Publications | Max Planck Institute for Intelligent Systems

Language Models Can Reduce Asymmetry in Information Markets

Rahaman, N., Weiss, M., Wüthrich, M., Bengio, Y., Li, E., Pal, C., Schölkopf, B.

arXiv:2403.14443, March 2024, Published as: Redesigning Information Markets in the Era of Language Models, Conference on Language Modeling (COLM) (techreport)

Abstract

This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limit access to prevent theft. To study this, we introduce an open-source simulated digital marketplace where intelligent agents, powered by language models, buy and sell information on behalf of external participants. The central mechanism enabling this marketplace is the agents' dual capabilities: they not only have the capacity to assess the quality of privileged information but also come equipped with the ability to forget. This ability to induce amnesia allows vendors to grant temporary access to proprietary information, significantly reducing the risk of unauthorized retention while enabling agents to accurately gauge the information's relevance to specific queries or tasks. To perform well, agents must make rational decisions, strategically explore the marketplace through generated sub-queries, and synthesize answers from purchased information. Concretely, our experiments (a) uncover biases in language models leading to irrational behavior and evaluate techniques to mitigate these biases, (b) investigate how price affects demand in the context of informational goods, and (c) show that inspection and higher budgets both lead to higher quality outcomes.

ei Rahaman, N., Weiss, M., Wüthrich, M., Bengio, Y., Li, E., Pal, C., Schölkopf, B. Language Models Can Reduce Asymmetry in Information Markets arXiv:2403.14443, March 2024, Published as: Redesigning Information Markets in the Era of Language Models, Conference on Language Modeling (COLM) (techreport)

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 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)

Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation

Achterhold, J., Guttikonda, S., Kreber, J. U., Li, H., Stueckler, J.

CoRR abs/2409.11452, 2024, Preprint submitted to Robotics and Autonomous Systems Journal. https://arxiv.org/abs/2409.11452 (techreport) Submitted

Abstract

Mobile robots should be capable of planning cost-efficient paths for autonomous navigation. Typically, the terrain and robot properties are subject to variations. For instance, properties of the terrain such as friction may vary across different locations. Also, properties of the robot may change such as payloads or wear and tear, e.g., causing changing actuator gains or joint friction. Autonomous navigation approaches should thus be able to adapt to such variations. In this article, we propose a novel approach for learning a probabilistic, terrain- and robot-aware forward dynamics model (TRADYN) which can adapt to such variations and demonstrate its use for navigation. Our learning approach extends recent advances in meta-learning forward dynamics models based on Neural Processes for mobile robot navigation. We evaluate our method in simulation for 2D navigation of a robot with uni-cycle dynamics with varying properties on terrain with spatially varying friction coefficients. In our experiments, we demonstrate that TRADYN has lower prediction error over long time horizons than model ablations which do not adapt to robot or terrain variations. We also evaluate our model for navigation planning in a model-predictive control framework and under various sources of noise. We demonstrate that our approach yields improved performance in planning control-efficient paths by taking robot and terrain properties into account.

preprint [BibTex]

ev Achterhold, J., Guttikonda, S., Kreber, J. U., Li, H., Stueckler, J. Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation CoRR abs/2409.11452, 2024, Preprint submitted to Robotics and Autonomous Systems Journal. https://arxiv.org/abs/2409.11452 (techreport) Submitted

preprint [BibTex]

A Pontryagin Perspective on Reinforcement Learning

Eberhard, O., Vernade, C., Muehlebach, M.

Max Planck Institute for Intelligent Systems, 2024 (techreport)

lds

lds Eberhard, O., Vernade, C., Muehlebach, M. A Pontryagin Perspective on Reinforcement Learning Max Planck Institute for Intelligent Systems, 2024 (techreport)

Distributed Event-Based Learning via ADMM

Er, D., Trimpe, S., Muehlebach, M.

