Events & Talks

Talk 23-10-2018 Learning to Act with Confidence Actively acquiring decision-relevant information is a key capability of intelligent systems, and plays a central role in the scientific process. In this talk I will present research from my group on this topic at the intersection of statistical learning, optimization and decision making. In particular, I will discuss how statistical confidence bounds can guide data acquisition in a principled way to make effective and reliable decisions in a variety of complex domains. I will also discuss several applications, ranging from autonomously guiding wetlab experiments in protein function optim...

Max Planck Lecture 22-10-2018 Autonomous Robots that Walk and Fly While robots are already doing a wonderful job as factory workhorses, they are now gradually appearing in our daily environments and offering their services as autonomous cars, delivery drones, helpers in search and rescue and much more. Katherine J. Kuchenbecker Matthias Tröndle Ildikó Papp-Wiedmann Barbara Kettemann

Intelligent Control Systems Talk 18-10-2018 Scalable Methods for Monitoring and Controlling Large-Scale Phenomena What do forest fires, disease outbreaks, robot swarms, and social networks have in common? How can we develop a common set of tools for these applications? In this talk, I will first introduce a modeling framework that describes large-scale phenomena and which is based on the idea of "local interactions." I will then describe my work on creating estimation and control methods for a single agent and for a cooperative team of autonomous agents. In particular, these algorithms are scalable as the solution does not change if the number of agents or environment size changes. Forest fires and the... Sebastian Trimpe

Max Planck Lecture 12-10-2018 Transparent Amorphous Oxide Semiconductors: from materials design to implementation to state of the art displays Thin film transistor (TFTs) is a fundamental building block in electronic circuits. Since the specification for TFTs to drive the pixel of flat panel displays rather differs from that for CPUs and memories because of their large dimension.

Haptic Intelligence Talk 05-10-2018 FEA-based Design of Continuum Structures for Optimal Dynamic Properties Continuum structures need to be designed for optimal vibrational characteristics in various fields. Recent developments in the finite element analysis (FEA) and numerical optimization methods allow creating more accurate computational models, which favors designing superior systems and reduces the need for experimentation. In this talk, I will present my work on FEA-based optimization of thin shell structures for improved dynamic properties where the focus will be on laminated composites. I will initially explain multi-objective optimization strategies for enhancing load-carrying and vibrat... Katherine J. Kuchenbecker

Haptic Intelligence Talk 05-10-2018 Interactive and Effective Representation of Digital Content through Touch using Local Tactile Feedback The increasing availability of on-line resources and the widespread practice of storing data over the internet arise the problem of their accessibility for visually impaired people. A translation from the visual domain to the available modalities is therefore necessary to study if this access is somewhat possible. However, the translation of information from vision to touch is necessarily impaired due to the superiority of vision during the acquisition process. Yet, compromises exist as visual information can be simplified, sketched. A picture can become a map. An object can become a geom... Katherine J. Kuchenbecker

Haptic Intelligence IS Colloquium 04-10-2018 Medical Robots with a Haptic Touch – First Experiences with the FLEXMIN System The FLEXMIN haptic robotic system is a single-port tele-manipulator for robotic surgery in the small pelvis. Using a transanal approach it allows bi-manual tasks such as grasping, monopolar cutting, and suturing with a footprint of Ø 160 x 240 mm³. Forces up to 5 N in all direction can be applied easily. In addition to provide low latency and highly dynamic control over its movements, high-fidelity haptic feedback was realised using built-in force sensors, lightweight and friction-optimized kinematics as well as dedicated parallel kinematics input devices. After a brief description of the s... Katherine J. Kuchenbecker

IS Colloquium 04-10-2018 - 04-09-2018 Soft Feel by Soft Robotic Hand: New way of robotic sensing This lecture will show some interesting examples how soft body/skin will change your idea of robotic sensing. Soft Robotics does not only discuss about compliance and safety; soft structure will change the way to categorize objects by dynamic exploration and enables the robot to learn sense of slip. Soft Robotics will entirely change your idea how to design sensing and open up a new way to understand human sensing. Ardian Jusufi

