Publications | Max Planck Institute for Intelligent Systems

Ground reaction force sensing is one of the key components of gait analysis in legged locomotion research. To measure continuous force data during locomotion, we present a novel compound instrumented treadmill design. The treadmill is 1.7 m long, with a natural frequency of 170 Hz and an adjustable range that can be used for humans and small robots alike. Here, we present the treadmill’s design methodology and characterize it in its natural frequency, noise behavior and real-life performance. Additionally, we apply an ISO 376 norm conform calibration procedure for all spatial force directions and center of pressure position. We achieve a force accuracy of ≤ 5.6 N for the ground reaction forces and ≤ 13 mm in center of pressure position.

dlg

arXiv link (url) DOI [BibTex]

dlg Sarvestani, A., Ruppert, F., Badri-Spröwitz, A. An Open-Source Modular Treadmill for Dynamic Force Measurement with Load Dependant Range Adjustment 2023 (unpublished) Submitted

arXiv link (url) DOI [BibTex]

Synchronizing Machine Learning Algorithms, Realtime Robotic Control and Simulated Environment with o80

Berenz, V., Widmaier, F., Guist, S., Schölkopf, B., Büchler, D.

Robot Software Architectures Workshop (RSA) 2023, ICRA, 2023 (techreport)

Abstract

Robotic applications require the integration of various modalities, encompassing perception, control of real robots and possibly the control of simulated environments. While the state-of-the-art robotic software solutions such as ROS 2 provide most of the required features, flexible synchronization between algorithms, data streams and control loops can be tedious. o80 is a versatile C++ framework for robotics which provides a shared memory model and a command framework for real-time critical systems. It enables expert users to set up complex robotic systems and generate Python bindings for scientists. o80's unique feature is its flexible synchronization between processes, including the traditional blocking commands and the novel ``bursting mode'', which allows user code to control the execution of the lower process control loop. This makes it particularly useful for setups that mix real and simulated environments.

arxiv poster link (url) [BibTex]

ei Berenz, V., Widmaier, F., Guist, S., Schölkopf, B., Büchler, D. Synchronizing Machine Learning Algorithms, Realtime Robotic Control and Simulated Environment with o80 Robot Software Architectures Workshop (RSA) 2023, ICRA, 2023 (techreport)

arxiv poster link (url) [BibTex]

Challenging Common Assumptions in Multi-task Learning

Elich, C., Kirchdorfer, L., Köhler, J. M., Schott, L.

abs/2311.04698, CoRR/arxiv, 2023 (techreport)

paper link (url) [BibTex]

ev Elich, C., Kirchdorfer, L., Köhler, J. M., Schott, L. Challenging Common Assumptions in Multi-task Learning abs/2311.04698, CoRR/arxiv, 2023 (techreport)

paper link (url) [BibTex]

2022

Investigating Independent Mechanisms in Neural Networks

Liang, W.

Université Paris-Saclay, France, October 2022 (mastersthesis)

[BibTex]

2022

ei Liang, W. Investigating Independent Mechanisms in Neural Networks Université Paris-Saclay, France, October 2022 (mastersthesis)

[BibTex]

Modeling subgroup differences in fMRI data: disentangling subgroup-specific responses from shared ones

Keidar, D.

ETH Zurich, Switzerland, October 2022 (mastersthesis)

[BibTex]

ei Keidar, D. Modeling subgroup differences in fMRI data: disentangling subgroup-specific responses from shared ones ETH Zurich, Switzerland, October 2022 (mastersthesis)

[BibTex]

Multi-Target Multi-Object Manipulation using Relational Deep Reinforcement Learning

Feil, M.

Technnical University Munich, Germany, September 2022 (mastersthesis)

[BibTex]

ei Feil, M. Multi-Target Multi-Object Manipulation using Relational Deep Reinforcement Learning Technnical University Munich, Germany, September 2022 (mastersthesis)

[BibTex]

Independent Mechanism Analysis for High Dimensions

Sliwa, J.

University of Tübingen, Germany, September 2022, (Graduate Training Centre of Neuroscience) (mastersthesis)

[BibTex]

ei Sliwa, J. Independent Mechanism Analysis for High Dimensions University of Tübingen, Germany, September 2022, (Graduate Training Centre of Neuroscience) (mastersthesis)

[BibTex]

On the Adversarial Robustness of Causal Algorithmic Recourse

Dominguez-Olmedo, R.

University of Tübingen, Germany, August 2022 (mastersthesis)

[BibTex]

ei Dominguez-Olmedo, R. On the Adversarial Robustness of Causal Algorithmic Recourse University of Tübingen, Germany, August 2022 (mastersthesis)

[BibTex]

Independent Mechanism Analysis in High-Dimensional Observation Spaces

Ghosh, S.

ETH Zurich, Switzerland, June 2022 (mastersthesis)

[BibTex]

ei Ghosh, S. Independent Mechanism Analysis in High-Dimensional Observation Spaces ETH Zurich, Switzerland, June 2022 (mastersthesis)

[BibTex]

Learning Plastic Matching of Robot Dynamics in Closed-Loop Central Pattern Generators: Data

Ruppert, F., Badri-Spröwitz, A.

