (proceedings)

link (url) [BibTex]

no image
Multi-Timescale Representation Learning of Human and Robot Haptic Interactions

Richardson, B.

University of Stuttgart, Stuttgart, Germany, December 2022, Faculty of Computer Science, Electrical Engineering and Information Technology (phdthesis)

Abstract
The sense of touch is one of the most crucial components of the human sensory system. It allows us to safely and intelligently interact with the physical objects and environment around us. By simply touching or dexterously manipulating an object, we can quickly infer a multitude of its properties. For more than fifty years, researchers have studied how humans physically explore and form perceptual representations of objects. Some of these works proposed the paradigm through which human haptic exploration is presently understood: humans use a particular set of exploratory procedures to elicit specific semantic attributes from objects. Others have sought to understand how physically measured object properties correspond to human perception of semantic attributes. Few, however, have investigated how specific explorations are perceived. As robots become increasingly advanced and more ubiquitous in daily life, they are beginning to be equipped with haptic sensing capabilities and algorithms for processing and structuring haptic information. Traditional haptics research has so far strongly influenced the introduction of haptic sensation and perception into robots but has not proven sufficient to give robots the necessary tools to become intelligent autonomous agents. The work presented in this thesis seeks to understand how single and sequential haptic interactions are perceived by both humans and robots. In our first study, we depart from the more traditional methods of studying human haptic perception and investigate how the physical sensations felt during single explorations are perceived by individual people. We treat interactions as probability distributions over a haptic feature space and train a model to predict how similarly a pair of surfaces is rated, predicting perceived similarity with a reasonable degree of accuracy. Our novel method also allows us to evaluate how individual people weigh different surface properties when they make perceptual judgments. The method is highly versatile and presents many opportunities for further studies into how humans form perceptual representations of specific explorations. Our next body of work explores how to improve robotic haptic perception of single interactions. We use unsupervised feature-learning methods to derive powerful features from raw robot sensor data and classify robot explorations into numerous haptic semantic property labels that were assigned from human ratings. Additionally, we provide robots with more nuanced perception by learning to predict graded ratings of a subset of properties. Our methods outperform previous attempts that all used hand-crafted features, demonstrating the limitations of such traditional approaches. To push robot haptic perception beyond evaluation of single explorations, our final work introduces and evaluates a method to give robots the ability to accumulate information over many sequential actions; our approach essentially takes advantage of object permanence by conditionally and recursively updating the representation of an object as it is sequentially explored. We implement our method on a robotic gripper platform that performs multiple exploratory procedures on each of many objects. As the robot explores objects with new procedures, it gains confidence in its internal representations and classification of object properties, thus moving closer to the marvelous haptic capabilities of humans and providing a solid foundation for future research in this domain.

hi

link (url) Project Page [BibTex]

hi Richardson, B. Multi-Timescale Representation Learning of Human and Robot Haptic Interactions University of Stuttgart, Stuttgart, Germany, December 2022, Faculty of Computer Science, Electrical Engineering and Information Technology (phdthesis)

link (url) Project Page [BibTex]

Reconstructing Expressive {3D} Humans from {RGB} Images
Reconstructing Expressive 3D Humans from RGB Images

Choutas, V.

ETH Zurich, Max Planck Institute for Intelligent Systems and ETH Zurich, December 2022 (phdthesis)