Max Planck Institute for Intelligent Systems, 2024 (techreport)

lds

lds Er, D., Trimpe, S., Muehlebach, M. Distributed Event-Based Learning via ADMM Max Planck Institute for Intelligent Systems, 2024 (techreport)

preprint supplemental video link (url) [BibTex]

Incremental Few-Shot Adaptation for Non-Prehensile Object Manipulation using Parallelizable Physics Simulators

Baumeister, F., Mack, L., Stueckler, J.

CoRR abs/2409.13228, CoRR, 2024, Submitted to IEEE International Conference on Robotics and Automation (ICRA) 2025 (techreport) Submitted

Abstract

Few-shot adaptation is an important capability for intelligent robots that perform tasks in open-world settings such as everyday environments or flexible production. In this paper, we propose a novel approach for non-prehensile manipulation which iteratively adapts a physics-based dynamics model for model-predictive control. We adapt the parameters of the model incrementally with a few examples of robot-object interactions. This is achieved by sampling-based optimization of the parameters using a parallelizable rigid-body physics simulation as dynamic world model. In turn, the optimized dynamics model can be used for model-predictive control using efficient sampling-based optimization. We evaluate our few-shot adaptation approach in several object pushing experiments in simulation and with a real robot.

ev Baumeister, F., Mack, L., Stueckler, J. Incremental Few-Shot Adaptation for Non-Prehensile Object Manipulation using Parallelizable Physics Simulators CoRR abs/2409.13228, CoRR, 2024, Submitted to IEEE International Conference on Robotics and Automation (ICRA) 2025 (techreport) Submitted

preprint supplemental video link (url) [BibTex]

2023

Fairness in Machine Learning: Limitations and Opportunities

Barocas, S., Hardt, M., Narayanan, A.

MIT Press, December 2023 (book)

Abstract

An introduction to the intellectual foundations and practical utility of the recent work on fairness and machine learning. Fairness and Machine Learning introduces advanced undergraduate and graduate students to the intellectual foundations of this recently emergent field, drawing on a diverse range of disciplinary perspectives to identify the opportunities and hazards of automated decision-making. It surveys the risks in many applications of machine learning and provides a review of an emerging set of proposed solutions, showing how even well-intentioned applications may give rise to objectionable results. It covers the statistical and causal measures used to evaluate the fairness of machine learning models as well as the procedural and substantive aspects of decision-making that are core to debates about fairness, including a review of legal and philosophical perspectives on discrimination. This incisive textbook prepares students of machine learning to do quantitative work on fairness while reflecting critically on its foundations and its practical utility.• Introduces the technical and normative foundations of fairness in automated decision-making• Covers the formal and computational methods for characterizing and addressing problems• Provides a critical assessment of their intellectual foundations and practical utility• Features rich pedagogy and extensive instructor resources

2023

sf Barocas, S., Hardt, M., Narayanan, A. Fairness in Machine Learning: Limitations and Opportunities MIT Press, December 2023 (book)

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

Natural Language Processing for Policymaking

Jin, Z., Mihalcea, R.

In Handbook of Computational Social Science for Policy, pages: 141-162, 7, (Editors: Bertoni, E. and Fontana, M. and Gabrielli, L. and Signorelli, S. and Vespe, M.), Springer International Publishing, 2023 (inbook)

ei Jin, Z., Mihalcea, R. Natural Language Processing for Policymaking In Handbook of Computational Social Science for Policy, pages: 141-162, 7, (Editors: Bertoni, E. and Fontana, M. and Gabrielli, L. and Signorelli, S. and Vespe, M.), Springer International Publishing, 2023 (inbook)

arxiv poster link (url) [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.

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]

2022

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)

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)

Magnetic Micro-/Nanopropellers for Biomedicine

Qiu, T., Jeong, M., Goyal, R., Kadiri, V., Sachs, J., Fischer, P.

In Field-Driven Micro and Nanorobots for Biology and Medicine, pages: 389-410, 16, (Editors: Sun, Y. and Wang, X. and Yu, J.), Springer, Cham, 2022 (inbook)

Abstract

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.

pf Qiu, T., Jeong, M., Goyal, R., Kadiri, V., Sachs, J., Fischer, P. Magnetic Micro-/Nanopropellers for Biomedicine In Field-Driven Micro and Nanorobots for Biology and Medicine, pages: 389-410, 16, (Editors: Sun, Y. and Wang, X. and Yu, J.), Springer, Cham, 2022 (inbook)

Life Improvement Science

Lieder, F., Prentice, M.

