Events & Talks

Perceiving Systems Talk Sven Dickinson 29-05-2017 The Perceptual Advantage of Symmetry for Scene Perception Human observers can classify photographs of real-world scenes after only a very brief exposure to the image (Potter & Levy, 1969; Thorpe, Fize, Marlot, et al., 1996; VanRullen & Thorpe, 2001). Line drawings of natural scenes have been shown to capture essential structural information required for successful scene categorization (Walther et al., 2011). Here, we investigate how the spatial relationships between lines and line segments in the line drawings affect scene classification. In one experiment, we tested the effect of removing either the junctions or the middle segments between juncti... Ahmed Osman

Perceiving Systems Talk Yael Moses 24-05-2017 Dynamic Scene Analysis Using CrowdCam Data Dynamic events such as family gatherings, concerts or sports events are often photographed by a group of people. The set of still images obtained this way is rich in dynamic content. We consider the question of whether such a set of still images, rather the traditional video sequences, can be used for analyzing the dynamic content of the scene. This talk will describe several instances of this problem, their solutions and directions for future studies. In particular, we will present a method to extend epipolar geometry to predict location of a moving feature in CrowdCam images. The method ... Jonas Wulff

Talk Guido Montúfar 24-05-2017 Geometry of Neural Networks Deep Learning is one of the most successful machine learning approaches to artificial intelligence. In this talk I discuss the geometry of neural networks as a way to study the success of Deep Learning at a mathematical level and to develop a theoretical basis for making further advances, especially in situations with limited amounts of data and challenging problems in reinforcement learning. I present a few recent results on the representational power of neural networks and then demonstrate how to align this with structures from perception-action problems in order to obtain more efficient ... Jane Walters

Probabilistic Numerics Talk Dino Sejdinovic 22-05-2017 Inference with Kernel Embeddings Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric hypothesis testing and for learning on distributional inputs. I will give an overview of this framework and present some of its recent applications within the context of approximate Bayesian inference. Further, I will discuss a recent modification of MMD which aims to encode invariance to additive symmetric noise and leads to learning on distributions robust to the distributional covariate shift, e.g. where measurement noise on the... Philipp Hennig

Autonomous Motion Talk Dr. Raj Madhavan 19-05-2017 Humanitarian Technologies & Technology-Public Policy Considerations for Societal Good Many of the existing Robotics & Automation (R&A) technologies are at a sufficient level of maturity and are widely accepted by the academic (and to a lesser extent by the industrial) community after having undergone the scientific rigor and peer reviews that accompany such works. I believe that most of the past and current research and development efforts in robotics and automation have been squarely aimed at increasing the Standard of Living (SoL) in developed economies where housing, running water, transportation, schools, access to healthcare, to name a few, are taken for granted... Ludovic Righetti

Perceiving Systems Talk Cordelia Schmid 19-05-2017 Learning to segment moving objects This talk addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal features in a video sequence respectively, while the memory module captures the evolution of objects over time. The module to build a “visual memory” in video, i.e., a joint representation of all the video frames, is realized with a convolutional recurrent unit learned from a small number of training video sequences. Given video frames as input, our approach... Osman Ulusoy

Max Planck Lecture Robert J. Birgeneau 18-05-2017 Superconductors Old and New Solid State Physics is a field which continuously renews itself through the discovery of new materials and new phenomena. This has been particularly true for the subfield of superconductivity.