Abstract
To interact with our environment, we need to adapt our body posture and grasp objects with our hands. During a conversation our facial expressions and hand gestures convey important non-verbal cues about our emotional state and intentions towards our fellow speakers. Thus, modeling and capturing 3D full-body shape and pose, hand articulation and facial expressions are necessary to create realistic human avatars for augmented and virtual reality. This is a complex task, due to the large number of degrees of freedom for articulation, body shape variance, occlusions from objects and self-occlusions from body parts, e.g. crossing our hands, and subject appearance. The community has thus far relied on expensive and cumbersome equipment, such as multi-view cameras or motion capture markers, to capture the 3D human body. While this approach is effective, it is limited to a small number of subjects and indoor scenarios. Using monocular RGB cameras would greatly simplify the avatar creation process, thanks to their lower cost and ease of use. These advantages come at a price though, since RGB capture methods need to deal with occlusions, perspective ambiguity and large variations in subject appearance, in addition to all the challenges posed by full-body capture. In an attempt to simplify the problem, researchers generally adopt a divide-and-conquer strategy, estimating the body, face and hands with distinct methods using part-specific datasets and benchmarks. However, the hands and face constrain the body and vice-versa, e.g. the position of the wrist depends on the elbow, shoulder, etc.; the divide-and-conquer approach can not utilize this constraint. In this thesis, we aim to reconstruct the full 3D human body, using only readily accessible monocular RGB images. In a first step, we introduce a parametric 3D body model, called SMPL-X, that can represent full-body shape and pose, hand articulation and facial expression. Next, we present an iterative optimization method, named SMPLify-X, that fits SMPL-X to 2D image keypoints. While SMPLify-X can produce plausible results if the 2D observations are sufficiently reliable, it is slow and susceptible to initialization. To overcome these limitations, we introduce ExPose, a neural network regressor, that predicts SMPL-X parameters from an image using body-driven attention, i.e. by zooming in on the hands and face, after predicting the body. From the zoomed-in part images, dedicated part networks predict the hand and face parameters. ExPose combines the independent body, hand, and face estimates by trusting them equally. This approach though does not fully exploit the correlation between parts and fails in the presence of challenges such as occlusion or motion blur. Thus, we need a better mechanism to aggregate information from the full body and part images. PIXIE uses neural networks called moderators that learn to fuse information from these two image sets before predicting the final part parameters. Overall, the addition of the hands and face leads to noticeably more natural and expressive reconstructions. Creating high fidelity avatars from RGB images requires accurate estimation of 3D body shape. Although existing methods are effective at predicting body pose, they struggle with body shape. We identify the lack of proper training data as the cause. To overcome this obstacle, we propose to collect internet images from fashion models websites, together with anthropometric measurements. At the same time, we ask human annotators to rate images and meshes according to a pre-defined set of linguistic attributes. We then define mappings between measurements, linguistic shape attributes and 3D body shape. Equipped with these mappings, we train a neural network regressor, SHAPY, that predicts accurate 3D body shapes from a single RGB image. We observe that existing 3D shape benchmarks lack subject variety and/or ground-truth shape. Thus, we introduce a new benchmark, Human Bodies in the Wild (HBW), which contains images of humans and their corresponding 3D ground-truth body shape. SHAPY shows how we can overcome the lack of in-the-wild images with 3D shape annotations through easy-to-obtain anthropometric measurements and linguistic shape attributes. Regressors that estimate 3D model parameters are robust and accurate, but often fail to tightly fit the observations. Optimization-based approaches tightly fit the data, by minimizing an energy function composed of a data term that penalizes deviations from the observations and priors that encode our knowledge of the problem. Finding the balance between these terms and implementing a performant version of the solver is a time-consuming and non-trivial task. Machine-learned continuous optimizers combine the benefits of both regression and optimization approaches. They learn the priors directly from data, avoiding the need for hand-crafted heuristics and loss term balancing, and benefit from optimized neural network frameworks for fast inference. Inspired from the classic Levenberg-Marquardt algorithm, we propose a neural optimizer that outperforms classic optimization, regression and hybrid optimization-regression approaches. Our proposed update rule uses a weighted combination of gradient descent and a network-predicted update. To show the versatility of the proposed method, we apply it on three other problems, namely full body estimation from (i) 2D keypoints, (ii) head and hand location from a head-mounted device and (iii) face tracking from dense 2D landmarks. Our method can easily be applied to new model fitting problems and offers a competitive alternative to well-tuned traditional model fitting pipelines, both in terms of accuracy and speed. To summarize, we propose a new and richer representation of the human body, SMPL-X, that is able to jointly model the 3D human body pose and shape, facial expressions and hand articulation. We propose methods, SMPLify-X, ExPose and PIXIE that estimate SMPL-X parameters from monocular RGB images, progressively improving the accuracy and realism of the predictions. To further improve reconstruction fidelity, we demonstrate how we can use easy-to-collect internet data and human annotations to overcome the lack of 3D shape data and train a model, SHAPY, that predicts accurate 3D body shape from a single RGB image. Finally, we propose a flexible learnable update rule for parametric human model fitting that outperforms both classic optimization and neural network approaches. This approach is easily applicable to a variety of problems, unlocking new applications in AR/VR scenarios.

ps

pdf [BibTex]

ps Choutas, V. Reconstructing Expressive 3D Humans from RGB Images ETH Zurich, Max Planck Institute for Intelligent Systems and ETH Zurich, December 2022 (phdthesis)

pdf [BibTex]

no image
Mechanical Design, Development and Testing of Bioinspired Legged Robots for Dynamic Locomotion

Sarvestani, L. A.