Edmond, May 2022 (techreport)

dlg

link (url) DOI [BibTex]

dlg Ruppert, F., Badri-Spröwitz, A. Learning Plastic Matching of Robot Dynamics in Closed-Loop Central Pattern Generators: Data Edmond, May 2022 (techreport)

link (url) DOI [BibTex]

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)

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]

Data for BirdBot Achieves Energy-Efﬁcient Gait with Minimal Control Using Avian-Inspired Leg Clutching

Badri-Spröwitz, A., Sarvestani, A. A., Sitti, M., Daley, M. A.

Edmond, March 2022 (techreport)

dlg pi

DOI Project Page [BibTex]

dlg pi Badri-Spröwitz, A., Sarvestani, A. A., Sitti, M., Daley, M. A. Data for BirdBot Achieves Energy-Efﬁcient Gait with Minimal Control Using Avian-Inspired Leg Clutching Edmond, March 2022 (techreport)

DOI Project Page [BibTex]

Observability Analysis of Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models

Li, H., Stueckler, J.

abs/2204.06651, CoRR/arxiv, 2022 (techreport)

Abstract

In this paper, we analyze the observability of the visual-inertial odometry (VIO) using stereo cameras with a velocity-control based kinematic motion model. Previous work shows that in general case the global position and yaw are unobservable in VIO system, additionally the roll and pitch become also unobservable if there is no rotation. We prove that by integrating a planar motion constraint roll and pitch become observable. We also show that the parameters of the motion model are observable.

link (url) [BibTex]

ev Li, H., Stueckler, J. Observability Analysis of Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models abs/2204.06651, CoRR/arxiv, 2022 (techreport)

link (url) [BibTex]

Voltage dependent investigations on the spin polarization of layered heterostructues

Miller, M.

Universität Stuttgart, Stuttgart, 2022 (mastersthesis)

mms

[BibTex]

mms Miller, M. Voltage dependent investigations on the spin polarization of layered heterostructues Universität Stuttgart, Stuttgart, 2022 (mastersthesis)

[BibTex]

2021

Learning Neural Causal Models with Active Interventions

Scherrer, N.

ETH Zurich, Switzerland, November 2021 (mastersthesis)

[BibTex]

2021

ei Scherrer, N. Learning Neural Causal Models with Active Interventions ETH Zurich, Switzerland, November 2021 (mastersthesis)

[BibTex]

HealthGen: Conditional Generation of Realistic Medical Time Series with Informative Missingness

Bing, S.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Bing, S. HealthGen: Conditional Generation of Realistic Medical Time Series with Informative Missingness ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

Study of the Interventional Consistency of Autoencoders

Lanzillotta, G.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Lanzillotta, G. Study of the Interventional Consistency of Autoencoders ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

Training with Few to Manipulate Many. On OOD generalization in relational reinforcement learning

Mambelli, D.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Mambelli, D. Training with Few to Manipulate Many. On OOD generalization in relational reinforcement learning ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

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)

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]

Toward a Science of Effective Well-Doing

Lieder, F., Prentice, M., Corwin-Renner, E.

May 2021 (techreport)

Abstract

Well-doing, broadly construed, encompasses acting and thinking in ways that contribute to humanity’s flourishing in the long run. This often takes the form of setting a prosocial goal and pursuing it over an extended period of time. To set and pursue goals in a way that is extremely beneficial for humanity (effective well-doing), people often have to employ critical thinking and far-sighted, rational decision-making in the service of the greater good. To promote effective well-doing, we need to better understand its determinants and psychological mechanisms, as well as the barriers to effective well-doing and how they can be overcome. In this article, we introduce a taxonomy of different forms of well-doing and introduce a conceptual model of the cognitive mechanisms of effective well-doing. We view effective well-doing as the upper end of a moral continuum whose lower half comprises behaviors that are harmful to humanity (ill-doing), and we argue that the capacity for effective well-doing has to be developed through personal growth (e.g., learning how to pursue goals effectively). Research on these phenomena has so far been scattered across numerous disconnected literatures from multiple disciplines. To bring these communities together, we call for the establishment of a transdisciplinary research field focussed on understanding and promoting effective well-doing and personal growth as well as understanding and reducing ill-doing. We define this research field in terms of its goals and questions. We review what is already known about these questions in different disciplines and argue that laying the scientific foundation for promoting effective well-doing is one of the most valuable contributions that the behavioral sciences can make in the 21st century.