In Encyclopedia of Quality of Life and Well-Being Research, Springer, November 2022 (inbook)

re Lieder, F., Prentice, M. Life Improvement Science In Encyclopedia of Quality of Life and Well-Being Research, Springer, November 2022 (inbook)

Causality, causal digital twins, and their applications

Schölkopf, B.

Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382), (Editors: Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica), September 2022 (talk)

ei Schölkopf, B. Causality, causal digital twins, and their applications Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382), (Editors: Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica), September 2022 (talk)

Patterns, Predictions, and Actions: Foundations of Machine Learning

Hardt, M., Recht, B.

Princeton University Press, August 2022 (book)

Abstract

An authoritative, up-to-date graduate textbook on machine learning that highlights its historical context and societal impacts Patterns, Predictions, and Actions introduces graduate students to the essentials of machine learning while offering invaluable perspective on its history and social implications. Beginning with the foundations of decision making, Moritz Hardt and Benjamin Recht explain how representation, optimization, and generalization are the constituents of supervised learning. They go on to provide self-contained discussions of causality, the practice of causal inference, sequential decision making, and reinforcement learning, equipping readers with the concepts and tools they need to assess the consequences that may arise from acting on statistical decisions. Provides a modern introduction to machine learning, showing how data patterns support predictions and consequential actions Pays special attention to societal impacts and fairness in decision making Traces the development of machine learning from its origins to today Features a novel chapter on machine learning benchmarks and datasets Invites readers from all backgrounds, requiring some experience with probability, calculus, and linear algebra An essential textbook for students and a guide for researchers

sf Hardt, M., Recht, B. Patterns, Predictions, and Actions: Foundations of Machine Learning Princeton University Press, August 2022 (book)

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

Ruppert, F., Badri-Spröwitz, A.

Edmond, May 2022 (techreport)

dlg

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

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 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)

DOI Project Page [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

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.

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)

Causal Models for Dynamical Systems

Peters, J., Bauer, S., Pfister, N.

In Probabilistic and Causal Inference: The Works of Judea Pearl, pages: 671-690, 1, Association for Computing Machinery, 2022 (inbook)

ei Peters, J., Bauer, S., Pfister, N. Causal Models for Dynamical Systems In Probabilistic and Causal Inference: The Works of Judea Pearl, pages: 671-690, 1, Association for Computing Machinery, 2022 (inbook)

Karimi, A. H., von Kügelgen, J., Schölkopf, B., Valera, I.

Towards Causal Algorithmic Recourse

In xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pages: 139-166, (Editors: Holzinger, Andreas and Goebel, Randy and Fong, Ruth and Moon, Taesup and Müller, Klaus-Robert and Samek, Wojciech), Springer International Publishing, 2022 (inbook)

ei plg

ei plg Karimi, A. H., von Kügelgen, J., Schölkopf, B., Valera, I. Towards Causal Algorithmic Recourse In xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pages: 139-166, (Editors: Holzinger, Andreas and Goebel, Randy and Fong, Ruth and Moon, Taesup and Müller, Klaus-Robert and Samek, Wojciech), Springer International Publishing, 2022 (inbook)

CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations

Salewski, L., Koepke, A. S., Lensch, H. P. A., Akata, Z.

In xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pages: 69-88, (Editors: Holzinger, Andreas and Goebel, Randy and Fong, Ruth and Moon, Taesup and Müller, Klaus-Robert and Samek, Wojciech), Springer International Publishing, 2022 (inbook)

ei Salewski, L., Koepke, A. S., Lensch, H. P. A., Akata, Z. CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations In xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pages: 69-88, (Editors: Holzinger, Andreas and Goebel, Randy and Fong, Ruth and Moon, Taesup and Müller, Klaus-Robert and Samek, Wojciech), Springer International Publishing, 2022 (inbook)

Causality for Machine Learning

Schölkopf, B.

