Publications

In nature, many bacteria swim by rotating their helical flagella. A particularly promising class of artificial micro- and nano-robots mimic this propeller-like propulsion mechanism to move through fluids and tissues for applications in minimally-invasive medicine. Several fundamental challenges have to be overcome in order to build micro-machines that move similar to bacteria for in vivo applications. Here, we review recent advances of magnetically-powered micro-/nano-propellers. Four important aspects of the propellers – the geometrical shape, the fabrication method, the generation of magnetic fields for actuation, and the choice of biocompatible magnetic materials – are highlighted. First, the fundamental requirements are elucidated that arise due to hydrodynamics at low Reynolds (Re) number. We discuss the role that the propellers’ shape and symmetry play in realizing effective propulsion at low Re. Second, the additive nano-fabrication method Glancing Angle Deposition is discussed as a versatile technique to quickly grow large numbers of designer nano-helices. Third, systems to generate rotating magnetic fields via permanent magnets or electromagnetic coils are presented. And finally, the biocompatibility of the magnetic materials is discussed. Iron-platinum is highlighted due to its biocompatibility and its superior magnetic properties, which is promising for targeted delivery, minimally-invasive magnetic nano-devices and biomedical applications.

We introduce a simple but effective method for managing risk in zero-order trajectory optimization that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.

To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure in the environment were shown to perform well on many different tasks. In particular, some of them were applied to learn basic manipulation skills in compositional multi-object environments. However, these methods learn skills without taking the dependencies between objects into account. Thus, the learned skills are difficult to combine in realistic environments. We propose a novel self-supervised agent that estimates relations between environment components and uses them to independently control different parts of the environment state. In addition, the estimated relations between objects can be used to decompose a complex goal into a compatible sequence of subgoals. We show that, by using this framework, an agent can efficiently and automatically learn manipulation tasks in multi-object environments with different relations between objects.

Astronauts are at risk for pneumothorax, a medical condition where air accumulating between the chest wall and the lungs impedes breathing and can result in fatality. Treatments include needle decompression (ND) and chest tube insertion (tube thoracostomy, TT). Unfortunately, the literature reports very high failure rates for ND and high complication rates for TT– especially whenn performed urgently, infrequently, or by inexperienced operators. These statistics are problematic in the context of skill retention for physician astronauts on long-duration exploration-class missions, or for non-medical astronauts if the physician astronaut is the one in need of treatment. We propose reducing the medical risk for exploration-class missions by improving ND/TT outcomes using a robot-based paradigm that automates tool depth control. Our goal is to produce a robotic system that improves the safety of pneumothorax treatments regardless of operator skill and without the use of ground resources. This poster provides an overview of our team's work toward this goal, including robot instrumentation schemes, tool-tissue interaction characterization, and automated puncture detection.

Hand, the bearer of human productivity and intelligence, is receiving much attention due to the recent fever of 3D digital avatars. Among different hand morphable models, MANO has been widely used in various vision & graphics tasks. However, MANO disregards textures and accessories, which largely limits its power to synthesize photorealistic & lifestyle hand data. In this paper, we extend MANO with more Diverse Accessories and Rich Textures, namely DART. DART is comprised of 325 exquisite hand-crafted texture maps which vary in appearance and cover different kinds of blemishes, make-ups, and accessories. We also provide the Unity GUI which allows people to render hands with user-specific settings, e.g. pose, camera, background, lighting, and DART textures. In this way, we generate large-scale (800K), diverse, and high-fidelity hand images, paired with perfect-aligned 3D labels, called DARTset. Experiments demonstrate its superiority in generalization and diversity. As a great complement to existing datasets, DARTset could boost hand pose estimation & surface reconstruction tasks. DART and Unity software will be publicly available for research purposes.

It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsically motivated reinforcement learning (RL), sample-efficient exploration in object manipulation scenarios remains a significant challenge as most of the relevant information lies in the sparse agent-object and object-object interactions. In this paper, we propose to use structured world models to incorporate relational inductive biases in the control loop to achieve sample-efficient and interaction-rich exploration in compositional multi-object environments. By planning for future novelty inside structured world models, our method generates free-play behavior that starts to interact with objects early on and develops more complex behavior over time. Instead of using models only to compute intrinsic rewards, as commonly done, our method showcases that the self-reinforcing cycle between good models and good exploration also opens up another avenue: zero-shot generalization to downstream tasks via model-based planning. After the entirely intrinsic task-agnostic exploration phase, our method solves challenging downstream tasks such as stacking, flipping, pick & place, and throwing that generalizes to unseen numbers and arrangements of objects without any additional training.