Autonomous Vision Talk Carolin Schmitt 11-05-2017 Biquadratic Forms and Semi-Definite Relaxations I'll present my master thesis "Biquadratic Forms and Semi-Definite Relaxations". It is about biquadratic optimization programs (which are NP-hard generally) and examines a condition under which there exists an algorithm that finds a solution to every instance of the problem in polynomial time. I'll present a counterexample for which this is not possible generally and face the question of what happens if further knowledge about the variables over which we optimise is applied. Fatma Güney

Perceiving Systems Talk Björn Andres 08-05-2017 Graph Decomposition Problems in Image Analysis A large part of image analysis is about breaking things into pieces. Decompositions of a graph are a mathematical abstraction of the possible outcomes. This talk is about optimization problems whose feasible solutions define decompositions of a graph. One example is the correlation clustering problem whose feasible solutions relate one-to-one to the decompositions of a graph, and whose objective function puts a cost or reward on neighboring nodes ending up in distinct components. This talk shows applications of this problem and proposed generalizations to diverse image analysis tasks. It sk... Christoph Lassner

Talk Rahul Chaudhari and David Gueorguiev 05-05-2017 Haptic Texture Compression and Perceptual Quality Evaluation / Understanding Friction Based Haptic Feedback Colloquium on haptics: Two guests of the department "Haptic Intelligence" (Dept. Kuchenbecker), will each give a short talk this Friday (May 5) in Tübingen. The talks will be broadcasted to Stuttgart, room 2 P4.

Perceiving Systems Talk Gul Varol 04-05-2017 Learning from Synthetic Humans Estimating human pose, shape, and motion from images and video are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL: a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 m... Dimitris Tzionas

Autonomous Motion Talk Sylvain Calinon 27-04-2017 Robot learning from few demonstrations by exploiting the structure and geometry of data Human-centric robotic applications often require the robots to learn new skills by interacting with the end-users. From a machine learning perspective, the challenge is to acquire skills from only few interactions, with strong generalization demands. It requires: 1) the development of intuitive active learning interfaces to acquire meaningful demonstrations; 2) the development of models that can exploit the structure and geometry of the acquired data in an efficient way; 3) the development of adaptive control techniques that can exploit the learned task variations and coordination patterns.... Ludovic Righetti

Autonomous Motion Talk Dr. Andrea Del Prete 25-04-2017 Multi-contact locomotion control for legged robots This talk will survey recent work to achieve multi-contact locomotion control of humanoid and legged robots. I will start by presenting some results on robust optimization-based control. We exploited robust optimization techniques, either stochastic or worst-case, to improve the robustness of Task-Space Inverse Dynamics (TSID), a well-known control framework for legged robots. We modeled uncertainties in the joint torques, and we immunized the constraints of the system to any of the realizations of these uncertainties. We also applied the same methodology to ensure the balance of the robot ... Ludovic Righetti

Probabilistic Numerics Talk Philipp Berens 24-04-2017 Towards a complete parts list: multimodal data science in the retina The retina in the eye performs complex computations, to transmit only behaviourally relevant information about our visual environment to the brain. These computations are implemented by numerous different cell types that form complex circuits. New experimental and computational methods make it possible to study the cellular diversity of the retina in detail – the goal of obtaining a complete list of all the cell types in the retina and, thus, its “building blocks”, is within reach. I will review our recent contributions in this area, showing how analyzing multimodal datasets from electron m... Philipp Hennig

Perceiving Systems Talk Yanxi Liu 13-04-2017 Dancing with TURKs or Tai Chi with a Master? From gait, dance to martial art, human movements provide rich, complex yet coherent spatiotemporal patterns reflecting characteristics of a group or an individual. We develop computer algorithms to automatically learn such quality discriminative features from multimodal data. In this talk, I present a trilogy on learning from human movements: (1) Gait analysis from video data: based on frieze patterns (7 frieze groups), a video sequence of silhouettes is mapped into a pair of spatiotemporal patterns that are near-periodic along the time axis. A group theoretical analysis of periodic pat... Laura Sevilla Siyu Tang

Perceiving Systems Talk Silvia Zuffi 07-04-2017 Building Multi-Family Animal Models There has been significant prior work on learning realistic, articulated, 3D statistical shape models of the human body. In contrast, there are few such models for animals, despite their many applications in biology, neuroscience, agriculture, and entertainment. The main challenge is that animals are much less cooperative subjects than humans: the best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals. In the talk I will illustrate how we extend a state-of-the-art articulated 3D human body model (SMPL) to animals ...