In Probabilistic and Causal Inference: The Works of Judea Pearl, pages: 765-804, 1, Association for Computing Machinery, New York, NY, USA, 2022 (inbook)

ei Schölkopf, B. Causality for Machine Learning In Probabilistic and Causal Inference: The Works of Judea Pearl, pages: 765-804, 1, Association for Computing Machinery, New York, NY, USA, 2022 (inbook)

Strecke, M., Stückler, J.

2021

Physically Plausible Tracking & Reconstruction of Dynamic Objects

KIT Science Week Scientific Conference & DGR-Days 2021, October 2021 (talk)

2021

ev Strecke, M., Stückler, J. Physically Plausible Tracking & Reconstruction of Dynamic Objects KIT Science Week Scientific Conference & DGR-Days 2021, October 2021 (talk)

Supplemental Material link (url) DOI [BibTex]

Electriflow: Augmenting Books With Tangible Animation Using Soft Electrohydraulic Actuators

Purnendu, , Novack, S., Acome, E., Alistar, M., Keplinger, C., Gross, M. D., Bruns, C., Leithinger, D.

In ACM SIGGRAPH 2021 Labs, pages: 1-2, Association for Computing Machinery, SIGGRAPH 2021, August 2021 (inbook)

Abstract

We present Electriflow: a method of augmenting books with tangible animation employing soft electrohydraulic actuators. These actuators are compact, silent and fast in operation, and can be fabricated with commodity materials. They generate an immediate hydraulic force upon electrostatic activation without an external fluid supply source, enabling a simple and self-contained design. Electriflow actuators produce an immediate shape transition from flat to folded state which enabled their seamless integration into books. For the Emerging Technologies exhibit, we will demonstrate the prototype of a book augmented with the capability of tangible animation.

rm Purnendu, , Novack, S., Acome, E., Alistar, M., Keplinger, C., Gross, M. D., Bruns, C., Leithinger, D. Electriflow: Augmenting Books With Tangible Animation Using Soft Electrohydraulic Actuators In ACM SIGGRAPH 2021 Labs, pages: 1-2, Association for Computing Machinery, SIGGRAPH 2021, August 2021 (inbook)

Supplemental Material link (url) DOI [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)

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)

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

Preprint Project Page [BibTex]

Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning

Heindrich, L., Consul, S., Stojcheski, J., Lieder, F.

Tübingen, Germany, The first edition of Life Improvement Science Conference, June 2021 (talk) Accepted

Abstract

The discovery of decision strategies is an essential part of creating effective cognitive tutors that teach planning and decision-making skills to humans. In the context of bounded rationality, this requires weighing the benefits of different planning operations compared to their computational costs. For small decision problems, it has already been shown that near-optimal decision strategies can be discovered automatically and that the discovered strategies can be taught to humans to increase their performance. Unfortunately, these near-optimal strategy discovery algorithms have not been able to scale well to larger problems due to their computational complexity. In this talk, we will present recent work at the Rationality Enhancement Group to overcome the computational bottleneck of existing strategy discovery algorithms. Our approach makes use of the hierarchical structure of human behavior by decomposing sequential decision problems into two sub-problems: setting a goal and planning how to achieve it. An additional metacontroller component is introduced to switch the current goal when it becomes beneficial. The hierarchical decomposition enables us to discover near-optimal strategies for human planning in larger and more complex tasks than previously possible. We then show in online experiments that teaching the discovered strategies to humans improves their performance in complex sequential decision-making tasks.

Project Page [BibTex]

re Heindrich, L., Consul, S., Stojcheski, J., Lieder, F. Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning Tübingen, Germany, The first edition of Life Improvement Science Conference, June 2021 (talk) Accepted

Project Page [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.

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

Preprint Project Page [BibTex]

Optimal To-Do List Gamification for Long Term Planning

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

arXiv preprint arXiv:2109.06505, 2021 (techreport)

re Consul, S., Stojcheski, J., Felso, V., Lieder, F. Optimal To-Do List Gamification for Long Term Planning arXiv preprint arXiv:2109.06505, 2021 (techreport)

Sitti, M., Liimatainen, V.