Intelligent Control Systems Talk 01-10-2018 Private Federated Learning With the expanding collection of data, organisations are becoming more and more aware of the potential gain of combining their data. Analytic and predictive tasks, such as classification, perform more accurately if more features or more data records are available, which is why data providers have an interest in joining their datasets and learning from the obtained database. However, this rising interest for federated learning also comes with an increasing concern about security and privacy, both from the consumers whose data is used, and from the data providers who are liable for protecting... Sebastian Trimpe

Physical Intelligence Talk 24-09-2018 Dexterous and non contact micromanipulation for micro-nano-assembly and biomedical applications This talk presents an overview of recent activities of FEMTO-ST institute in the field of micro-nanomanipulation fo both micro nano assembly and biomedical applications. Microrobotic systems are currently limited by the number of degree of freedom addressed and also are very limited by their throughput. Two ways can be considered to improve both the velocity and the degrees of freedom: non-contact manipulation and dexterous micromanipulation. Indeed in both ways movement including rotation and translation are done locally and are only limited by the micro-nano-objects inertia which is very ...

Perceiving Systems Talk 24-09-2018 Learning to align images and surfaces In this talk I will be presenting recent work on combining ideas from deformable models with deep learning. I will start by describing DenseReg and DensePose, two recently introduced systems for establishing dense correspondences between 2D images and 3D surface models ``in the wild'', namely in the presence of background, occlusions, and multiple objects. For DensePose in particular we introduce DensePose-COCO, a large-scale dataset for dense pose estimation, and DensePose-RCNN, a system which operates at multiple frames per second on a single GPU while handling multiple humans simultaneo... Vassilis Choutas

Event 18-09-2018 - 20-09-2018 Special Symposium on Intelligent Systems 2018 Special Symposium on Intelligent Systems 2018 Michael Black Metin Sitti

Event 15-09-2018 Open House in Stuttgart Erleben Sie Grundlagenforschung hautnah! Linda Behringer

Event 15-09-2018 Open House in Tübingen Come and visit our labs and learn about our research! Claudia Daefler Julia Braun Johannes Steinle

Event 14-09-2018 Max Planck Day in Tübingen Symposium "AI and society" - Science Slam - Light Installation - Get-together on the Max Planck Campus in Tübingen Claudia Daefler Johannes Steinle Julia Braun

Event 14-09-2018 Science Slam on the Max Planck Day in Stuttgart Wir feiern den Max-Planck-Tag am 14. September 2018 mit einem Science Slam für Schüler (ab Klasse 9) und ihre Lehrer. Dort können sie spannende Grundlagenforschung LIVE auf der Bühne erleben! Linda Behringer

Event 14-09-2018 Symposium Artificial Intelligence and Society Max-Planck-Tag 2018</spam> The <a href="https://is.mpg.de/en/pages/ki-symposium-videos">accompanying videos</a> for the Symposium Artificial Intelligence and Society have been compiled on an <a href="https://is.mpg.de/en/pages/ki-symposium-videos">extra page.</a> Julia Braun Claudia Daefler Bernhard Schölkopf

Perceiving Systems Talk 07-09-2018 Visual Reconstruction and Image-Based Rendering The reconstruction of 3D scenes and their appearance from imagery is one of the longest-standing problems in computer vision. Originally developed to support robotics and artificial intelligence applications, it has found some of its most widespread use in support of interactive 3D scene visualization. One of the keys to this success has been the melding of 3D geometric and photometric reconstruction with a heavy re-use of the original imagery, which produces more realistic rendering than a pure 3D model-driven approach. In this talk, I give a retrospective of two decades of research in ... Mohamed Hassan

Perceiving Systems Talk 27-07-2018 Imitation of Human Motion Planning Humans act upon their environment through motion, the ability to plan their movements is therefore an essential component of their autonomy. In recent decades, motion planning has been widely studied in robotics and computer graphics. Nevertheless robots still fail to achieve human reactivity and coordination. The need for more efficient motion planning algorithms has been present through out my own research on "human-aware" motion planning, which aims to take the surroundings humans explicitly into account. I believe imitation learning is the key to this particular problem as it allows to ...

