Institute Homepage
Institute Homepage DE Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Haptic Intelligence Miscellaneous OCRA: An Optimization-Based Customizable Retargeting Algorithm for Teleoperation Mohan, M., Kuchenbecker, K. J. Workshop paper (3 pages) presented at the ICRA Workshop Toward Robot Avatars, London, UK, May 2023 (Published)
This paper presents a real-time optimization-based algorithm for mapping motion between two kinematically dissimilar serial linkages, such as a human arm and a robot arm. OCRA can be customized based on the target task to weight end-effector orientation versus the configuration of the central line of the arm, which we call the skeleton. A video-watching study (N=70) demonstrated that when this algorithm considers both the hand orientation and the arm skeleton, it creates robot arm motions that users perceive to be highly similar to those of the human operator, indicating OCRA would be suitable for telerobotics and telepresence through avatars.
URL BibTeX
Perceiving Systems Article Fast-SNARF: A Fast Deformer for Articulated Neural Fields Chen, X., Jiang, T., Song, J., Rietmann, M., Geiger, A., Black, M. J., Hilliges, O. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 1-15, April 2023 (Published)
Neural fields have revolutionized the area of 3D reconstruction and novel view synthesis of rigid scenes. A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space. We propose a new articulation module for neural fields, Fast-SNARF, which finds accurate correspondences between canonical space and posed space via iterative root finding. Fast-SNARF is a drop-in replacement in functionality to our previous work, SNARF, while significantly improving its computational efficiency. We contribute several algorithmic and implementation improvements over SNARF, yielding a speed-up of 150× . These improvements include voxel-based correspondence search, pre-computing the linear blend skinning function, and an efficient software implementation with CUDA kernels. Fast-SNARF enables efficient and simultaneous optimization of shape and skinning weights given deformed observations without correspondences (e.g. 3D meshes). Because learning of deformation maps is a crucial component in many 3D human avatar methods and since Fast-SNARF provides a computationally efficient solution, we believe that this work represents a significant step towards the practical creation of 3D virtual humans.
pdf publisher site code DOI URL BibTeX
Robotic Materials Patent High Strain Peano Hydraulically Amplified Self-healing Electrostatic (HASEL) Transducers Keplinger, C. M., Wang, X., Mitchell, S. K. (US Patent 11635094), April 2023
High strain hydraulically amplified self-healing electrostatic transducers having increased maximum theoretical and practical strains are disclosed. In particular, the actuators include electrode configurations having a zipping front created by the attraction of the electrodes that is configured orthogonally to a strain axis along which the actuators. This configuration produces increased strains. In turn, various form factors for the actuator configuration are presented including an artificial circular muscle and a strain amplifying pulley system. Other actuator configurations are contemplated that include independent and opposed electrode pairs to create cyclic activation, hybrid electrode configurations, and use of strain limiting layers for controlled deflection of the actuator.
URL BibTeX
Empirical Inference Article Uncovering the Organization of Neural Circuits with Generalized Phase Locking Analysis Safavi, S., Panagiotaropoulos, T. I., Kapoor, V., Ramirez-Villegas, J. F., Logothetis, N., Besserve, M. PLOS Computational Biology, 19(4):45, Public Library of Science, April 2023 (Published) bioRxiv DOI BibTeX
Robotic Materials Physical Intelligence Bioinspired Autonomous Miniature Robots Article A Versatile Jellyfish-Like Robotic Platform for Effective Underwater Propulsion and Manipulation Wang, T., Joo, H., Song, S., Hu, W., Keplinger, C., Sitti, M. Science Advances, 9(15), American Association for the Advancement of Science, April 2023, Tianlu Wang and Hyeong-Joon Joo contributed equally to this work. (Published)
Underwater devices are critical for environmental applications. However, existing prototypes typically use bulky, noisy actuators and limited configurations. Consequently, they struggle to ensure noise-free and gentle interactions with underwater species when realizing practical functions. Therefore, we developed a jellyfish-like robotic platform enabled by a synergy of electrohydraulic actuators and a hybrid structure of rigid and soft components. Our 16-cm-diameter noise-free prototype could control the fluid flow to propel while manipulating objects to be kept beneath its body without physical contact, thereby enabling safer interactions. Its against-gravity speed was up to 6.1 cm/s, substantially quicker than other examples in literature, while only requiring a low input power of around 100 mW. Moreover, using the platform, we demonstrated contact-based object manipulation, fluidic mixing, shape adaptation, steering, wireless swimming, and cooperation of two to three robots. This study introduces a versatile jellyfish-like robotic platform with a wide range of functions for diverse applications.