Method of making one or more fibrils, computer implemented method of simulating an adhesive force of one or more fibrils and fibril

2021, EP Prio. Patent App. 21 162 253.5 (mpi_year_book)

pi Sitti, M., Liimatainen, V. Method of making one or more fibrils, computer implemented method of simulating an adhesive force of one or more fibrils and fibril 2021, EP Prio. Patent App. 21 162 253.5 (mpi_year_book)

Reinforcement Learning Algorithms: Analysis and Applications

Belousov, B., H., A., Klink, P., Parisi, S., Peters, J.

883, Studies in Computational Intelligence, Springer International Publishing, 2021 (book)

ei Belousov, B., H., A., Klink, P., Parisi, S., Peters, J. Reinforcement Learning Algorithms: Analysis and Applications 883, Studies in Computational Intelligence, Springer International Publishing, 2021 (book)

Scientific Report 2016 - 2021 [BibTex]

Scientific Report 2016 - 2021

2021 (mpi_year_book)

Abstract

This report presents research done at the Max Planck Institute for Intelligent Systems from January2016 to November 2021. It is our fourth report since the founding of the institute in 2011. Dueto the fact that the upcoming evaluation is an extended one, the report covers a longer reportingperiod.This scientific report is organized as follows: we begin with an overview of the institute, includingan outline of its structure, an introduction of our latest research departments, and a presentationof our main collaborative initiatives and activities (Chapter1). The central part of the scientificreport consists of chapters on the research conducted by the institute’s departments (Chapters2to6) and its independent research groups (Chapters7 to24), as well as the work of the institute’scentral scientific facilities (Chapter25). For entities founded after January 2016, the respectivereport sections cover work done from the date of the establishment of the department, group, orfacility. These chapters are followed by a summary of selected outreach activities and scientificevents hosted by the institute (Chapter26). The scientific publications of the featured departmentsand research groups published during the 6-year review period complete this scientific report.

ei hi ps pi rm

ei hi ps pi rm Scientific Report 2016 - 2021 2021 (mpi_year_book)

Scientific Report 2016 - 2021 [BibTex]

Turbulence Modulation and Energy Transfer in Turbulent Channel Flow Coupled with One-Side Porous Media

Chu, X., Wang, W., Müller, J., Schöning, H. V., Liu, Y., Weigand, B.

In High Performance Computing in Science and Engineering’20, pages: 373-386, Springer, 2021 (incollection)

minibot

minibot Chu, X., Wang, W., Müller, J., Schöning, H. V., Liu, Y., Weigand, B. Turbulence Modulation and Energy Transfer in Turbulent Channel Flow Coupled with One-Side Porous Media In High Performance Computing in Science and Engineering’20, pages: 373-386, Springer, 2021 (incollection)

link (url) DOI Project Page [BibTex]

2020

Towards Hybrid Active and Passive Compliant Mechanisms in Legged Robots

Milad Shafiee Ashtiani, A. A. S., Badri-Sproewitz, A.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, October 2020 (poster) Accepted

dlg

Abstract Poster [BibTex]

2020

dlg Milad Shafiee Ashtiani, A. A. S., Badri-Sproewitz, A. Towards Hybrid Active and Passive Compliant Mechanisms in Legged Robots IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, October 2020 (poster) Accepted

Abstract Poster [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.

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

link (url) DOI Project Page [BibTex]

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Heim, S., Badri-Spröwitz, A.

May 2020 (talk)

dlg

Presentation [BibTex]

dlg Heim, S., Badri-Spröwitz, A. Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics May 2020 (talk)

Presentation [BibTex]

VP above or below? A new perspective on the story of the virtual point

Drama, Ö., Badri-Spröwitz, A.