Perceiving Systems Talk 24-07-2018 New Ideas for Stereo Matching of Untextured Scenes Two talks for the price of one! I will present my recent work on the challenging problem of stereo matching of scenes with little or no surface texture, attacking the problem from two very different angles. First, I will discuss how surface orientation priors can be added to the popular semi-global matching (SGM) algorithm, which significantly reduces errors on slanted weakly-textured surfaces. The orientation priors serve as a soft constraint during matching and can be derived in a variety of ways, including from low-resolution matching results and from monocular analysis and Manhatta... Anurag Ranjan

Perceiving Systems Talk 16-07-2018 DensePose: Dense Human Pose Estimation In The Wild Non-planar object deformations result in challenging but informative signal variations. We aim to recover this information in a feedforward manner by employing discriminatively trained convolutional networks. We formulate the task as a regression problem and train our networks by leveraging upon manually annotated correspondences between images and 3D surfaces. In this talk, the focus will be on our recent work "DensePose", where we form the "COCO-DensePose" dataset by introducing an efficient annotation pipeline to collect correspondences between 50K persons appearing in the COCO dataset a... Georgios Pavlakos

Talk 13-07-2018 Household Assistants: the Path from the Care-o-bot Vision to First Products In 1995 Fraunhofer IPA embarked on a mission towards designing a personal robot assistant for everyday tasks. In the following years Care-O-bot developed into a long-term experiment for exploring and demonstrating new robot technologies and future product visions. The recent fourth generation of the Care-O-bot, introduced in 2014 aimed at designing an integrated system which addressed a number of innovations such as modularity, “low-cost” by making use of new manufacturing processes, and advanced human-user interaction. Some 15 systems were built and the intellectual property (IP) generated... Katherine J. Kuchenbecker Ildikó Papp-Wiedmann Matthias Tröndle Claudia Daefler

Talk 13-07-2018 Interactive Visualization – A Key Discipline for Big Data Analysis Big Data has become the general term relating to the benefits and threats which result from the huge amount of data collected in all parts of society. While data acquisition, storage and access are relevant technical aspects, the analysis of the collected data turns out to be at the core of the Big Data challenge. Automatic data mining and information retrieval techniques have made much progress but many application scenarios remain in which the human in the loop plays an essential role. Consequently, interactive visualization techniques have become a key discipline of Big Data analysis and... Katherine J. Kuchenbecker Ildikó Papp-Wiedmann Matthias Tröndle Claudia Daefler

Talk 13-07-2018 Learning Control for Intelligent Physical Systems Modern technology allows us to collect, process, and share more data than ever before. This data revolution opens up new ways to design control and learning algorithms, which will form the algorithmic foundation for future intelligent systems that shall act autonomously in the physical world. Starting from a discussion of the special challenges when combining machine learning and control, I will present some of our recent research in this exciting area. Using the example of the Apollo robot learning to balance a stick in its hand, I will explain how intelligent agents can learn new behav... Katherine J. Kuchenbecker Ildikó Papp-Wiedmann Matthias Tröndle Claudia Daefler

Talk 13-07-2018 Smart Magnetic Soft Material and its Application in Miniature Robot Katherine J. Kuchenbecker Ildikó Papp-Wiedmann Matthias Tröndle Claudia Daefler

Event 13-07-2018 Summer Colloquium 2018 MPI-IS cordially invites you to attend the 2018 Intelligent Systems Summer Colloquium Katherine J. Kuchenbecker Matthias Tröndle Ildikó Papp-Wiedmann Claudia Daefler