YouTube video DOI URL BibTeX
Empirical Inference Article Adapting to noise distribution shifts in flow-based gravitational-wave inference Wildberger, J., Dax, M., Green, S. R., Gair, J., Pürrer, M., Macke, J. H., Buonanno, A., Schölkopf, B. Physical Review D, 107(8), April 2023 (Published) DOI BibTeX
Empirical Inference Conference Paper BaCaDI: Bayesian Causal Discovery with Unknown Interventions Hägele, A., Rothfuss, J., Lorch, L., Somnath, V. R., Schölkopf, B., Krause, A. Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) , 206:1411-1436, Proceedings of Machine Learning Research, (Editors: Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Conference Paper Backtracking Counterfactuals von Kügelgen, J., Mohamed, A., Beckers, S. Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), 213:177-196, Proceedings of Machine Learning Research, (Editors: van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Conference Paper Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning Liu, Y., Alahi, A., Russell, C., Horn, M., Zietlow, D., Schölkopf, B., Locatello, F. Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), 213:553-573, Proceedings of Machine Learning Research, (Editors: van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Conference Paper Dataflow graphs as complete causal graphs Paleyes, A., Guo, S., Schölkopf, B., Lawrence, N. D. 2nd International Conference on AI Engineering - Software Engineering for AI (CAIN), 7-12, IEEE, April 2023 (Published) arXiv DOI BibTeX
Haptic Intelligence Article Effects of Automated Skill Assessment on Robotic Surgery Training Brown, J. D., Kuchenbecker, K. J. The International Journal of Medical Robotics and Computer Assisted Surgery, 19(2):e2492, April 2023 (Published)
Background: Several automated skill-assessment approaches have been proposed for robotic surgery, but their utility is not well understood. This article investigates the effects of one machine-learning-based skill-assessment approach on psychomotor skill development in robotic surgery training. Methods: N=29 trainees (medical students and residents) with no robotic surgery experience performed five trials of inanimate peg transfer with an Intuitive Surgical da Vinci Standard robot. Half of the participants received no post-trial feedback. The other half received automatically calculated scores from five Global Evaluative Assessment of Robotic Skill (GEARS) domains post-trial. Results: There were no significant differences between the groups regarding overall improvement or skill improvement rate. However, participants who received post-trial feedback rated their overall performance improvement significantly lower than participants who did not receive feedback. Conclusions: These findings indicate that automated skill evaluation systems might improve trainee selfawareness but not accelerate early-stage psychomotor skill development in robotic surgery training.
DOI BibTeX
Haptic Intelligence Article Haptify: A Measurement-Based Benchmarking System for Grounded Force-Feedback Devices Fazlollahi, F., Kuchenbecker, K. J. IEEE Transactions on Robotics, 39(2):1622-1636, April 2023 (Published)
Grounded force-feedback (GFF) devices are an established and diverse class of haptic technology based on robotic arms. However, the number of designs and how they are specified make comparing devices difficult. We thus present Haptify, a benchmarking system that can thoroughly, fairly, and noninvasively evaluate GFF haptic devices. The user holds the instrumented device end-effector and moves it through a series of passive and active experiments. Haptify records the interaction between the hand, device, and ground with a seven-camera optical motion-capture system, a 60-cm-square custom force plate, and a customized sensing end-effector. We demonstrate six key ways to assess GFF device performance: workspace shape, global free-space forces, global free-space vibrations, local dynamic forces and torques, frictionless surface rendering, and stiffness rendering. We then use Haptify to benchmark two commercial haptic devices. With a smaller workspace than the 3D Systems Touch, the more expensive Touch X outputs smaller free-space forces and vibrations, smaller and more predictable dynamic forces and torques, and higher-quality renderings of a frictionless surface and high stiffness.