Dynamic Walking, May 2020 (poster)

Abstract

The spring inverted pendulum model with an extended trunk (TSLIP) is widely used to investigate the postural stability in bipedal locomotion [1, 2]. The challenge of the model is to define a hip torque that generates feasible gait patterns while stabilizing the floating trunk. The virtual point (VP) method is proposed as a simplified solution, where the hip torque is coupled to the passive compliant leg force via a virtual point. This geometric coupling is based on the assumption that the instantaneous ground reaction forces of the stance phase (GRF) intersect at a single virtual point.

dlg

Poster Abstract link (url) [BibTex]

dlg Drama, Ö., Badri-Spröwitz, A. VP above or below? A new perspective on the story of the virtual point Dynamic Walking, May 2020 (poster)

Poster Abstract link (url) [BibTex]

Viscous Damping in Legged Locomotion

Mo, A., Izzi, F., Haeufle, D. F. B., Badri-Spröwitz, A.

Dynamic Walking, May 2020 (poster)

Abstract

Damping likely plays an essential role in legged animal locomotion, but remains an insufficiently understood mechanism. Intrinsic damping muscle forces can potentially add to the joint torque output during unexpected impacts, stabilise movements, convert the system’s energy, and reject unexpected perturbations.

dlg

dlg Mo, A., Izzi, F., Haeufle, D. F. B., Badri-Spröwitz, A. Viscous Damping in Legged Locomotion Dynamic Walking, May 2020 (poster)

How Quadrupeds Benefit from Lower Leg Passive Elasticity

Ruppert, F., Badri-Spröwitz, A.

Dynamic Walking, May 2020 (poster)

Abstract

Recently developed and fully actuated, legged robots start showing exciting locomotion capabilities, but rely heavily on high-power actuators, high-frequency sensors, and complex locomotion controllers. The engineering solutions implemented in these legged robots are much different compared to animals. Vertebrate animals share magnitudes slower neurocontrol signal velocities [1] compared to their robot counterparts. Also, animals feature a plethora of cascaded and underactuated passive elastic structures [2].

dlg

dlg Ruppert, F., Badri-Spröwitz, A. How Quadrupeds Benefit from Lower Leg Passive Elasticity Dynamic Walking, May 2020 (poster)

Nichtgleichgewichtsdynamik einer abgekühlten kritischen Flüssigkeit mit Oberflächenfeldern unterschiedlichen Vorzeichens

Dertli, Denis

Universität Stuttgart, Stuttgart, January 2020 (thesis)

icm

icm Dertli, Denis Nichtgleichgewichtsdynamik einer abgekühlten kritischen Flüssigkeit mit Oberflächenfeldern unterschiedlichen Vorzeichens Universität Stuttgart, Stuttgart, January 2020 (thesis)

Potential for elastic soft tissue deformation and mechanosensory function within the lumbosacral spinal canal of birds

Kamska, V., Daley, M., Badri-Spröwitz, A.

Society for Integrative and Comparative Biology Annual Meeting (SICB Annual Meeting 2020), January 2020 (poster)

dlg

dlg Kamska, V., Daley, M., Badri-Spröwitz, A. Potential for elastic soft tissue deformation and mechanosensory function within the lumbosacral spinal canal of birds Society for Integrative and Comparative Biology Annual Meeting (SICB Annual Meeting 2020), January 2020 (poster)

25th International Symposium on Vision, Modeling and Visualization, VMV 2020

(Editors: Jens Krüger and Matthias Nießner and Jörg Stückler), Eurographics Association, 2020 (proceedings)

ev 25th International Symposium on Vision, Modeling and Visualization, VMV 2020 (Editors: Jens Krüger and Matthias Nießner and Jörg Stückler), Eurographics Association, 2020 (proceedings)

arXiv code (python) PDF [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

am ics Marco, A., Rohr, A. V., Baumann, D., Hernández-Lobato, J. M., Trimpe, S. Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures 2020 (proceedings) In revision

arXiv code (python) PDF [BibTex]

TUM Flyers: Vision-Based MAV Navigation for Systematic Inspection of Structures

Usenko, V., Stumberg, L. V., Stückler, J., Cremers, D.