Eberhard Karls Universität Tübingen, Tübingen , November 2022 (phdthesis)

dlg

DOI [BibTex]

dlg Sarvestani, L. A. Mechanical Design, Development and Testing of Bioinspired Legged Robots for Dynamic Locomotion Eberhard Karls Universität Tübingen, Tübingen , November 2022 (phdthesis)

DOI [BibTex]

no image
Towards learning mechanistic models at the right level of abstraction

Neitz, A.

University of Tübingen, Germany, November 2022 (phdthesis)

ei

[BibTex]

ei Neitz, A. Towards learning mechanistic models at the right level of abstraction University of Tübingen, Germany, November 2022 (phdthesis)

[BibTex]

no image
Learning Causal Representations for Generalization and Adaptation in Supervised, Imitation, and Reinforcement Learning

Lu, C.

University of Cambridge, UK, Cambridge, October 2022, (Cambridge-Tübingen-Fellowship) (phdthesis)

ei

[BibTex]

ei Lu, C. Learning Causal Representations for Generalization and Adaptation in Supervised, Imitation, and Reinforcement Learning University of Cambridge, UK, Cambridge, October 2022, (Cambridge-Tübingen-Fellowship) (phdthesis)

[BibTex]

no image
Understanding the Influence of Moisture on Fingerpad-Surface Interactions

Nam, S.

University of Tübingen, Tübingen, Germany, October 2022, Department of Computer Science (phdthesis)

Abstract
People frequently touch objects with their fingers. The physical deformation of a finger pressing an object surface stimulates mechanoreceptors, resulting in a perceptual experience. Through interactions between perceptual sensations and motor control, humans naturally acquire the ability to manage friction under various contact conditions. Many researchers have advanced our understanding of human fingers to this point, but their complex structure and the variations in friction they experience due to continuously changing contact conditions necessitate additional study. Moisture is a primary factor that influences many aspects of the finger. In particular, sweat excreted from the numerous sweat pores on the fingerprints modifies the finger's material properties and the contact conditions between the finger and a surface. Measuring changes of the finger's moisture over time and in response to external stimuli presents a challenge for researchers, as commercial moisture sensors do not provide continuous measurements. This dissertation investigates the influence of moisture on fingerpad-surface interactions from diverse perspectives. First, we examine the extent to which moisture on the finger contributes to the sensation of stickiness during contact with glass. Second, we investigate the representative material properties of a finger at three distinct moisture levels, since the softness of human skin varies significantly with moisture. The third perspective is friction; we examine how the contact conditions, including the moisture of a finger, determine the available friction force opposing lateral sliding on glass. Fourth, we have invented and prototyped a transparent in vivo moisture sensor for the continuous measurement of finger hydration. In the first part of this dissertation, we explore how the perceptual intensity of light stickiness relates to the physical interaction between the skin and the surface. We conducted a psychophysical experiment in which nine participants actively pressed their index finger on a flat glass plate with a normal force close to 1.5 N and then detached it after a few seconds. A custom-designed apparatus recorded the contact force vector and the finger contact area during each interaction as well as pre- and post-trial finger moisture. After detaching their finger, participants judged the stickiness of the glass using a nine-point scale. We explored how sixteen physical variables derived from the recorded data correlate with each other and with the stickiness judgments of each participant. These analyses indicate that stickiness perception mainly depends on the pre-detachment pressing duration, the time taken for the finger to detach, and the impulse in the normal direction after the normal force changes sign; finger-surface adhesion seems to build with pressing time, causing a larger normal impulse during detachment and thus a more intense stickiness sensation. We additionally found a strong between-subjects correlation between maximum real contact area and peak pull-off force, as well as between finger moisture and impulse. When a fingerpad presses into a hard surface, the development of the contact area depends on the pressing force and speed. Importantly, it also varies with the finger's moisture, presumably because hydration changes the tissue's material properties. Therefore, for the second part of this dissertation, we collected data from one finger repeatedly pressing a glass plate under three moisture conditions, and we constructed a finite element model that we optimized to simulate the same three scenarios. We controlled the moisture of the subject's finger to be dry, natural, or moist and recorded 15 pressing trials in each condition. The measurements include normal force over time plus finger-contact images that are processed to yield gross contact area. We defined the axially symmetric 3D model's lumped parameters to include an SLS-Kelvin model (spring in series with parallel spring and damper) for the bulk tissue, plus an elastic epidermal layer. Particle swarm optimization was used to find the parameter values that cause the simulation to best match the trials recorded in each moisture condition. The results show that the softness of the bulk tissue reduces as the finger becomes more hydrated. The epidermis of the moist finger model is softest, while the natural finger model has the highest viscosity. In the third part of this dissertation, we focused on friction between the fingerpad and the surface. The magnitude of finger-surface friction available at the onset of full slip is crucial for understanding how the human hand can grip and manipulate objects. Related studies revealed the significance of moisture and contact time in enhancing friction. Recent research additionally indicated that surface temperature may also affect friction. However, previously reported friction coefficients have been measured only in dynamic contact conditions, where the finger is already sliding across the surface. In this study, we repeatedly measured the initial friction before full slip under eight contact conditions with low and high finger moisture, pressing time, and surface temperature. Moisture and pressing time both independently increased finger-surface friction across our population of twelve participants, and the effect of surface temperature depended on the contact conditions. Furthermore, detailed analysis of the recorded measurements indicates that micro stick-slip during the partial-slip phase contributes to enhanced friction. For the fourth and final part of this dissertation, we designed a transparent moisture sensor for continuous measurement of fingerpad hydration. Because various stimuli cause the sweat pores on fingerprints to excrete sweat, many researchers want to quantify the flow and assess its impact on the formation of the contact area. Unfortunately, the most popular sensor for skin hydration is opaque and does not offer continuous measurements. Our capacitive moisture sensor consists of a pair of inter-digital electrodes covered by an insulating layer, enabling impedance measurements across a wide frequency range. This proposed sensor is made entirely of transparent materials, which allows us to simultaneously measure the finger's contact area. Electrochemical impedance spectroscopy identifies the equivalent electrical circuit and the electrical component parameters that are affected by the amount of moisture present on the surface of the sensor. Most notably, the impedance at 1 kHz seems to best reflect the relative amount of sweat.