DOI BibTeX
Empirical Inference Article Instrumental variable regression via kernel maximum moment loss Zhang, R., Imaizumi, M., Schölkopf, B., Muandet, K. Journal of Causal Inference, 11(1), April 2023 (Published) DOI BibTeX
Empirical Inference Conference Paper Iterative Teaching by Data Hallucination Qiu, Z., Liu, W., Xiao, T., Liu, Z., Bhatt, U., Luo, Y., Weller, A., Schölkopf, B. Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) , 206:9892-9913, Proceedings of Machine Learning Research, (Editors: Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Robust Machine Learning Article Jacobian-based Causal Discovery with Nonlinear ICA Reizinger, P., Sharma, Y., Bethge, M., Schölkopf, B., Huszár, F., Brendel, W. Transactions on Machine Learning Research, April 2023 (Published) URL BibTeX
Perceiving Systems Patent Method and systems for labelling motion-captured points J., B. M., Ghorbani, N. (US Patent App.~17/949,087), April 2023 (Published)
Computer-implemented methods are provided for labelling motion-captured points that correspond to markers on an object. The methods include obtaining the motion-captured points, processing a representation of the motion-captured points in a trained self-attention unit to obtain label scores for the motion-captured points, and assigning labels based on the label scores.
BibTeX
Empirical Inference Article Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference Dax, M., Green, S. R., Gair, J., Pürrer, M., Wildberger, J., Macke, J. H., Buonanno, A., Schölkopf, B. Physical Review Letters, 130(17), April 2023 (Published) DOI BibTeX
Empirical Inference Conference Paper Nonparametric Indirect Active Learning Singh, S. Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) , 206:2515-2541, Proceedings of Machine Learning Research, (Editors: Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Conference Paper On the Interventional Kullback-Leibler Divergence Wildberger, J. B., Guo, S., Bhattacharyya, A., Schölkopf, B. Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), 213:328-349, Proceedings of Machine Learning Research, (Editors: van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik), PMLR, April 2023 (Published) URL BibTeX
Empirical Inference Article The ENCODE Imputation Challenge: a critical assessment of methods for cross-cell type imputation of epigenomic profiles Schreiber*, J., Boix*, C., Lee, J. W., Li, H., Guan, Y., Chang, C., Chang, J., Hawkins-Hooker, A., Schölkopf, B., Schweikert, G., Carulla, M. R., Canakoglu, A., Guzzo, F., Nanni, L., Masseroli, M., Carman, M. J., Pinoli, P., Hong, C., Yip, K. Y., Spence, J. P., et al. Genome Biology, 24, April 2023, *co‑first authors (Published) DOI BibTeX
Empirical Inference Conference Paper Unsupervised Object Learning via Common Fate Tangemann, M., Schneider, S., von Kügelgen, J., Locatello, F., Gehler, P., Brox, T., Kümmerer, M., Bethge, M., Schölkopf, B. Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), 213:281-327, Proceedings of Machine Learning Research, (Editors: van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik), PMLR, April 2023 (Published) arXiv URL BibTeX
Haptic Intelligence Miscellaneous Wearable Biofeedback for Knee Joint Health Rokhmanova, N. Extended abstract (5 pages) presented at the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI) Doctoral Consortium, Hamburg, Germany, April 2023 (Published)
The human body has the tremendous capacity to learn a new way of walking that reduces its risk of musculoskeletal disease progression. Wearable haptic biofeedback has been used to guide gait retraining in patients with knee osteoarthritis, enabling reductions in pain and improvement in function. However, this promising therapy is not yet a part of standard clinical practice. Here, I propose a two-pronged approach to improving the design and deployment of biofeedback for gait retraining. The first section concerns prescription, with the aim of providing clinicians with an interpretable model of gait retraining outcome in order to best guide their treatment decisions. The second section concerns learning, by examining how internal physiological state and external environmental factors influence the process of learning a therapeutic gait. This work aims to address the challenges keeping a highly promising intervention from being widely used to maintain pain-free mobility throughout the lifespan.