Talk 13-07-2018 The Critical Role of Atoms at Surfaces and Interfaces: Do we really have control? Can we? With the ubiquity of catalyzed reactions in manufacturing, the emergence of the device laden internet of things, and global challenges with respect to water and energy, it has never been more important to understand atomic interactions in the functional materials that can provide solutions in these spaces. Katherine J. Kuchenbecker Ildikó Papp-Wiedmann Matthias Tröndle Claudia Daefler

Talk 13-07-2018 Variational Inference, GPs and non-linear state space models Gaussian Processes are a principled, practical, probabilistic approach to learning in flexible non-parametric models and have found numerous applications in regression, classification, unsupervised learning and reinforcement learning. Inference, learning and prediction can be done exactly on small data sets with Gaussian likelihood. In more realistic application with large scale data and more complicated likelihoods approximations are necessary. The variational framework for approximate inference in Gaussian processes has emerged recently as a highly effective and practical tool. I will rev... Philipp Hennig

Dynamic Locomotion Talk 09-07-2018 Robin Thandiackal: Modeling anguilliform swimming, robotic swimming Exciting talk on modeling anguilliform swimming, robotic testing. Steve Heim Alexander Badri-Spröwitz

Autonomous Vision Talk 06-07-2018 Representing and Explaining Novel Concepts With Minimal Supervision Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text; contemporary vision-language models can describe image content but fail to take into account class-discriminative image aspects which justify visual predictions. In this talk, I will present my past and current work on Zero-Shot Learning, Vision and Language for Generative Modeling and Explainable Artificial Intelligence in that (1) how we can generalize the image... Andreas Geiger

Perceiving Systems Talk 03-07-2018 Structure-Aware Shape Synthesis Complex shapes can can be summarized using a coarsely defined structure which is consistent and robust across variety of observations. However, existing synthesis techniques do not consider structural decomposition during synthesis, causing generation of implausible or structurally unrealistic shapes. We explore how structure-aware reasoning can benefit existing generative techniques for complex 2D and 3D shapes. We evaluate our methodology on a 3D dataset of chairs and a 2D dataset of typefaces. Sergi Pujades

Haptic Intelligence IS Colloquium 02-07-2018 The Computational Skin. Tactile Perception based on Slip Movements. Touch requires mechanical contact and is governed by the physics of friction. Frictional movements may convert the continuous 3D profile of textural objects into discrete and probabilistic movement events of the viscoelastic integument (skin/hair) called stick-slip movements (slips). This complex transformation may further be determined by the microanatomy and the active movements of the sensing organ. Thus, the integument may realize a computation, transforming the tactile world in a context dependent way - long before it even activates neurons. The possibility that the tactile world is pe... Katherine J. Kuchenbecker

Autonomous Learning Talk 28-06-2018 Discrete approximations in optimal control: From Runge Kutta to Pseudospectral Methods Optimal control problems are often too complex to solve analytically. Computational methods usually replace the continuous infinite dimensional problem by a finite dimensional discrete approximation. The talk will survey classical discretization techniques based on a Runge-Kutta approximation to the differential equations (an h-method) and then introduce recent approximations based on collocation at the roots of orthogonal polynomials (a p-method). The best approximations are often achieved using an hp-framework that combines the best features of both approaches. Numerical results using t... Jia-Jie Zhu

Haptic Intelligence IS Colloquium 20-06-2018 Haptic Engineering and Science at Multiple Scales I will describe recent research in my lab on haptics and robotics. It has been a longstanding challenge to realize engineering systems that can match the amazing perceptual and motor feats of biological systems for touch, including the human hand. Some of the difficulties of meeting this objective can be traced to our limited understanding of the mechanics, and to the high dimensionality of the signals, and to the multiple length and time scales - physical regimes - involved. An additional source of richness and complication arises from the sensitive dependence of what we feel on what ... Katherine J. Kuchenbecker

