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 low. It consequently enable to generate 6DOF and to induce high dynamics. The talk presents recent works which have shown that controlled trajectories in non contact manipulation enable to manipulate micro-objects in high speed. Dexterous manipulation on a 4 fingers microtweezers have been also experimented and show that in-hand micromanipulations are possible in micro-nanoscale based on original finger trajectory planning. These two approaches have been applied to perform micro-nano-assemby and biomedical operations
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 simultaneously. I will then present Deforming AutoEncoders, a method for unsupervised dense correspondence estimation. We show that we can disentangle deformations from appearance variation in an entirely unsupervised manner, and also provide promising results for a more thorough disentanglement of images into deformations, albedo and shading. Time permitting we will discuss a parallel line of work aiming at combining grouping with deep learning, and see how both grouping and correspondence can be understood as establishing associations between neurons.
Organizers: Vassilis Choutas
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.
Organizers: Ardian Jusufi
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 system and some of its key aspects, first evaluation results will be presented. In the second half of the talk the Institute of Medical Device Technology will be presented. The institute was founded in July 2017 and has ever since started a number of projects in the field of biomedical actuation, medical systems and robotics and advanced light microscopy. To illustrate this a few snapshots of bits and pieces will be presented that are condensation nuclei for the future.
Organizers: Katherine Kuchenbecker
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 geometrical shape. Under some circumstances, and with a reasonable loss of generality, touch can substitute vision. In particular, when touch substitutes vision, data can be differentiated by adding a further dimension to the tactile feedback, i.e. extending tactile feedback to three dimensions instead of two. This mode has been chosen because it mimics our natural way of following object profiles with fingers. Specifically, regardless if a hand lying on an object is moving or not, our tactile and proprioceptive systems are both stimulated and tell us something about which object we are manipulating, what can be its shape and size. The goal of this talk is to describe how to exploit tactile stimulation to render digital information non visually, so that cognitive maps associated with this information can be efficiently elicited from visually impaired persons. In particular, the focus is to deliver geometrical information in a learning scenario. Moreover, a completely blind interaction with virtual environment in a learning scenario is something little investigated because visually impaired subjects are often passive agents of exercises with fixed environment constraints. For this reason, during the talk I will provide my personal answer to the question: can visually impaired people manipulate dynamic virtual content through touch? This process is much more challenging than only exploring and learning a virtual content, but at the same time it leads to a more conscious and dynamic creation of the spatial understanding of an environment during tactile exploration.
Organizers: Katherine Kuchenbecker
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. This talk will present some recent highlights in the field of autonomous mobile robotics research and touch on some of the great challenges and opportunities. Legged robots are able to overcome the limitations of wheeled or tracked ground vehicles. ETH’s electrically powered legged quadruped robots are designed for high agility, efficiency and robustness in rough terrain. This is realized through an optimal exploitation of the natural dynamics and serial elastic actuation. For fast inspection of complex environments, flying robots are probably the most efficient and versatile devices. However, the limited payload and computing power of drones renders autonomous navigation quite challenging. Thanks to our custom designed visual-inertial sensor, real-time on-board localization, mapping and planning has become feasible and enables our multi-copters and solar-powered fixed wing drones for advanced rescue and inspection tasks or support in precision farming, even in GPS-denied environments.
Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming. In motor control studies, humans or other animals are often marked with reflective markers to assist with computer-based tracking, yet markers are intrusive (especially for smaller animals), and the number and location of the markers must be determined a priori. Here, we present a highly efficient method for markerless tracking based on transfer learning with deep neural networks that achieves excellent results with minimal training data. We demonstrate the versatility of this framework by tracking various body parts in a broad collection of experimental settings: mice odor trail-tracking, egg-laying behavior in drosophila, and mouse hand articulation in a skilled forelimb task. For example, during the skilled reaching behavior, individual joints can be automatically tracked (and a confidence score is reported). Remarkably, even when a small number of frames are labeled (≈200), the algorithm achieves excellent tracking performance on test frames that is comparable to human accuracy.
Organizers: Melanie Feldhofer
Today’s robots have motor abilities and sensors that exceed those of humans in many ways: They move more accurately and faster; their sensors see more and at a higher precision and in contrast to humans they can accurately measure even the smallest forces and torques. Robot hands with three, four, or five fingers are commercially available, and, so are advanced dexterous arms. Indeed, modern motion-planning methods have rendered grasp trajectory generation a largely solved problem. Still, no robot to date matches the manipulation skills of industrial assembly workers despite that manipulation of mechanical objects remains essential for the industrial assembly of complex products. So, why are current robots still so bad at manipulation and humans so good?