hi

DOI Project Page [BibTex]

hi Nam, S. Understanding the Influence of Moisture on Fingerpad-Surface Interactions University of Tübingen, Tübingen, Germany, October 2022, Department of Computer Science (phdthesis)

DOI Project Page [BibTex]

no image
Learning Time-Continuous Dynamics Models with Gaussian-Process-Based Gradient Matching

Wenk, P.

ETH Zurich, Switzerland, October 2022, CLS PhD Program (phdthesis)

ei

[BibTex]

ei Wenk, P. Learning Time-Continuous Dynamics Models with Gaussian-Process-Based Gradient Matching ETH Zurich, Switzerland, October 2022, CLS PhD Program (phdthesis)

[BibTex]

no image
Methods for Minimizing the Spread of Misinformation on the Web

Tabibian, B.

University of Tübingen, Germany, September 2022 (phdthesis)

ei

[BibTex]

ei Tabibian, B. Methods for Minimizing the Spread of Misinformation on the Web University of Tübingen, Germany, September 2022 (phdthesis)

[BibTex]

no image
Learning and Using Causal Knowledge: A Further Step Towards a Higher-Level Intelligence

Huang, B.

Carnegie Mellon University, Pittsburgh, USA, July 2022 (phdthesis)

ei

[BibTex]

ei Huang, B. Learning and Using Causal Knowledge: A Further Step Towards a Higher-Level Intelligence Carnegie Mellon University, Pittsburgh, USA, July 2022 (phdthesis)

[BibTex]

no image
Learning and Using Causal Knowledge: A Further Step Towards a Higher-Level Intelligence

Huang, B.

Carnegie Mellon University, July 2022, external supervision (phdthesis)

ei

[BibTex]

ei Huang, B. Learning and Using Causal Knowledge: A Further Step Towards a Higher-Level Intelligence Carnegie Mellon University, July 2022, external supervision (phdthesis)

[BibTex]

no image
Proceedings of the First Conference on Causal Learning and Reasoning (CLeaR 2022)

Schölkopf, B., Uhler, C., Zhang, K.

177, Proceedings of Machine Learning Research, PMLR, April 2022 (proceedings)

ei

link (url) [BibTex]

ei Schölkopf, B., Uhler, C., Zhang, K. Proceedings of the First Conference on Causal Learning and Reasoning (CLeaR 2022) 177, Proceedings of Machine Learning Research, PMLR, April 2022 (proceedings)

link (url) [BibTex]

no image
Variational Inference in Dynamical Systems

Ialongo, A.