DOI BibTeX
Physical Intelligence Article Hygroscopic Materials Guo, S., De Wolf, S., Sitti, M., Serre, C., Tan, S. C. Advanced Materials, 36(12), Wiley, Weinheim, March 2023 (Published) DOI BibTeX
Dynamic Locomotion Article Muscle prestimulation tunes velocity preflex in simulated perturbed hopping Izzi, F., Mo, A., Schmitt, S., Badri-Spröwitz, A., Häufle, D. Scientific Reports, 13:4559, Nature Publishing Group, March 2023 (Published)
Muscle fibres possess unique visco-elastic properties, which generate a stabilising zero-delay response to unexpected perturbations. This instantaneous response—termed “preflex”—mitigates neuro-transmission delays, which are hazardous during fast locomotion due to the short stance duration. While the elastic contribution to preflexes has been studied extensively, the function of fibre viscosity due to the force–velocity relation remains unknown. In this study, we present a novel approach to isolate and quantify the preflex force produced by the force–velocity relation in musculo-skeletal computer simulations. We used our approach to analyse the muscle response to ground-level perturbations in simulated vertical hopping. Our analysis focused on the preflex-phase—the first 30 ms after impact—where neuronal delays render a controlled response impossible. We found that muscle force at impact and dissipated energy increase with perturbation height, helping reject the perturbations. However, the muscle fibres reject only 15\% of step-down perturbation energy with constant stimulation. An open-loop rising stimulation, observed in locomotion experiments, amplified the regulatory effects of the muscle fibre’s force–velocity relation, resulting in 68\% perturbation energy rejection. We conclude that open-loop neuronal tuning of muscle activity around impact allows for adequate feed-forward tuning of muscle fibre viscous capacity, facilitating energy adjustment to unexpected ground-level perturbations.
DOI URL BibTeX
Organizational Leadership and Diversity Article The Organizational Psychology of Gig Work: An Integrative Conceptual Review Cropanzano, R., Keplinger, K., Lambert, B. K., Caza, B., Ashford, S. J. Journal of Applied Psychology, 108(3):492-519, March 2023 (Published) Psychology of Gig Work Psychology of Gig Work DOI BibTeX
Autonomous Vision Article KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D Liao, Y., Xie, J., Geiger, A. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3292-3310, IEEE, March 2023 (Published) DOI BibTeX
Haptic Intelligence Miscellaneous A Lasting Impact: Using Second-Order Dynamics to Customize the Continuous Emotional Expression of a Social Robot Burns, R. B., Kuchenbecker, K. J. Workshop paper (5 pages) presented at the HRI Workshop on Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI), Stockholm, Sweden, March 2023 (Published)
Robots are increasingly being developed as assistants for household, education, therapy, and care settings. Such robots need social skills to interact warmly and effectively with their users, as well as adaptive behavior to maintain user interest. While complex emotion models exist for chat bots and virtual agents, autonomous physical robots often lack a dynamic internal affective state, instead displaying brief, fixed emotion routines to promote or discourage specific user actions. We address this need by creating a mathematical emotion model that can easily be implemented in a social robot to enable it to react intelligently to external stimuli. The robot's affective state is modeled as a second-order dynamic system analogous to a mass connected to ground by a parallel spring and damper. The present position of this imaginary mass shows the robot's valence, which we visualize as the height of its displayed smile (positive) or frown (negative). Associating positive and negative stimuli with appropriately oriented and sized force pulses applied to the mass enables the robot to respond to social touch and other inputs with a valence that evolves over a longer timescale, capturing essential features of approach-avoidance theory. By adjusting the parameters of this emotion model, one can modify three main aspects of the robot's personality, which we term disposition, stoicism, and calmness.
URL BibTeX
Rationality Enhancement Article A gamified mobile app that helps people develop the metacognitive skills to cope with stressful situations and difficult emotions: Formative assessment of the InsightApp Amo, V., Prentice, M., Lieder, F. JMIR Formative Research, March 2023 (Published)
Ecological Momentary interventions (EMIs) open new and exciting possibilities for conducting research and delivering mental health interventions in real-life environments via smartphones. This makes designing psychotherapeutic EMIs a promising step towards cost-effective, scalable digital solutions for improving mental health and understanding the effects and mechanisms of psychotherapy.