Talk Moritz Hardt, Google Brain / University of California, Berkeley 04-04-2017 Discovering discrimination in supervised learning Moritz Hardt will review some progress and challenges towards preventing discrimination based on sensitive attributes in supervised learning. Michael Black Stefan Schaal Bernhard Schölkopf

Autonomous Motion Symposium 27-03-2017 - 29-03-2017 Interactive Multisensory Object Perception for Embodied Agents Symposium at the AAAI Spring Symposium Series in 2017 at Stanford University. Jeannette Bohg

Autonomous Motion Talk Todor Stoyanov and Robert Krug 16-03-2017 Integrated Perception and Control for Autonomous Manipulation In this talk we will give an overview of research efforts within autonomous manipulation at the AASS Research Center, Örebro University, Sweden. We intend to give a holistic view on the historically separated subjects of robot motion planning and control. In particular, viewing motion behavior generation as an optimal control problem allows for a unified formulation that is uncluttered by a-priori domain assumptions and simplified solution strategies. Furthermore, We will also discuss the problems of workspace modeling and perception and how to integrate them in the overarching problem o... Ludovic Righetti

Empirical Inference IS Colloquium John Cunningham 06-03-2017 Statistical testing of epiphenomena for multi-index data As large tensor-variate data increasingly become the norm in applied machine learning and statistics, complex analysis methods similarly increase in prevalence. Such a trend offers the opportunity to understand more intricate features of the data that, ostensibly, could not be studied with simpler datasets or simpler methodologies. While promising, these advances are also perilous: these novel analysis techniques do not always consider the possibility that their results are in fact an expected consequence of some simpler, already-known feature of simpler data (for example, treating the te... Philipp Hennig

Autonomous Motion Talk Matteo Turchetta 22-02-2017 Safe Exploration in Finite Markov Decision Processes with Gaussian Processes In classical reinforcement learning agents accept arbitrary short term loss for long term gain when exploring their environment. This is infeasible for safety critical applications such as robotics, where even a single unsafe action may cause system failure or harm the environment. In this work, we address the problem of safely exploring finite Markov decision processes (MDP). We define safety in terms of an a priori unknown safety constraint that depends on states and actions and satisfies certain regularity conditions expressed via a Gaussian process prior. We develop a novel algo... Sebastian Trimpe

Empirical Inference IS Colloquium Surjo R. Soekadar 06-02-2017 Brain-machine interfaces: New treatment options for psychiatric disorders Moritz Grosse-Wentrup

Autonomous Vision Event 06-02-2017 - 09-02-2017 Computer Vision Retreat Andreas Geiger

Autonomous Motion Talk Dr. Thomas Besselmann 13-01-2017 Power meets Computation This is the story of the novel model predictive control (MPC) solution for ABB’s largest drive, the Megadrive LCI. LCI stands for load commutated inverter, a type of current source converter which powers large machineries in many industries such as marine, mining or oil & gas. Starting from a small software project at ABB Corporate Research, this novel control solution turned out to become the first time ever MPC was employed in a 48 MW commercial drive. Subsequently it was commissioned at Kollsnes, a key facility of the natural gas delivery chain, in order to increase the plant’s a... Sebastian Trimpe

Empirical Inference IS Colloquium Fabien Lotte 19-12-2016 Human Learning and Alternative Applications Towards Usable Electroencephalography-based Brain-Computer Interfaces Brain-Computer Interfaces (BCIs) are systems that can translate brain activity patterns of a user into messages or commands for an interactive application. Such brain activity is typically measured using Electroencephalography (EEG), before being processed and classified by the system. EEG-based BCIs have proven promising for a wide range of applications ranging from communication and control for motor impaired users, to gaming targeted at the general public, real-time mental state monitoring and stroke rehabilitation, to name a few. Despite this promising potential, BCIs are still scarcely...