Preprint Project Page [BibTex]

re Lieder, F., Prentice, M., Corwin-Renner, E. Toward a Science of Effective Well-Doing May 2021 (techreport)

Preprint Project Page [BibTex]

Robotic Surgery Training in AR: Multimodal Record and Replay

Krauthausen, F.

pages: 1-147, University of Stuttgart, Stuttgart, May 2021, Study Program in Software Engineering (mastersthesis)

[BibTex]

hi Krauthausen, F. Robotic Surgery Training in AR: Multimodal Record and Replay pages: 1-147, University of Stuttgart, Stuttgart, May 2021, Study Program in Software Engineering (mastersthesis)

[BibTex]

Direct detection of spin Hall effect induced torques in platinum/ferromagnetic bilayer systems

Alten, F.

Universität Stuttgart, Stuttgart, January 2021 (mastersthesis)

mms

[BibTex]

mms Alten, F. Direct detection of spin Hall effect induced torques in platinum/ferromagnetic bilayer systems Universität Stuttgart, Stuttgart, January 2021 (mastersthesis)

[BibTex]

Community detection in heterogeneously attributed networks

Zottino, N.

Politecnico di Torino, 2021 (mastersthesis)

pio

link (url) [BibTex]

pio Zottino, N. Community detection in heterogeneously attributed networks Politecnico di Torino, 2021 (mastersthesis)

link (url) [BibTex]

2020

Hydromagnonics: Manipulation of magnonic systems with hydrogen

Sauter, R.

Universität Stuttgart, Stuttgart, December 2020 (mastersthesis)

mms

[BibTex]

2020

mms Sauter, R. Hydromagnonics: Manipulation of magnonic systems with hydrogen Universität Stuttgart, Stuttgart, December 2020 (mastersthesis)

[BibTex]

A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Ahmed, O.

ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

ei Ahmed, O. A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

A Comprehensive Benchmark Evaluation of Synthetic Data Generation for Biomedical Imaging

DuMont Schütte, A.

ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

ei DuMont Schütte, A. A Comprehensive Benchmark Evaluation of Synthetic Data Generation for Biomedical Imaging ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

Optimal To-Do List Gamification

Stojcheski, J., Felso, V., Lieder, F.

ArXiv Preprint, 2020 (techreport)

Abstract

What should I work on first? What can wait until later? Which projects should I prioritize and which tasks are not worth my time? These are challenging questions that many people face every day. People’s intuitive strategy is to prioritize their immediate experience over the long-term consequences. This leads to procrastination and the neglect of important long-term projects in favor of seemingly urgent tasks that are less important. Optimal gamification strives to help people overcome these problems by incentivizing each task by a number of points that communicates how valuable it is in the long-run. Unfortunately, computing the optimal number of points with standard dynamic programming methods quickly becomes intractable as the number of a person’s projects and the number of tasks required by each project increase. Here, we introduce and evaluate a scalable method for identifying which tasks are most important in the long run and incentivizing each task according to its long-term value. Our method makes it possible to create to-do list gamification apps that can handle the size and complexity of people’s to-do lists in the real world.

link (url) DOI Project Page [BibTex]

re Stojcheski, J., Felso, V., Lieder, F. Optimal To-Do List Gamification ArXiv Preprint, 2020 (techreport)

link (url) DOI Project Page [BibTex]

Deep learning for the parameter estimation of tight-binding Hamiltonians

Cacioppo, A.

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

[BibTex]

ei Cacioppo, A. Deep learning for the parameter estimation of tight-binding Hamiltonians University of Roma, La Sapienza, Italy, May 2020 (mastersthesis)

[BibTex]

Learning Algorithms, Invariances, and the Real World

Zecevic, M.

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

[BibTex]

ei Zecevic, M. Learning Algorithms, Invariances, and the Real World Technical University of Darmstadt, Germany, April 2020 (mastersthesis)

[BibTex]

Interaction of hydrogen isotopes with flexible metal-organic frameworks

Bondorf, L.

Universität Stuttgart, Stuttgart, February 2020 (mastersthesis)

mms

[BibTex]

mms Bondorf, L. Interaction of hydrogen isotopes with flexible metal-organic frameworks Universität Stuttgart, Stuttgart, February 2020 (mastersthesis)

[BibTex]

Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures

Marco, A., Rohr, A. V., Baumann, D., Hernández-Lobato, J. M., Trimpe, S.

2020 (proceedings) In revision

Abstract

When learning to ride a bike, a child falls down a number of times before achieving the first success. As falling down usually has only mild consequences, it can be seen as a tolerable failure in exchange for a faster learning process, as it provides rich information about an undesired behavior. In the context of Bayesian optimization under unknown constraints (BOC), typical strategies for safe learning explore conservatively and avoid failures by all means. On the other side of the spectrum, non conservative BOC algorithms that allow failing may fail an unbounded number of times before reaching the optimum. In this work, we propose a novel decision maker grounded in control theory that controls the amount of risk we allow in the search as a function of a given budget of failures. Empirical validation shows that our algorithm uses the failures budget more efficiently in a variety of optimization experiments, and generally achieves lower regret, than state-of-the-art methods. In addition, we propose an original algorithm for unconstrained Bayesian optimization inspired by the notion of excursion sets in stochastic processes, upon which the failures-aware algorithm is built.

am ics

arXiv code (python) PDF [BibTex]