University of Cambridge, UK, Cambridge, February 2022, (Cambridge-Tübingen-Fellowship) (phdthesis)

ei

[BibTex]

ei Ialongo, A. Variational Inference in Dynamical Systems University of Cambridge, UK, Cambridge, February 2022, (Cambridge-Tübingen-Fellowship) (phdthesis)

[BibTex]

no image
Entwicklung von Methoden und Bausteinen zur Realisierung Komplexer Magnonischer Systeme

Groß, F.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2022 (phdthesis)

mms

link (url) [BibTex]

mms Groß, F. Entwicklung von Methoden und Bausteinen zur Realisierung Komplexer Magnonischer Systeme Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2022 (phdthesis)

link (url) [BibTex]

no image
Machine-Learning-Driven Haptic Sensor Design

Sun, H.

University of Tuebingen, Library, 2022 (phdthesis)

Abstract
Similar to biological systems, robots may need skin-like sensing ability to perceive interactions in complex, changing, and human-involved environments. Current skin-like sensing technologies are still far behind their biological counterparts when considering resolution, dynamics range, robustness, and surface coverage together. One key challenge is the wiring of sensing elements. During my Ph.D. study, I explore how machine learning can enable the design of a new kind of haptic sensors to deal with such a challenge. On the one hand, I propose super-resolution-oriented tactile skins, reducing the number of physical sensing elements while achieving high spatial accuracy. On the other hand, I explore vision-based haptic sensor designs. In this thesis, I present four types of machine-learning-driven haptic sensors that I designed for coarse and fine robotic applications, varying from large surface (robot limbs) to small surface sensing (robot fingers). Moreover, I propose a super-resolution theory to guide sensor designs at all levels ranging from hardware design (material/structure/transduction), data collection (real/simulated), and signal processing methods (analytical/data-driven). I investigate two designs for large-scale coarse-resolution sensing, e.g., robotic limbs. HapDef sparsely attaches a few strain gauges on a large curved surface internally to measure the deformation over the whole surface. ERT-DNN wraps a large surface with a piece of multi-layered conductive fabric, which varies its conductivity upon contacts exerted. I also conceive two approaches for small-scale fine-resolution sensing, e.g., robotic fingertips. BaroDome sparsely embeds a few barometers inside a soft elastomer to measure internal pressure changes caused by external contact. Insight encloses a high-resolution camera to view a soft shell from within. Generically, an inverse problem needs to be solved when trying to obtain high-resolution sensing with a few physical sensing elements. I develop machine-learning frameworks suitable for solving this inverse problem. They process various raw sensor data and extract useful haptic information in practice. Machine learning methods rely on data collected by an automated robotic stimulation device or synthesized using finite element methods. I build several physical testbeds and finite element models to collect copious data. I propose machine learning frameworks to combine data from different sources that are good enough to deal with the noise in real data and generalize well from seen to unseen situations. While developing my prototype sensors, I have faced reoccurring design choices. To help my developments and guide future research, I propose a unified theory with the concept of taxel-value-isolines. It captures the physical effects required for super-resolution, ties them to all parts of the sensor design, and allows us to assess them quantitatively. The theory offers an explanation about physically achievable accuracies for localizing and quantifying contact based on uncertainties introduced by measurement noise in sensor elements. The theoretical analysis aims to predict the best performance before a physical prototype is built and helps to evaluate the hardware design, data collection, and data processing methods during implementation. This thesis presents a new perspective on haptic sensor design. Using machine learning to substitute the entire data-processing pipeline, I present several haptic sensor designs for applications ranging from large-surface skins to high-resolution tactile fingertip sensors. The developed theory for obtaining optimal super-resolution can guide future sensor designs.

al

link (url) [BibTex]

al Sun, H. Machine-Learning-Driven Haptic Sensor Design University of Tuebingen, Library, 2022 (phdthesis)

link (url) [BibTex]

no image
Advanced Miniature Soft Robotic Systems

Wang, T.

ETH Zürich , Zürich, 2022 (phdthesis)

pi

DOI [BibTex]

pi Wang, T. Advanced Miniature Soft Robotic Systems ETH Zürich , Zürich, 2022 (phdthesis)

DOI [BibTex]

2021

no image
Models for Data-Efficient Reinforcement Learning on Real-World Applications

Doerr, A.

University of Stuttgart, Stuttgart, October 2021 (phdthesis)

ics

DOI [BibTex]

2021

ics Doerr, A. Models for Data-Efficient Reinforcement Learning on Real-World Applications University of Stuttgart, Stuttgart, October 2021 (phdthesis)

DOI [BibTex]

no image
Dynamics of Learning and Learning of Dynamics

Mehrjou, A.