Symposium 13-12-2016 - 16-12-2016 Special Symposium on Intelligent Systems

Talk Ralf Nagel 12-12-2016 Bayesian Inference for Uncertainty Quantification and Inverse Problems The predictive simulation of engineering systems increasingly rests on the synthesis of physical models and experimental data. In this context, Bayesian inference establishes a framework for quantifying the encountered uncertainties and fusing the available information. A summary and discussion of some recently emerged methods for uncertainty propagation (polynomial chaos expansions) and related MCMC-free techniques for posterior computation (spectral likelihood expansions, optimal transportation theory) is presented. Philipp Hennig

Autonomous Vision Talk Laura Leal-Taixé 08-12-2016 Deep Learning and its Relationship with Time In this talk I am going to present the work we have been doing at the Computer Vision Lab of the Technical University of Munich which started as an attempt to better deal with videos (and therefore the time domain) within neural network architectures. Joel Janai

Perceiving Systems Talk Kathleen Robinette 05-12-2016 Modeling Opportunities for Effective Product Development & Sizing Kathleen is the creator of the well-known CAESAR anthropomorphic dataset and is an expert on body shape and apparel fit. Javier Romero

Autonomous Motion Talk Wallace M. Bessa 01-12-2016 - 01-11-2016 Intelligent control of uncertain underactuated mechanical systems Underactuated mechanical systems (UMS) play an essential role in several branches of industrial activity and their application scope ranges from robotic manipulators and overhead cranes to aerospace vehicles and watercrafts. Despite this broad spectrum of applications, the problem of designing accurate controllers for underactuated systems is, however, much more tricky than for fully actuated ones. Moreover, the dynamic behavior of an UMS is frequently uncertain and highly nonlinear, which in fact makes the design of control schemes for such systems a challenge for conventio... Sebastian Trimpe

Autonomous Vision Talk Carsten Rother 21-11-2016 A Collection of Recent Work: From 6D Pose estimation via MRF-Diversity to zebrafish detection In this talk I will present the portfolio of work we conduct in our lab. Herby, I will present three recent body of work in more detail. This is firstly our work on learning 6D Object Pose estimation and Camera localizing from RGB or RGBD images. I will show that by utilizing the concepts of uncertainty and learning to score hypothesis, we can improve the state of the art. Secondly, I will present a new approach for inferring multiple diverse labeling in a graphical model. Besides guarantees of an exact solution, our method is also faster than existing techniques. Finally, I will present a ... Aseem Behl

Autonomous Vision Talk Bogdan Savchynskyy 21-11-2016 Future of graphical models: more modeling power, parallelization, scalable solvers We propose a new computational framework for combinatorial problems arising in machine learning and computer vision. This framework is a special case of Lagrangean (dual) decomposition, but allows for efficient dual ascent (message passing) optimization. In a sense, one can understand both the framework and the optimization technique as a generalization of those for standard undirected graphical models (conditional random fields). We will make an overview of our recent results and plans for the nearest future. Aseem Behl

Talk Dr. Bogdan Savchynskyy 21-11-2016 Future of graphical models: more modeling power, parallelization, scalable solvers. We propose a new computational framework for combinatorial problems arising in machine learning and computer vision. This framework is a special case of Lagrangean (dual) decomposition, but allows for efficient dual ascent (message passing) optimization. In a sense, one can understand both the framework and the optimization technique as a generalization of those for standard undirected graphical models (conditional random fields). We will make an overview of our recent results and plans for the nearest future. Aseem Behl

Talk Rémi Bardenet 02-11-2016 Monte Carlo with determinantal point processes In this talk, we show that using repulsive random variables, it is possible to build Monte Carlo methods that converge faster than vanilla Monte Carlo. More precisely, we build estimators of integrals, the variance of which decreases as $N^{-1-1/d}$, where $N$ is the number of integrand evaluations, and $d$ is the ambient dimension. To do so, we propose stochastic numerical quadratures involving determinantal point processes (DPPs) associated to multivariate orthogonal polynomials. The proposed method can be seen as a stochastic version of Gauss' quadrature, where samples from a determinant... Alexandra Gessner