DOI URL BibTeX
Empirical Inference Master Thesis Intrinsic complexity and mechanisms of expressivity of cortical neurons Spieler, A. M. University of Tübingen, Germany, March 2023 (Published) BibTeX
Empirical Inference Optics and Sensing Laboratory Micro, Nano, and Molecular Systems Article Multiplane Diffractive Acoustic Networks Athanassiadis, A. G., Schlieder, L., Melde, K., Volchkov, V., Schölkopf, B., Fischer, P. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 70(5):441-448, IEEE, March 2023 (Published) DOI BibTeX
Empirical Inference Article Proactive Contact Tracing Gupta, P., Maharaj, T., Weiss, M., Rahaman, N., Alsdurf, H., Minoyan, N., Harnois-Leblanc, S., Merckx, J., Williams, A., Schmidt, V., St-Charles, P., Patel, A., Zhang, Y., Buckeridge, D. L., Pal, C., Schölkopf, B., Bengio, Y. PLOS Digital Health, 2(3):1-19, March 2023 (Published) DOI BibTeX
Empirical Inference Article Self-supervised contrastive learning with random walks for medical image segmentation with limited annotations Fischer, M., Hepp, T., Gatidis, S., Yang, B. Computerized Medical Imaging and Graphics, 104, Elsevier, Amsterdam, March 2023 (Published) DOI BibTeX
Rationality Enhancement Article Systematic metacognitive reflection helps people discover far-sighted decision strategies: a process-tracing experiment Becker, F., Wirzberger, M., Pammer-Schindler, V., Srinivas, S., Lieder, F. Judgment and Decision Making, March 2023 (Published) DOI BibTeX
Empirical Inference Article Compact holographic sound fields enable rapid one-step assembly of matter in 3D Melde, K., Kremer, H., Shi, M., Seneca, S., Frey, C., Platzman, I., Degel, C., Schmitt, D., Schölkopf, B., Fischer, P. Science Advances, 9(6), AAAS, Washington, DC, February 2023 (Published) DOI URL BibTeX
Perceiving Systems Ph.D. Thesis Reconstruction and Synthesis of Human-Scene Interaction Hassan, M. University of Tübingen, February 2023 (Published)
In this thesis, we argue that the 3D scene is vital for understanding, reconstructing, and synthesizing human motion. We present several approaches which take the scene into consideration in reconstructing and synthesizing Human-Scene Interaction (HSI). We first observe that state-of-the-art pose estimation methods ignore the 3D scene and hence reconstruct poses that are inconsistent with the scene. We address this by proposing a pose estimation method that takes the 3D scene explicitly into account. We call our method PROX for Proximal Relationships with Object eXclusion. We leverage the data generated using PROX and build a method to automatically place 3D scans of people with clothing in scenes. The core novelty of our method is encoding the proximal relationships between the human and the scene in a novel HSI model, called POSA for Pose with prOximitieS and contActs. POSA is limited to static HSI, however. We propose a real-time method for synthesizing dynamic HSI, which we call SAMP for Scene-Aware Motion Prediction. SAMP enables virtual humans to navigate cluttered indoor scenes and naturally interact with objects. Data-driven kinematic models, like SAMP, can produce high-quality motion when applied in environments similar to those shown in the dataset. However, when applied to new scenarios, kinematic models can struggle to generate realistic behaviors that respect scene constraints. In contrast, we present InterPhys which uses adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a physical and life-like manner.