ETH Zürich, Zürich, October 2021 (phdthesis)

ei

DOI [BibTex]

ei Mehrjou, A. Dynamics of Learning and Learning of Dynamics ETH Zürich, Zürich, October 2021 (phdthesis)

DOI [BibTex]

no image
A Large Scale Brain-Computer Interface for Patients with Neurological Diseases

Hohmann, M.

University of Tübingen, Germany, September 2021 (phdthesis)

ei

[BibTex]

ei Hohmann, M. A Large Scale Brain-Computer Interface for Patients with Neurological Diseases University of Tübingen, Germany, September 2021 (phdthesis)

[BibTex]

no image
Deep Learning Beyond The Training Distribution

Parascandolo, G.

ETH Zürich, Switzerland, Zürich, September 2021, (CLS Fellowship Program) (phdthesis)

ei

DOI [BibTex]

ei Parascandolo, G. Deep Learning Beyond The Training Distribution ETH Zürich, Switzerland, Zürich, September 2021, (CLS Fellowship Program) (phdthesis)

DOI [BibTex]

Huggie{B}ot: An Interactive Hugging Robot With Visual and Haptic Perception
HuggieBot: An Interactive Hugging Robot With Visual and Haptic Perception

Block, A. E.

ETH Zürich, Zürich, August 2021, Department of Computer Science (phdthesis)

Abstract
Hugs are one of the first forms of contact and affection humans experience. Receiving a hug is one of the best ways to feel socially supported, and the lack of social touch can have severe adverse effects on an individual's well-being. Due to the prevalence and health benefits of hugging, roboticists are interested in creating robots that can hug humans as seamlessly as humans hug other humans. However, hugs are complex affective interactions that need to adapt to the height, body shape, and preferences of the hugging partner, and they often include intra-hug gestures like squeezes. This dissertation aims to create a series of hugging robots that use visual and haptic perception to provide enjoyable interactive hugs. Each of the four presented HuggieBot versions is evaluated by measuring how users emotionally and behaviorally respond to hugging it; HuggieBot 4.0 is explicitly compared to a human hugging partner using physiological measures. Building on research both within and outside of human-robot interaction (HRI), this thesis proposes eleven tenets of natural and enjoyable robotic hugging. These tenets were iteratively crafted through a design process combining user feedback and experimenter observation, and they were evaluated through user studies. A good hugging robot should (1) be soft, (2) be warm, (3) be human-sized, (4) autonomously invite the user for a hug when it detects someone in its personal space, and then it should wait for the user to begin walking toward it before closing its arms to ensure a consensual and synchronous hugging experience. It should also (5) adjust its embrace to the user's size and position, (6) reliably release when the user wants to end the hug, and (7) perceive the user's height and adapt its arm positions accordingly to comfortably fit around the user at appropriate body locations. Finally, a hugging robot should (8) accurately detect and classify gestures applied to its torso in real time, regardless of the user's hand placement, (9) respond quickly to their intra-hug gestures, (10) adopt a gesture paradigm that blends user preferences with slight variety and spontaneity, and (11) occasionally provide unprompted, proactive affective social touch to the user through intra-hug gestures. We believe these eleven tenets are essential to delivering high-quality robot hugs. Their presence results in a hug that pleases the user, and their absence results in a hug that is likely to be inadequate. We present these tenets as guidelines for future hugging robot creators to follow when designing new hugging robots to ensure user acceptance. We tested the four versions of HuggieBot through six user studies. First, we analyzed data collected in a previous study with a modified Willow Garage Personal Robot 2 (PR2) to evaluate human responses to different robot physical characteristics and hugging behaviors. Participants experienced and evaluated twelve hugs with the robot, divided into three randomly ordered trials that focused on physical robot characteristics (single factor, three levels) and nine randomly ordered trials with low, medium, and high hug pressure and duration (two factors, three levels each). Second, we created an entirely new robotic platform, HuggieBot 2.0, according to our first six tenets. The new platform features a soft, warm, inflated body (HuggieChest) and uses visual and haptic sensing to deliver closed-loop hugging. We first verified the outward appeal of this platform compared to the previous PR2-based HuggieBot 1.0 via an online video-watching study involving 117 users. We then conducted an in-person experiment in which 32 users each exchanged eight hugs with HuggieBot 2.0, experiencing all combinations of visual hug initiation, haptic sizing, and haptic releasing. We then refine the original fourth tenet (visually perceive its user) and present the remaining five tenets for designing interactive hugging robots; we validate the full list of eleven tenets through more in-person studies with our custom robot. To enable perceptive and pleasing autonomous robot behavior, we investigated robot responses to four human intra-hug gestures: holding, rubbing, patting, and squeezing. The robot's inflated torso's microphone and pressure sensor collected data of 32 people repeatedly demonstrating these gestures, which were used to develop a perceptual algorithm that classifies user actions with 88% accuracy. From user preferences, we created a probabilistic behavior algorithm that chooses robot responses in real time. We implemented improvements to the robot platform to create a third version of our robot, HuggieBot 3.0. We then validated its gesture perception system and behavior algorithm in a fifth user study with 16 users. Finally, we refined the quality and comfort of the embrace by adjusting the joint torques and joint angles of the closed pose position, we further improved the robot's visual perception to detect changes in user approach, we upgraded the robot's response to users who do not press on its back, and we had the robot respond to all intra-hug gestures with squeezes to create our final version of the robotic platform, HuggieBot 4.0. In our sixth user study, we investigated the emotional and physiological effects of hugging a robot compared to the effects of hugging a friendly but unfamiliar person. We continuously monitored participant heart rate and collected saliva samples at seven time points across the 3.5-hour study to measure the temporal evolution of cortisol and oxytocin. We used an adapted Trier Social Stress Test (TSST) protocol to reliably and ethically induce stress in the participants. They then experienced one of five different hug intervention methods before all interacting with HuggieBot 4.0. The results of these six user studies validated our eleven hugging tenets and informed the iterative design of HuggieBot. We see that users enjoy robot softness, robot warmth, and being physically squeezed by the robot. Users dislike being released too soon from a hug and equally dislike being held by the robot for too long. Adding haptic reactivity definitively improves user perception of a hugging robot; the robot's responses and proactive intra-hug gestures were greatly enjoyed. In our last study, we learned that HuggieBot can positively affect users on a physiological level and is somewhat comparable to hugging a person. Participants have more favorable opinions about hugging robots after prolonged interaction with HuggieBot in all of our research studies.