Talk 18-06-2018 Less-artificial intelligence

Probabilistic Numerics Talk 15-06-2018 An approach to the text normalization problem making use of deep learning techniques The problem of text normalization is simple to understand: transform a given arbitrary text into its spoken form. In the context of text-to-speech systems – that we will focus on – this can be exemplified by turning the text “$200” into “two hundred dollars”. Lately, the interest of solving this problem with deep learning techniques has raised since it is a highly context-dependent problem that is still being solved by ad-hoc solutions. So much so that Google even started a contest in the web Kaggle to solve this problem. In this talk we will see how this problem has been approached as p... Philipp Hennig

Statistical Learning Theory Talk 15-06-2018 Understanding Regularized Spectral Clustering via Graph Conductance This paper uses the relationship between graph conductance and spectral clustering to study (i) the failures of spectral clustering and (ii) the benefits of regularization. The explanation is simple. Sparse and stochastic graphs create a lot of small trees that are connected to the core of the graph by only one edge. Graph conductance is sensitive to these noisy "dangling sets." Spectral clustering inherits this sensitivity. The second part of the paper starts from a previously proposed form of regularized spectral clustering and shows that it is related to the graph conductance on a "regul... Damien Garreau

Perceiving Systems Talk 14-06-2018 Quantifying the risk of collision for self driving cars Ahmed Osman

Haptic Intelligence Workshop 13-06-2018 From Fingertip Mechanics to Tactile Sensation It is well known that the dynamics of the interacting finger mediate the human tactile sensation of materials and textures but its contact dynamics also contribute to other aspects of human cognition such as proprioceptive perception and our capacity to dexterously manipulate objects. The broad range of perceptual phenomena stemming from finger mechanics makes it essential to develop further our understanding of the finger behavior during interaction and its perceptual consequences. David Gueorguiev

Talk 11-06-2018 Double Machine Learning with two Applications: Transformation Models and Gaussian Graphical Models in High-Dimensional Settings In this talk first an introduction to the double machine learning framework is given. This allows inference on parameters in high-dimensional settings. Then, two applications are given, namely transformation models and Gaussian graphical models in high-dimensional settings. Both kind of models are widely used by practitioners. As high-dimensional data sets become more and more available, it is important to allow situations where the number of parameters is large compared to the sample size.

Empirical Inference Talk 11-06-2018 Double Machine Learning with two Applications: Transformation Models and Gaussian Graphical Models in High-Dimensional Settings In this talk first an introduction to the double machine learning framework is given. This allows inference on parameters in high-dimensional settings. Then, two applications are given, namely transformation models and Gaussian graphical models in high-dimensional settings. Both kind of models are widely used by practitioners. As high-dimensional data sets become more and more available, it is important to allow situations where the number of parameters is large compared to the sample size. Philipp Geiger

Empirical Inference IS Colloquium 11-06-2018 Learning Representations for Hyperparameter Transfer Learning Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, Gaussian process-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs. After a brief intro to BO and an overview of several use cases at Amazon, I will discuss a multi-task adaptive Bayesian linear regression model, whose computational complexity is ... Isabel Valera

Perceiving Systems IS Colloquium 08-06-2018 Lessons from the visual system to understand (and help) the brain Visual perception involves a complex interaction between feedforward and feedback processes. A mechanistic understanding of these processing, and its limitations, is a necessary first step towards elucidating key aspects of perceptual functions and dysfunctions. In this talk, I will review our ongoing effort towards the understanding of how feedback visual processing operates at the level of the thalamus, a dynamic relay station halfway between the retina and the cortex. I will present experimental evidence from several recent electrophysiology studies performed on subjects engaged in ... Daniel Cudeiro