download pdf DOI BibTeX
Empirical Inference Article Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets Choe, J., Oh, S. J., Chun, S., Lee, S., Akata, Z., Shim, H. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2):1732-1748, IEEE, New York, NY, February 2023 (Published) DOI URL BibTeX
Learning and Dynamical Systems Empirical Inference Master Thesis Causal Effect Estimation by Combining Observational and Interventional Data Kladny, K. ETH Zurich, Switzerland, February 2023 (Published) BibTeX
Materials Article Dry Synthesis of Pure and Ultrathin Nanoporous Metallic Films Kwon, H., Barad, H., Olaya, A. R. S., Alarcón-Correa, M., Hahn, K., Richter, G., Wittstock, G., Fischer, P. ACS Applied Materials and Interfaces, 15(4):5620-5627, February 2023 (Published) DOI BibTeX
Empirical Inference Article GRASP: Scalable Graph Alignment by Spectral Corresponding Functions Hermanns, J., Skitsas, K., Tsitsulin, A., Munkhoeva, M., Kyster, A., Nielsen, S., Bronstein, A. M., Mottin, D., Karras, P. ACM Transactions on Knowledge Discovery from Data, 17(4), February 2023 (Published) DOI BibTeX
Social Foundations of Computation Conference Paper Human-Guided Fair Classification for Natural Language Processing Dorner, F. E., Peychev, M., Konstantinov, N., Goel, N., Ash, E., Vechev, M. In The Eleventh International Conference on Learning Representations (ICLR 2023), February 2023 (Published)
Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes such as gender or ethnicity. However, there is a gap between human intuition about these perturbations and the formal similarity specifications capturing them. While existing research has started to address this gap, current methods are based on hardcoded word replacements, resulting in specifications with limited expressivity or ones that fail to fully align with human intuition (e.g., in cases of asymmetric counterfactuals). This work proposes novel methods for bridging this gap by discovering expressive and intuitive individual fairness specifications. We show how to leverage unsupervised style transfer and GPT-3's zero-shot capabilities to automatically generate expressive candidate pairs of semantically similar sentences that differ along sensitive attributes. We then validate the generated pairs via an extensive crowdsourcing study, which confirms that a lot of these pairs align with human intuition about fairness in the context of toxicity classification. Finally, we show how limited amounts of human feedback can be leveraged to learn a similarity specification that can be used to train downstream fairness-aware models.
arXiv URL BibTeX
Physics for Inference and Optimization Article Immiscible Color Flows in Optimal Transport Networks for Image Classification Lonardi, A., Baptista, D., De Bacco, C. Frontiers Physics, 11, February 2023 (Published) Preprint Code DOI BibTeX
Physics for Inference and Optimization Article Infrastructure adaptation and emergence of loops in network routing with time-dependent loads Lonardi, A., Facca, E., Putti, M., De Bacco, C. Physical Review E, 107(2), February 2023 (Published) Code Preprint DOI URL BibTeX
Dynamic Locomotion Article Slack-based tunable damping leads to a trade-off between robustness and efficiency in legged locomotion Mo, A., Izzi, F., Gönen, E. C., Häufle, D., Badri-Spröwitz, A. Scientific Reports, 13:3290, Nature Publishing Group, February 2023 (Published)
Animals run robustly in diverse terrain. This locomotion robustness is puzzling because axon conduction velocity is limited to a few ten meters per second. If reflex loops deliver sensory information with significant delays, one would expect a destabilizing effect on sensorimotor control. Hence, an alternative explanation describes a hierarchical structure of low-level adaptive mechanics and high-level sensorimotor control to help mitigate the effects of transmission delays. Motivated by the concept of an adaptive mechanism triggering an immediate response, we developed a tunable physical damper system. Our mechanism combines a tendon with adjustable slackness connected to a physical damper. The slack damper allows adjustment of damping force, onset timing, effective stroke, and energy dissipation. We characterize the slack damper mechanism mounted to a legged robot controlled in open-loop mode. The robot hops vertically and planar over varying terrains and perturbations. During forward hopping, slack-based damping improves faster perturbation recovery (up to 170\%) at higher energetic cost (27\%). The tunable slack mechanism auto-engages the damper during perturbations, leading to a perturbation-trigger damping, improving robustness at minimum energetic cost. With the results from the slack damper mechanism, we propose a new functional interpretation of animals' redundant muscle tendons as tunable dampers.
arxiv Video Journal URL CAD and data DOI URL BibTeX
Empirical Inference Article SphereFace Revived: Unifying Hyperspherical Face Recognition Liu, W., Wen, Y., Raj, B., Singh, R., Weller, A. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2):2458-2474, February 2023 (Published) DOI BibTeX
Haptic Intelligence Article The S-BAN: Insights into the Perception of Shape-Changing Haptic Interfaces via Virtual Pedestrian Navigation Spiers, A. J., Young, E., Kuchenbecker, K. J. ACM Transactions on Computer-Human Interaction, 30(1):1-31, February 2023 (Published)
Screen-based pedestrian navigation assistance can be distracting or inaccessible to users. Shape-changing haptic interfaces can overcome these concerns. The S-BAN is a new handheld haptic interface that utilizes a parallel kinematic structure to deliver 2-DOF spatial information over a continuous workspace, with a form factor suited to integration with other travel aids. The ability to pivot, extend and retract its body opens possibilities and questions around spatial data representation. We present a static study to understand user perception of absolute pose and relative motion for two spatial mappings, showing highest sensitivity to relative motions in the cardinal directions. We then present an embodied navigation experiment in virtual reality. User motion efficiency when guided by the S-BAN was statistically equivalent to using a vision-based tool (a smartphone proxy). Although haptic trials were slower than visual trials, participants' heads were more elevated with the S-BAN, allowing greater visual focus on the environment.