In Bringing Innovative Robotic Technologies from Research Labs to Industrial End-users: The Experience of the European Robotics Challenges, 136, pages: 189-209, Springer Tracts in Advanced Robotics, Springer International Publishing, 2020 (inbook)

ev Usenko, V., Stumberg, L. V., Stückler, J., Cremers, D. TUM Flyers: Vision-Based MAV Navigation for Systematic Inspection of Structures In Bringing Innovative Robotic Technologies from Research Labs to Industrial End-users: The Experience of the European Robotics Challenges, 136, pages: 189-209, Springer Tracts in Advanced Robotics, Springer International Publishing, 2020 (inbook)

Popescu, M. N., Uspal, W. E.

Identifying Causal Structure in Dynamical Systems

Baumann, D., Solowjow, F., Johansson, K. H., Trimpe, S.

2020 (techreport)

ics

arXiv [BibTex]

ics Baumann, D., Solowjow, F., Johansson, K. H., Trimpe, S. Identifying Causal Structure in Dynamical Systems 2020 (techreport)

arXiv [BibTex]

Adopting the Boundary Homogenization Approximation from Chemical Kinetics to Motile Chemically Active Particles

In Chemical Kinetics, pages: 517-540, (Editors: Lindenberg, Katja and Metzler, Ralf and Oshanin, Gleb), World Scientific, New Jersey, NJ, 2020 (incollection)

icm

icm Popescu, M. N., Uspal, W. E. Adopting the Boundary Homogenization Approximation from Chemical Kinetics to Motile Chemically Active Particles In Chemical Kinetics, pages: 517-540, (Editors: Lindenberg, Katja and Metzler, Ralf and Oshanin, Gleb), World Scientific, New Jersey, NJ, 2020 (incollection)

Paper Video link (url) [BibTex]

Image-guided Neural Object Rendering

Thies, J., Zollhöfer, M., Theobalt, C., Stamminger, M., Nießner, M.

In International Conference on Learning Representations, 2020 (incollection)

Abstract

We propose a learned image-guided rendering technique that combines the benefits of image-based rendering and GAN-based image synthesis. The goal of our method is to generate photo-realistic re-renderings of reconstructed objects for virtual and augmented reality applications (e.g., virtual showrooms, virtual tours and sightseeing, the digital inspection of historical artifacts). A core component of our work is the handling of view-dependent effects. Specifically, we directly train an object-specific deep neural network to synthesize the view-dependent appearance of an object. As input data we are using an RGB video of the object. This video is used to reconstruct a proxy geometry of the object via multi-view stereo. Based on this 3D proxy, the appearance of a captured view can be warped into a new target view as in classical image-based rendering. This warping assumes diffuse surfaces, in case of view-dependent effects, such as specular highlights, it leads to artifacts. To this end, we propose EffectsNet, a deep neural network that predicts view-dependent effects. Based on these estimations, we are able to convert observed images to diffuse images. These diffuse images can be projected into other views. In the target view, our pipeline reinserts the new view-dependent effects. To composite multiple reprojected images to a final output, we learn a composition network that outputs photo-realistic results. Using this image-guided approach, the network does not have to allocate capacity on ``remembering’’ object appearance, instead it learns how to combine the appearance of captured images. We demonstrate the effectiveness of our approach both qualitatively and quantitatively on synthetic as well as on real data.

ncs

ncs Thies, J., Zollhöfer, M., Theobalt, C., Stamminger, M., Nießner, M. Image-guided Neural Object Rendering In International Conference on Learning Representations, 2020 (incollection)

Paper Video link (url) [BibTex]

Soft Microrobots Based on Photoresponsive Materials

Palagi, S.

In Mechanically Responsive Materials for Soft Robotics, pages: 327-362, (Editors: Koshima, Hideko), Wiley-VCH, Weinheim, 2020 (incollection)

pf Palagi, S. Soft Microrobots Based on Photoresponsive Materials In Mechanically Responsive Materials for Soft Robotics, pages: 327-362, (Editors: Koshima, Hideko), Wiley-VCH, Weinheim, 2020 (incollection)