hi

DOI Project Page [BibTex]

hi Block, A. E. HuggieBot: An Interactive Hugging Robot With Visual and Haptic Perception ETH Zürich, Zürich, August 2021, Department of Computer Science (phdthesis)

DOI Project Page [BibTex]

no image
Proceedings of the 1st Workshop on NLP for Positive Impact

Field, A., Prabhumoye, S., Sap, M., Jin, Z., Zhao, J., Brockett, C.

Association for Computational Linguistics, August 2021 (proceedings)

ei

link (url) [BibTex]

ei Field, A., Prabhumoye, S., Sap, M., Jin, Z., Zhao, J., Brockett, C. Proceedings of the 1st Workshop on NLP for Positive Impact Association for Computational Linguistics, August 2021 (proceedings)

link (url) [BibTex]

Chemically active micromotors
Chemically active micromotors

Yu, T.

University of Stuttgart, Stuttgart, July 2021 (phdthesis)

Abstract
Motion is a mark of living systems. It is realised by energy conversion to perform vital tasks and is thus of great importance for all living systems. One approach to achieve motion is by including active motion of micro/nano objects. Unlike in the fluid at the macro scale, active swimming cannot be achieved by reciprocal movements at the micro scale. Breaking symmetry at the micro scale thus becomes a critical issue. The challenge is that this often requires outside intervention to build systems that already show symmetry breaking. And another challenge is that there are few examples where active microscale motion can cause a macroscopic effect, or facilitate a useful application. In the first part of the thesis, the first challenge is addressed and a new route of spontaneous symmetry breaking is developed. Microscale motion in artificial chemical systems has thus far been realised in chemical motion. These are microparticles that are fabricated to possess two different halves, known as Janus particles. One half is catalytically active and drives the self-phoretics. The Janus micromotors are generally fabricated using fabrication techniques such as PVD, CVD. These techniques require deposition onto a surface, which limit the number of structures that can be fabricated. In this work, we show that two species of isotropic (symmetric) micro particles, one is a photocatalytically active particle TiO2, the other is a passive SiO2 particle can spontaneously form a dimer structure. Under UV illumination, a chemical gradient is generated around the photo active particles. The passive particle is attracted toward the highest chemical concentration of the reaction product towards the active particle. A dimer forms that starts to self-propel. The speed of the dimer can be controlled by adjusting the UV intensity. The mechanism of the dimer formation is examined and shown to be due to a diffusiophoretic interaction between the active and the passive particle. The interaction force and the propulsion of the dimer swimmers are examined. The role of salts, particle size and concentration are studied. An additional repulsion interaction is observed between two active particles. An optimal volumetric particle density of ≤ 2% is identified for dimer formation and the dimers remain active for > 20s. This thesis thereby demonstrates a self-assembly route where the chemical activity causes dimer formation and thus spontaneous symmetry breaking which does not require any physical fabrication steps. Most work thus far has studied the behaviour of individual chemical micromotors (Janus particles) at the micro scale. To induce a macroscopic effect and facilitate an application using individual micro/nano active particles requires cooperative effects of many "micromotors". Therefore, we developed a novel fabrication method which allows a large number of Janus structures to be assembled in an ordered manner. We fabricated an array of photoactive Janus micro structures on a surface by glancing angle deposition (GLAD) onto a photolithography patterned substrate. Illuminating the surface of Janus array structures with UV light initiates the water splitting reaction, which produces an osmotic flow around the micro structures. The osmotic flow at each structure is coupled with the flows generated by the neighbouring particles. The microscopic osmotic flow thereby results in a macroscopic fluid flow. By adjusting the spacing between