Perceiving Systems Talk Hedvig Kjellström 27-10-2016 Factorized Latent Representations for Improved Automated Diagnostics In this talk I will first outline my different research projects. I will then focus on one project with applications in Health, and introduce the Inter-Battery Topic Model (IBTM). Our approach extends traditional topic models by learning a factorized latent variable representation. The structured representation leads to a model that marries benefits traditionally associated with a discriminative approach, such as feature selection, with those of a generative model, such as principled regularization and ability to handle missing data. The factorization is provided by representing data in ter...

Autonomous Motion Talk Chris Atkeson and Akihiko Yamaguchi 19-10-2016 Optical Robot Skin and Whole Body Vision Chris Atkeson will talk about the motivation for optical robot skin and whole-body vision. Akihiko Yamaguchi will talk about a first application, FingerVision. Ludovic Righetti

Talk Jean-Claude Passy 29-09-2016 Numerics in Computational Stellar Astrophysics The importance of computer science in astrophysical research has increased tremendously over the past 15 years. Indeed, as observational facilities and missions are constantly pushing their precision limit, theorists need to provide observers with more and more realistic numerical models. These models need to be verified, validated, and their uncertainties must be assessed. In this talk, I will present the results of two independent numerical studies aiming at solving some fundamental problems in stellar astrophysics. First, I will explain how we have used different 3D hydrodynamics codes t... Raffi Enficiaud

Autonomous Motion Talk Jose R. Medina 27-09-2016 Considering uncertainty in robot decision-making: control and modelling aspects Control under uncertainty is an omnipresent problem in robotics that typically arises when robots must cope with unknown environments/tasks. Robot control typically ignores uncertainty by considering only the expected outcomes of the robot’s internal model. Interestingly, neuroscientist have shown that humans adapt their decisions depending on the level of uncertainty which is not reflected in the expected values, but in higher order statistics. In this talk I will first present an approach to systematically address this problem in the context of stochastic optimal control. I will then giv... Ludovic Righetti

Autonomous Motion Talk Stéphane Caron 19-09-2016 Multi-contact Stability: Support Areas and Volumes for Humanoid Locomotion under Frictional Contacts Humanoid locomotion on horizontal floors was solved by closing the feedback loop on the Zero-tiling Moment Point (ZMP), a measurable dynamic point that needs to stay inside the foot contact area to prevent the robot from falling (contact stability criterion). However, this criterion does not apply to general multi-contact settings, the "new frontier" in humanoid locomotion. In this talk, we will see how the ideas of ZMP and support area can be generalized and applied to multi-contact locomotion. First, we will show how support areas can be calculated in any virtual plane, allowin... Ludovic Righetti

Perceiving Systems Talk Siyu Tang 25-08-2016 Graph decomposition for multi-person tracking, pose estimation and motion segmentation Understanding people in images and videos is a problem studied intensively in computer vision. While continuous progress has been made, occlusions, cluttered background, complex poses and large variety of appearance remain challenging, especially for crowded scenes. In this talk, I will explore the algorithms and tools that enable computer to interpret people's position, motion and articulated poses in the real-world challenging images and videos.More specifically, I will discuss an optimization problem whose feasible solutions define a decomposition of a given graph. I will highlight the a... Naureen Mahmood

Empirical Inference Talk Hannes Nickisch, Philips Research, Hamburg 15-08-2016 Learning Patient-Specific Lumped Models for Interactive Coronary Blood Flow Simulations Coronary artery disease (CAD) is the single leading cause of death worldwide and Cardiac Computed Tomography Angiography (CCTA) is a non-invasive test to rule out CAD using the anatomical characterization of the coronary lesions. Recent studies suggest that coronary lesions’ hemodynamic significance can be assessed by Fractional Flow Reserve (FFR), which is usually measured invasively in the CathLab but can also be simulated from a patient-specific biophysical model based on CCTA data. We learn a parametric lumped model (LM) enabling fast computational fluid dynamic simulations of blood fl...