DOI BibTeX
Empirical Inference Conference Paper Towards Empirical Process Theory for Vector-Valued Functions: Metric Entropy of Smooth Function Classes Park, J., Muandet, K. Proceedings of the 34th International Conference on Algorithmic Learning Theory (ALT), 201:1216-1260, Proceedings of Machine Learning Research, (Editors: Agrawal, Shipra and Orabona, Francesco), PMLR, February 2023 (Published) URL BibTeX
Empirical Inference Master Thesis Towards Generative Machine Teaching Qui, Z. Technical University of Munich, Germany, February 2023 (Published) BibTeX
Empirical Inference Article ViViT: Curvature Access Through The Generalized Gauss-Newton’s Low-Rank Structure Dangel*, F., Tatzel*, L., Hennig, P. Transactions on Machine Learning Research, February 2023, *equal contribution (Published) URL BibTeX
Social Foundations of Computation Conference Paper What Makes ImageNet Look Unlike LAION Shirali, A., Hardt, M. The Twelfth International Conference on Learning Representations (ICLR 2024), February 2023 (Submitted)
ImageNet was famously created from Flickr image search results. What if we recreated ImageNet instead by searching the massive LAION dataset based on image captions alone? In this work, we carry out this counterfactual investigation. We find that the resulting ImageNet recreation, which we call LAIONet, looks distinctly unlike the original. Specifically, the intra-class similarity of images in the original ImageNet is dramatically higher than it is for LAIONet. Consequently, models trained on ImageNet perform significantly worse on LAIONet. We propose a rigorous explanation for the discrepancy in terms of a subtle, yet important, difference in two plausible causal data-generating processes for the respective datasets, that we support with systematic experimentation. In a nutshell, searching based on an image caption alone creates an information bottleneck that mitigates the selection bias otherwise present in image-based filtering. Our explanation formalizes a long-held intuition in the community that ImageNet images are stereotypical, unnatural, and overly simple representations of the class category. At the same time, it provides a simple and actionable takeaway for future dataset creation efforts.
arXiv URL BibTeX
Perceiving Systems MPI Year Book Virtuelle Körper ermöglichen Blick in eine gesunde Zukunft / Virtual bodies provide a glimpse into a healthy future Behrens, S. C., Tesch, J., Sun, P. J. B., Starke, S., Black, M. J., Schneider, H., Pruccoli, J., Zipfel, S., Giel, K. January 2023 (Published)
Menschen mit Magersucht leben in ständiger Angst, zuzunehmen. Betroffene tun oft alles dafür, um keinesfalls mehr zu wiegen – selbst wenn sie bereits unter den gesundheitlichen Folgen leiden oder im Alltag eingeschränkt sind. Forschende des Max-Planck-Instituts für Intelligente Systeme und des Universitätsklinikums Tübingen haben ein Virtual-Reality-Tool entwickelt, mit dem sich eine Gewichtszunahme simulieren lässt. Die Forschungsergebnisse deuten darauf hin, dass die wiederholte Auseinandersetzung mit virtuellem gesundem Gewicht Personen mit Magersucht hilft, ihre Angst vor einer Gewichtzunahme zu reduzieren. ENGLISH: People with anorexia live in constant fear of gaining weight. They often do everything in their power to avoid putting on weight, even if they are already suffering from the health consequences or are restricted in their daily lives. Computer Vision researchers at the Max Planck Institute for Intelligent Systems and the University Hospital Tübingen have developed a virtual reality tool that can be used to simulate weight gain. The research suggests that repeated exposure to a healthy bodyweight in virtual reality helps people with anorexia nervosa reduce their fear of gaining weight. The full text can be found in German on the website of the Max Planck Society.
URL BibTeX