Organizers: Katherine Kuchenbecker
Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. Prior methods addressing this problem typically attempt to fit parametric body models with certain priors on pose and shape. In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image. BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Each of them results in performance improvement as demonstrated by our experiments. To evaluate the method, we fit the SMPL model to our network output and show state-of-the-art results on the SURREAL and Unite the People datasets, outperforming recent approaches. Besides achieving state-of-the-art performance, our method also enables volumetric body-part segmentation.
For many service robots, reactivity to changes in their surroundings is a must. However, developing software suitable for dynamic environments is difficult. Existing robotic middleware allows engineers to design behavior graphs by organizing communication between components. But because these graphs are structurally inflexible, they hardly support the development of complex reactive behavior. To address this limitation, we propose Playful, a software platform that applies reactive programming to the specification of robotic behavior. The front-end of Playful is a scripting language which is simple (only five keywords), yet results in the runtime coordinated activation and deactivation of an arbitrary number of higher-level sensory-motor couplings. When using Playful, developers describe actions of various levels of abstraction via behaviors trees. During runtime an underlying engine applies a mixture of logical constructs to obtain the desired behavior. These constructs include conditional ruling, dynamic prioritization based on resources management and finite state machines. Playful has been successfully used to program an upper-torso humanoid manipulator to perform lively interaction with any human approaching it.
Human footsteps can provide a unique behavioural pattern for robust biometric systems. Traditionally, security systems have been based on passwords or security access cards. Biometric recognition deals with the design of security systems for automatic identification or verification of a human subject (client) based on physical and behavioural characteristics. In this talk, I will present spatio-temporal raw and processed footstep data representations designed and evaluated on deep machine learning models based on a two-stream resnet architecture, by using the SFootBD database the largest footstep database to date with more than 120 people and almost 20,000 footstep signals. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). In these scenarios we report state-of-the-art footstep recognition rates.
Organizers: Dimitris Tzionas
Animals are widespread in nature and the analysis of their shape and motion is of importance in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. In our previous SMAL model, we learn animal shape from toys figurines, but toys are limited in number and realism, and not every animal is sufficiently popular for there to be realistic toys depicting it. What is available in large quantities are images and videos of animals from nature photographs, animal documentaries, and webcams. In this talk I will present our recent work for capturing the detailed 3D shape of animals from images alone. Our method extracts significantly more 3D shape detail than previous work and is able to model new species using only a few video frames. Additionally, we extract realistic texture map from images for capturing both animal shape and appearance.
My plan is to present the motivation behind Deep GPs as well as some of the current approximate inference schemes available with their limitations. Then, I will explain how Deep GPs fit into the BayesOpt framework and the specific problems they could potentially solve.
In academic and policy circles, there has been considerable interest in the impact of “big data” on firm performance. We examine the question of how the amount of data impacts the accuracy of Machine Learned models of weekly retail product forecasts using a proprietary data set obtained from Amazon. We examine the accuracy of forecasts in two relevant dimensions: the number of products (N), and the number of time periods for which a product is available for sale (T). Theory suggests diminishing returns to larger N and T, with relative forecast errors diminishing at rate 1/sqrt(N) + 1/sqrt(T) . Empirical results indicate gains in forecast improvement in the T dimension; as more and more data is available for a particular product, demand forecasts for that product improve over time, though with diminishing returns to scale. In contrast, we find an essentially flat N effect across the various lines of merchandise: with a few exceptions, expansion in the number of retail products within a category does not appear associated with increases in forecast performance. We do find that the firm’s overall forecast performance, controlling for N and T effects across product lines, has improved over time, suggesting gradual improvements in forecasting from the introduction of new models and improved technology.
Political science is integrating computational methods like machine learning into its own toolbox. At the same time the awareness rises that the utilization of machine learning algorithms in our daily life is a highly political issue. These two trends - the integration of computational methods into political science and the political analysis of the digital revolution - form the ground for a new transdisciplinary approach: political data science. Interestingly, there is a rich tradition of crossing the borders of the disciplines, as can be seen in the works of Paul Werbos and Herbert Simon (both political scientists). Building on this tradition and integrating ideas from deep learning and Hegel's philosophy of logic a new perspective on causality might arise.
Organizers: Philipp Geiger
We present a novel probabilistic integrator for ordinary differential equations (ODEs) which allows for uncertainty quantification of the numerical error . In particular, we randomise the time steps and build a probability measure on the deterministic solution, which collapses to the true solution of the ODE with the same rate of convergence as the underlying deterministic scheme. The intrinsic nature of the random perturbation guarantees that our probabilistic integrator conserves some geometric properties of the deterministic method it is built on, such as the conservation of first integrals or the symplecticity of the flow. Finally, we present a procedure to incorporate our probabilistic solver into the frame of Bayesian inference inverse problems, showing how inaccurate posterior concentrations given by deterministic methods can be corrected by a probabilistic interpretation of the numerical solution.
Organizers: Hans Kersting