A pumping system includes a conduit with an inlet region and an outlet region and a first pump coupled with the conduit between the inlet region and the outlet region. The first pump includes a first actuator chamber configured to house at least a first actuator, a first pump chamber aligned along a longitudinal axis of the conduit, wherein the first pump chamber is in fluid communication with the inlet region and the outlet region, and a first flexible diaphragm separating the first actuator chamber from the first pump chamber. Methods for operating the pumping system are also disclosed.

For robots to become fully dexterous, their hardware needs to provide rich sensory feedback. High-resolution haptic sensing similar to the human fingertip can enable robots to execute delicate manipulation tasks like picking up small objects, inserting a key into a lock, or handing a cup of coffee to a human. Many tactile sensors have emerged in recent years; one especially promising direction is vision-based tactile sensors due to their low cost, low wiring complexity and high-resolution sensing capabilities. In this work, we build on previous findings to create a soft fingertip-sized tactile sensor. It can sense normal and shear contact forces all around its 3D surface with an average prediction error of 0.05 N, and it localizes contact on its shell with an average prediction error of 0.5 mm. The software of this sensor uses a data-efficient machine-learning pipeline to run in real time on hardware with low computational power like a Raspberry Pi. It provides a maximum data frame rate of 60 Hz via USB.

Blimps are well suited to perform long-duration aerial tasks as they are energy efficient, relatively silent and safe. To address the blimp navigation and control task, in previous work we developed a hardware and software-in-the-loop framework and a PID-based controller for large blimps in the presence of wind disturbance. However, blimps have a deformable structure and their dynamics are inherently non-linear and time-delayed, making PID controllers difficult to tune. Thus, often resulting in large tracking errors. Moreover, the buoyancy of a blimp is constantly changing due to variations in ambient temperature and pressure. To address these issues, in this paper we present a learning-based framework based on deep residual reinforcement learning (DRRL), for the blimp control task. Within this framework, we first employ a PID controller to provide baseline performance. Subsequently, the DRRL agent learns to modify the PID decisions by interaction with the environment. We demonstrate in simulation that DRRL agent consistently improves the PID performance. Through rigorous simulation experiments, we show that the agent is robust to changes in wind speed and buoyancy. In real-world experiments, we demonstrate that the agent, trained only in simulation, is sufficiently robust to control an actual blimp in windy conditions. We openly provide the source code of our approach at https://github.com/robot-perception-group/AutonomousBlimpDRL .

Robots need lightweight legs for agile locomotion, and intrinsic series elastic compliance has proven to be a major ingredient for energy-efficient locomotion and robust locomotion control. Animals' anatomy and locomotion capabilities emphasize the importance of that lightweight legs and integrated, compact, series elastically actuated for distal leg joints. But unlike robots, animals achieve series elastic actuation by their muscle-tendon units. So far no designs are available that feature all characteristics of a perfect distal legged locomotion actuator; a low-weight and low-inertia design, with high mechanical efficiency, no stick and sliding friction, low mechanical complexity, high-power output while being easy to mount. Ideally, such an actuator can be controlled directly and without mechanical cross-coupling, for example remotely. With this goal in mind, we propose a low-friction, lightweight Series ELastic Diaphragm distal Actuator (SELDA) which meets many, although not all, of the above requirements. We develop, implement, and characterize a bioinspired robot leg that features a SELDA-actuated foot segment. We compare two leg configurations controlled by a central pattern generator that both feature agile forward hopping. By tuning SELDA's activation timing, we effectively adjust the robot's hopping height by 11\% and its forward velocity by 14\%, even with comparatively low power injection to the distal joint.

Legged locomotion in humans is governed by natural dynamics of the human body and neural control. One mechanism that is assumed to contribute to the high efficiency of human walking is the impulsive ankle push-off, which potentially powers the swing leg catapult. However, the mechanics of the human’s lower leg with its complex muscle-tendon units spanning over single and multiple joints is not yet understood. Legged robots allow testing the interaction between complex leg mechanics, control, and environment in real-world walking gait. We developed a 0.49 m tall, 2.2 kg anthropomorphic bipedal robot with Soleus and Gastrocnemius muscle-tendon units represented by linear springs, acting as mono- and biarticular elastic structures around the robot’s ankle and knee joints. We tested the influence of three Soleus and Gastrocnemius spring-tendon configurations on the ankle power curves, the coordination of the ankle and knee joint movements, the total cost of transport, and walking speed. We controlled the robot with a feed-forward central pattern generator, leading to walking speeds between 0.35 m/s and 0.57 m/s at 1.0 Hz locomotion frequency, at 0.35 m leg length. We found differences between all three configurations; the Soleus spring-tendon modulates the robot’s speed and energy efficiency likely by ankle power amplification, while the Gastrocnemius spring-tendon changes the movement coordination between knee and ankle joints during push-off.