single micro structures, an optimised pumping velocity is achieved with a micro pillar diameter of 2 μm and a spacing of ∼ 2 μm. We compared the pumping performance of the micro pillar array with other topological chemical structures, such as micro Janus bar arrays and 2D micro Janus disk arrays, and find that the 3D structure is essential to generate a chemical gradient on the surface. We believe that this is the first chemical micropump formed by chemically active Janus structures. The active pumping surface can provide a flow speed of up to 4 μm/s. This active surface consisting of micropillar arrays can be easily integrated in most microchannels and serve as an on-board micropump. A theoretical model and numerical simulations are presented to describe the microchannel pumping. The theory reproduces the experimentally measured flow profiles very well. We have thus established a new type of chemical pump, which can wirelessly pump fluid in a microchannel, and the pumping volume rate and flow profile can be modified simply by changing the nature and orientation of the self-pumping walls.

pf

DOI [BibTex]

pf Yu, T. Chemically active micromotors University of Stuttgart, Stuttgart, July 2021 (phdthesis)

DOI [BibTex]

no image
Röntgenmikroskopische Untersuchungen der Magnetisierungsdynamik in nanoskaligen magnonischen Wellenleiterstrukturen

Träger, N.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), June 2021 (phdthesis)

mms

[BibTex]

mms Träger, N. Röntgenmikroskopische Untersuchungen der Magnetisierungsdynamik in nanoskaligen magnonischen Wellenleiterstrukturen Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), June 2021 (phdthesis)

[BibTex]

Promoting metacognitive learning through systematic reflection
Promoting metacognitive learning through systematic reflection

Frederic Becker, , Lieder, F.

The first edition of Life Improvement Science Conference, June 2021 (poster)

Abstract
Human decision-making is sometimes systematically biased toward suboptimal decisions. For example, people often make short-sighted choices because they don't give enough weight to the long-term consequences of their actions. Previous studies showed that it is possible to overcome such biases by teaching people a more rational decision strategy through instruction, demonstrations, or practice with feedback. The benefits of these approaches tend to be limited to situations that are very similar to those used during the training. One way to overcome this limitation is to create general tools and strategies that people can use to improve their decision-making in any situation. Here we propose one such approach, namely directing people to systematically reflect on how they make their decisions. In systematic reflection, past experience is re-evaluated with the intention to learn. In this study, we investigate how reflection affects how people learn to plan and whether reflective learning can help people to discover more far-sighted planning strategies. In our experiment participants solve a series of 30 planning problems where the immediate rewards are smaller and therefore less important than long-term rewards. Building on Wolfbauer et al. (2020), the experimental group is guided by four reflection prompts asking the participant to describe their planning strategy, the strategy's performance, and his or her emotional response, insights, and intention to change their strategy. The control group practices planning without reflection prompts. Our pilot data suggest that systematic reflection helps people to more rapidly discover adaptive planning strategies. Our findings suggest that reflection is useful not only for helping people learn what to do in a specific situation but also for helping people learn how to think about what to do. In future work, we will compare the effects of different types of reflection on the subsequent changes in people's decision strategies. Developing apps that prompt people to reflect on their decisions may be a promising approach to accelerating cognitive growth and promoting lifelong learning.

re

[BibTex]

re Frederic Becker, , Lieder, F. Promoting metacognitive learning through systematic reflection The first edition of Life Improvement Science Conference, June 2021 (poster)

[BibTex]