Perceiving Systems Talk Dimitris Tzionas 04-08-2016 Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses. All components are unified in a single objective function that can be optimized with st... Javier Romero

Autonomous Vision Talk Anton Milan 22-07-2016 Bipartite Matching and Multi-target Tracking Matching between two sets arises in various areas in computer vision, such as feature point matching for 3D reconstruction, person re-identification for surveillance or data association for multi-target tracking. Most previous work focused either on designing suitable features and matching cost functions, or on developing faster and more accurate solvers for quadratic or higher-order problems. In the first part of my talk, I will present a strategy for improving state-of-the-art solutions by efficiently computing the marginals of the joint matching probability. The second part of my talk wi...

Event 11-07-2016 - 13-07-2016 CLS Workshop - Deep Learning: Theory and Practice Workshop in Donaueschingen Peter Vincent Gehler

Event 18-06-2016 Open House - Tag der offenen Tür - Max Planck Campus Tübingen The four institutions on Tübingen Max Planck Campus open their doors to the interested public. Claudia Daefler

Perceiving Systems Talk Timo Bolkart 09-06-2016 Dynamic and Groupwise Statistical Analysis of 3D Faces The accurate reconstruction of facial shape is important for applications such as telepresence and gaming. It can be solved efficiently with the help of statistical shape models that constrain the shape of the reconstruction. In this talk, several methods to statistically analyze static and dynamic 3D face data are discussed. When statistically analyzing faces, various challenges arise from noisy, corrupt, or incomplete data. To overcome the limitations imposed by the poor data quality, we leverage redundancy in the data for shape processing. This is done by processing entire motion seq...

Autonomous Motion Talk Christian Ebenbauer 08-06-2016 Extremum Seeking Control: Theory and Applications in Multi-Agent Systems In many control applications it is the goal to operate a dynamical system in an optimal way with respect to a certain performance criterion. In a combustion engine, for example, the goal could be to control the engine such that the emissions are minimized. Due to the complexity of an engine, the desired operating point is unknown or may even change over time so that it cannot be determined a priori. Extremum seeking control is a learning-control methodology to solve such kind of control problems. It is a model-free method that optimizes the steady-state behavior of a dynamical syste... Sebastian Trimpe

Max Planck Lecture Professor Naomi Ehrich Leonard 06-06-2016 On the Nonlinear Dynamics of Collective Decision-Making in Nature and Design The successful deployment of complex, multi-agent systems requires well-designed, agent-level control strategies that accommodate sensing, communication, and computational limitations on individual agents.

Talk Georg Martius 31-05-2016 Self-organization of behavior in autonomous robot development I am studying the question how robots can autonomously develop skills. Considering children, it seems natural that they have their own agenda. They explore their environment in a playful way, without the necessity for somebody to tell them what to do next. With robots the situation is different. There are many methods to let robots learn to do something, but it is always about learning to do a specific task from a supervision signal. Unfortunately, these methods do not scale well to systems with many degrees of freedom, except a good prestructuring is available. The hypothesis is t... Jane Walters

Autonomous Motion IS Colloquium Angela Schoellig 25-04-2016 Safe Learning Control for Mobile Robots In the last decade, there has been a major shift in the perception, use and predicted applications of robots. In contrast to their early industrial counterparts, robots are envisioned to operate in increasingly complex and uncertain environments, alongside humans, and over long periods of time. In my talk, I will argue that machine learning is indispensable in order for this new generation of robots to achieve high performance. Based on various examples (and videos) ranging from aerial-vehicle dancing to ground-vehicle racing, I will demonstrate the effect of robot learning, and hi... Sebastian Trimpe

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