Whenever we touch a surface with our fingers, we perceive distinct tactile properties that are based on the underlying dynamics of the interaction. However, little is known about how the brain aggregates the sensory information from these dynamics to form abstract representations of textures. Earlier studies in surface perception all used general surface descriptors measured in controlled conditions instead of considering the unique dynamics of specific interactions, reducing the comprehensiveness and interpretability of the results. Here, we present an interpretable modeling method that predicts the perceptual similarity of surfaces by comparing probability distributions of features calculated from short time windows of specific physical signals (finger motion, contact force, fingernail acceleration) elicited during unconstrained finger-surface interactions. The results show that our method can predict the similarity judgments of individual participants with a maximum Spearman's correlation of 0.7. Furthermore, we found evidence that different participants weight interaction features differently when judging surface similarity. Our findings provide new perspectives on human texture perception during active touch, and our approach could benefit haptic surface assessment, robotic tactile perception, and haptic rendering.

Fitting parametric models of human bodies, hands or faces to sparse input signals in an accurate, robust, and fast manner has the promise of significantly improving immersion in AR and VR scenarios. A common first step in systems that tackle these problems is to regress the parameters of the parametric model directly from the input data. This approach is fast, robust, and is a good starting point for an iterative minimization algorithm. The latter searches for the minimum of an energy function, typically composed of a data term and priors that encode our knowledge about the problem's structure. While this is undoubtedly a very successful recipe, priors are often hand defined heuristics and finding the right balance between the different terms to achieve high quality results is a non-trivial task. Furthermore, converting and optimizing these systems to run in a performant way requires custom implementations that demand significant time investments from both engineers and domain experts. In this work, we build upon recent advances in learned optimization and propose an update rule inspired by the classic Levenberg-Marquardt algorithm. We show the effectiveness of the proposed neural optimizer on three problems, 3D body estimation from a head-mounted device, 3D body estimation from sparse 2D keypoints and face surface estimation 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.

Combining off-the-shelf components with 3D- printing, the Wheelbot is a symmetric reaction wheel unicycle that can jump onto its wheels from any initial position. With non-holonomic and under-actuated dynamics, as well as two coupled unstable degrees of freedom, the Wheelbot provides a challenging platform for nonlinear and data-driven control research. This letter presents the Wheelbot's mechanical and electrical design, its estimation and control algorithms, as well as experiments demonstrating both self-erection and disturbance rejection while balancing.

Face reconstruction and tracking is a building block of numerous applications in AR/VR, human-machine interaction, as well as medical applications. Most of these applications rely on a metrically correct prediction of the shape, especially, when the reconstructed subject is put into a metrical context (i.e., when there is a reference object of known size). A metrical reconstruction is also needed for any application that measures distances and dimensions of the subject (e.g., to virtually fit a glasses frame). State-of-the-art methods for face reconstruction from a single image are trained on large 2D image datasets in a self-supervised fashion. However, due to the nature of a perspective projection they are not able to reconstruct the actual face dimensions, and even predicting the average human face outperforms some of these methods in a metrical sense. To learn the actual shape of a face, we argue for a supervised training scheme. Since there exists no large-scale 3D dataset for this task, we annotated and unified small- and medium-scale databases. The resulting unified dataset is still a medium-scale dataset with more than 2k identities and training purely on it would lead to overfitting. To this end, we take advantage of a face recognition network pretrained on a large-scale 2D image dataset, which provides distinct features for different faces and is robust to expression, illumination, and camera changes. Using these features, we train our face shape estimator in a supervised fashion, inheriting the robustness and generalization of the face recognition network. Our method, which we call MICA (MetrIC fAce), outperforms the state-of-the-art reconstruction methods by a large margin, both on current non-metric benchmarks as well as on our metric benchmarks (15\%\/ and 24\%\/ lower average error on NoW, respectively). Project website: \url{https://zielon.github.io/mica/}.

Virtual facial avatars will play an increasingly important role in immersive communication, games and the metaverse, and it is therefore critical that they be inclusive. This requires accurate recovery of the albedo, regardless of age, sex, or ethnicity. While significant progress has been made on estimating 3D facial geometry, appearance estimation has received less attention. The task is fundamentally ambiguous because the observed color is a function of albedo and lighting, both of which are unknown. We find that current methods are biased towards light skin tones due to (1) strongly biased priors that prefer lighter pigmentation and (2) algorithmic solutions that disregard the light/albedo ambiguity. To address this, we propose a new evaluation dataset (FAIR) and an algorithm (TRUST) to improve albedo estimation and, hence, fairness. Specifically, we create the first facial albedo evaluation benchmark where subjects are balanced in terms of skin color, and measure accuracy using the Individual Typology Angle (ITA) metric. We then address the light/albedo ambiguity by building on a key observation: the image of the full scene –as opposed to a cropped image of the face– contains important information about lighting that can be used for disambiguation. TRUST regresses facial albedo by conditioning on both the face region and a global illumination signal obtained from the scene image. Our experimental results show significant improvement compared to state- of-the-art methods on albedo estimation, both in terms of accuracy and fairness. The evaluation benchmark and code are available for research purposes at https://trust.is.tue.mpg.de.