Talk 07-06-2018 Single Entity Resolution Valving of Nanoscopic Species in Liquids Investigations and control of biological and synthetic nanoscopic species in liquids at the ultimate resolution of single entity, are important in diverse fields such as biology, medicine, physics, chemistry and emerging field of nanorobotics. Progress made to date on trapping and/or manipulating nanoscopic objects includes methods that use permanently imposed force fields of various kinds, such as optical, electrical and magnetic forces, to counteract their inherent Brownian motion. Peer Fischer Ardian Jusufi

Haptic Intelligence Talk 05-06-2018 Making Sense of the Physical World with High-Resolution Tactile Sensing Why cannot the current robots act intelligently in the real-world environment? A major challenge lies in the lack of adequate tactile sensing technologies. Robots need tactile sensing to understand the physical environment, and detect the contact states during manipulation. Progress requires advances in the sensing hardware, but also advances in the software that can exploit the tactile signals. We developed a high-resolution tactile sensor, GelSight, which measures the geometry and traction field of the contact surface. For interpreting the high-resolution tactile signal, we utilize both t... Katherine J. Kuchenbecker

Haptic Intelligence IS Colloquium 28-05-2018 Making Haptics and its Design Accessible Today’s advances in tactile sensing and wearable, IOT and context-aware computing are spurring new ideas about how to configure touch-centered interactions in terms of roles and utility, which in turn expose new technical and social design questions. But while haptic actuation, sensing and control are improving, incorporating them into a real-world design process is challenging and poses a major obstacle to adoption into everyday technology. Some classes of haptic devices, e.g., grounded force feedback, remain expensive and limited in range. I’ll describe some recent highlights of an o... Katherine J. Kuchenbecker

Perceiving Systems IS Colloquium 25-05-2018 Digital Humans At Disney Research Disney Research has been actively pushing the state-of-the-art in digitizing humans over the past decade, impacting both academia and industry. In this talk I will give an overview of a selected few projects in this area, from research into production. I will be talking about photogrammetric shape acquisition and dense performance capture for faces, eye and teeth scanning and parameterization, as well as physically based capture and modelling for hair and volumetric tissues. Timo Bolkart

Empirical Inference Talk 14-05-2018 Machine learning in cognitive neuroscience: questions, challenges and potential opportunities In this talk I will describe the main types of research questions and neuroimaging tools used in my work in human cognitive neuroscience (with foci in audition and sleep), some of the existing approaches used to analyze our data, and their limitations. I will then discuss the main practical obstacles to applying machine learning methods in our field. Several of my ongoing and planned projects include research questions that could be addressed and perhaps considerably extended using machine learning approaches; I will describe some specific datasets and problems, with the goal of exploring i... Mara Cascianelli

Perceiving Systems Talk 27-04-2018 Constructing Artificial Characters - Traditional versus Deep Learning Approaches The definition of art has been debated for more than 1000 years, and continues to be a puzzle. While scientific investigations offer hope of resolving this puzzle, machine learning classifiers that discriminate art from non-art images generally do not provide an explicit definition, and brain imaging and psychological theories are at present too coarse to provide a formal characterization. In this work, rather than approaching the problem using a machine learning approach trained on existing artworks, we hypothesize that art can be defined in terms of preexisting properties of the visual co... Michael Black

Perceiving Systems Talk 26-04-2018 Automatic Understanding of the Visual World One of the central problems of artificial intelligence is machine perception, i.e., the ability to understand the visual world based on input from sensors such as cameras. In this talk, I will present recent progress with respect to data generation using weak annotations, motion information and synthetic data. I will also discuss our recent results for action recognition, where human tubes and tubelets have shown to be successful. Our tubelets moves away from state-of-the-art frame based approaches and improve classification and localization by relying on joint information from several fram... Ahmed Osman

Research

Departments

Research Groups

People

Contact

Our Institute

Our History

Career

Doctoral Programs

Training

Service Units

Central Scientific Facilities

Workshops

Campus Services

Impact

Cooperation

Partners and Initiatives