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.

Statistical 3D shape models of the head, hands, and fullbody are widely used in computer vision and graphics. Despite their wide use, we show that existing models of the head and hands fail to capture the full range of motion for these parts. Moreover, existing work largely ignores the feet, which are crucial for modeling human movement and have applications in biomechanics, animation, and the footwear industry. The problem is that previous body part models are trained using 3D scans that are isolated to the individual parts. Such data does not capture the full range of motion for such parts, e.g. the motion of head relative to the neck. Our observation is that full-body scans provide important in- formation about the motion of the body parts. Consequently, we propose a new learning scheme that jointly trains a full-body model and specific part models using a federated dataset of full-body and body-part scans. Specifically, we train an expressive human body model called SUPR (Sparse Unified Part-Based Representation), where each joint strictly influences a sparse set of model vertices. The factorized representation enables separating SUPR into an entire suite of body part models: an expressive head (SUPR-Head), an articulated hand (SUPR-Hand), and a novel foot (SUPR-Foot). Note that feet have received little attention and existing 3D body models have highly under-actuated feet. Using novel 4D scans of feet, we train a model with an extended kinematic tree that captures the range of motion of the toes. Additionally, feet de- form due to ground contact. To model this, we include a novel non-linear deformation function that predicts foot deformation conditioned on the foot pose, shape, and ground contact. We train SUPR on an unprecedented number of scans: 1.2 million body, head, hand and foot scans. We quantitatively compare SUPR and the separate body parts to existing expressive human body models and body-part models and find that our suite of models generalizes better and captures the body parts’ full range of motion. SUPR is publicly available for research purposes.

We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data, in combination with a text encoder that produces distribution parameters compatible with the VAE latent space. We show the TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions. We evaluate our approach on the KIT Motion-Language benchmark and, despite being relatively straightforward, demonstrate significant improvements over the state of the art. Code and models are available on our webpage.

Gender balance has been a declared goal in business and society for decades as gender diversity leads to more equality and better decision-making, enhances financial performance of organizations, and fosters creativity and innovation. Although there is a steady upward trend in the number of women actively participating in the workplace, there is still a dearth of women in top leadership positions. This motivates a closer look at the reasons why this happens. Stigmatization – a social process of disapproval based on stereotypes or particular distinguishing characteristics of individuals (e.g. gender) – has been recognized as one of the primary explanations for the barriers to career advancement of women. This chapter aims to address workplace inequality by analysing different sources of stigma women face in the workplace. Previous research has mostly focused on visible sources of stigma, such as gender or race/ethnicity. We propose to go beyond visible sources of stigma and expand the focus to other physical (e.g. physical appearance, age, childbearing age), emotional (e.g. mental health) and societal (e.g. flexibility) sources of stigma. We are especially interested in the consequences of stigma for women in the workplace. Stigmatization of women is a multi-level process, so this chapter focuses on the antecedents (sources of stigma) and outcomes (consequences of stigma) for women at the individual level, organizational level and the societal level. The proposed chapter will make contributions to the areas of management, diversity and gender studies.

Setting the right goals and prioritizing them might be the most crucial and the most challenging type of decisions people make for themselves, their teams, and their organizations. In this article, we explore whether it might be possible to leverage artificial intelligence (AI) to help people set better goals and which potential problems might arise from such applications. We devised the first prototype of an AI-powered digital goal-setting assistant and a rigorous empirical paradigm for assessing the quality of AI-generated goal suggestions. Our empirical paradigm compares the AI-generated goal suggestions against randomly-generated goal suggestions and unassisted goal-setting on a battery of self-report measures of important goal characteristics, motivation, and usability in a large-scale repeated-measures online experiment. The results of an online experiment with 259 participants revealed that our intuitively compelling goal suggestion algorithm was actively harmful to the quality of the people's goals and their motivation to pursue them. These surprising findings highlight three crucial problems to be tackled by future work on leveraging AI to help people set better goals: i) aligning the objective function of the AI algorithms with the design goals, ii) helping people quantify how valuable different goals are to them, and iii) preserving the user's sense of autonomy.