Abstract: Sequential Monte Carlo (SMC) methods (including the particle filters and smoothers) allows us to compute probabilistic representations of the unknown objects in models used to represent for example nonlinear dynamical systems. This talk has three connected parts: 1. A (hopefully pedagogical) introduction to probabilistic modelling of dynamical systems and an explanation of the SMC method. 2. In learning unknown parameters appearing in nonlinear state-space models using maximum likelihood it is natural to make use of SMC to compute unbiased estimates of the intractable likelihood. The challenge is that the resulting optimization problem is stochastic, which recently inspired us to construct a new solution to this problem. 3. A challenge with the above (and in fact with most use of SMC) is that it all quickly becomes very technical. This is indeed the key challenging in spreading the use of SMC methods to a wider group of users. At the same time there are many researchers who would benefit a lot from having access to these methods in their daily work and for those of us already working with them it is essential to reduce the amount of time spent on new problems. We believe that the solution to this can be provided by probabilistic programming. We are currently developing a new probabilistic programming language that we call Birch. A pre-release is available from birch-lang.org/ It allow users to use SMC methods without having to implement the algorithms on their own.
Organizers: Philipp Hennig
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 ongoing effort to understand how to support haptic designers and end-users. These include a wealth of online experimental design tools, and DIY open sourced hardware and accessible means of creating, for example, expressive physical robot motions and evolve physically sensed expressive tactile languages. Elsewhere, we are establishing the value of haptic force feedback in embodied learning environments, to help kids understand physics and math concepts. This has inspired the invention of a low-cost, handheld and large motion force feedback device that can be used in online environments or collaborative scenarios, and could be suitable for K-12 school contexts; this is ongoing research with innovative education and technological elements. All our work is available online, where possible as web tools, and we plan to push our research into a broader openhaptics effort.
Organizers: Katherine Kuchenbecker
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 traditional statistical models and deep neural networks. I will describe my research on both exploration and manipulation. For exploration, I use active touch to estimate the physical properties of the objects. The work has included learning the hardness of artificial objects, as well as estimating the general properties of natural objects via autonomous tactile exploration. For manipulation, I study the robot’s ability to detect slip or incipient slip with tactile sensing during grasping. The research helps robots to better understand and flexibly interact with the physical world.
Organizers: Katherine Kuchenbecker
Gliding evolved at least nine times in mammals. Despite the abundance and diversity of gliding mammals, little is known about their convergent morphology and mechanisms of aerodynamic control. Many gliding animals are capable of impressive and agile aerial behaviors and their flight performance depends on the aerodynamic forces resulting from airflow interacting with a flexible, membranous wing (patagium). Although the mechanisms that gliders use to control dynamic flight are poorly understood, the shape of the gliding membrane (e.g., angle of attack, camber) is likely a primary factor governing the control of the interaction between aerodynamic forces and the animal’s body. Data from field studies of gliding behavior, lab experiments examining membrane shape changes during glides and morphological and materials testing data of gliding membranes will be presented that can aid our understanding of the mechanisms gliding mammals use to control their membranous wings and potentially provide insights into the design of man-made flexible wings.
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 behavior from just a few experimental trails. I will also discuss the need for theoretical guarantees in learning-based control, and how we can obtain them by combining learning and control theory.
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 by over 20 years of research was recently licensed to a start-up. The presentation will review the path from an experimental platform for building up expertise in various robotic disciplines to recent pilot applications based on the now commercial Care-O-bot hardware.
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.
In this talk I introduce the neural statistician as an approach for meta learning. The neural statistician learns to appropriately summarise datasets through a learnt statistic vector. This can be used for few shot learning, by computing the statistic vectors for the presented data, and using these statistics as context variables for one-shot classification and generation. I will show how we can generalise the neural statistician to a context aware learner that learns to characterise and combine independently learnt contexts. I will also demonstrate an approach for meta-learning data augmentation strategies. Acknowledgments: This work is joint work with Harri Edwards, Antreas Antoniou, and Conor Durkan.
Organizers: Philipp Hennig
The field of transportation is undergoing a seismic change with the coming introduction of autonomous driving. The technologies required to enable computer driven cars involves the latest cutting edge artificial intelligence algorithms along three major thrusts: Sensing, Planning and Mapping. Prof. Amnon Shashua, Co-founder and Chairman of Mobileye, will describe the challenges and the kind of machine learning algorithms involved, but will do that through the perspective of Mobileye’s activity in this domain.
The fundamental building block in many learning models is the distance measure that is used. Usually, the linear distance is used for simplicity. Replacing this stiff distance measure with a flexible one could potentially give a better representation of the actual distance between two points. I will present how the normal distribution changes if the distance measure respects the underlying structure of the data. In particular, a Riemannian manifold will be learned based on observations. The geodesic curve can then be computed—a length-minimizing curve under the Riemannian measure. With this flexible distance measure we get a normal distribution that locally adapts to the data. A maximum likelihood estimation scheme is provided for inference of the parameters mean and covariance, and also, a systematic way to choose the parameter defining the Riemannian manifold. Results on synthetic and real world data demonstrate the efficiency of the proposed model to fit non-trivial probability distributions.
Organizers: Philipp Hennig
In this talk I will first outline my different research projects. I will then focus on the EACare project, a quite newly started multi-disciplinary collaboration with the aim to develop an embodied system, capable of carrying out neuropsychological tests to detect early signs of dementia, e.g., due to Alzheimer's disease. The system will use methods from Machine Learning and Social Robotics, and be trained with examples of recorded clinician-patient interactions. The interaction will be developed using a participatory design approach. I describe the scope and method of the project, and report on a first Wizard of Oz prototype.
Creating convincing human facial animation is challenging. Face animation is often hand-crafted by artists separately from body motion. Alternatively, if the face animation is derived from motion capture, it is typically performed while the actor is relatively still. Recombining the isolated face animation with body motion is non-trivial and often results in uncanny results if the body dynamics are not properly reflected on the face (e.g. cheeks wiggling when running). In this talk, I will discuss the challenges of human soft tissue simulation and control. I will then present our method for adding physical effects to facial blendshape animation. Unlike previous methods that try to add physics to face rigs, our method can combine facial animation and rigid body motion consistently while preserving the original animation as closely as possible. Our novel simulation framework uses the original animation as per-frame rest-poses without adding spurious forces. We also propose the concept of blendmaterials to give artists an intuitive means to control the changing material properties due to muscle activation.
Organizers: Timo Bolkart
Performance metrics are a key component of machine learning systems, and are ideally constructed to reflect real world tradeoffs. In contrast, much of the literature simply focuses on algorithms for maximizing accuracy. With the increasing integration of machine learning into real systems, it is clear that accuracy is an insufficient measure of performance for many problems of interest. Unfortunately, unlike accuracy, many real world performance metrics are non-decomposable i.e. cannot be computed as a sum of losses for each instance. Thus, known algorithms and associated analysis are not trivially extended, and direct approaches require expensive combinatorial optimization. I will outline recent results characterizing population optimal classifiers for large families of binary and multilabel classification metrics, including such nonlinear metrics as F-measure and Jaccard measure. Perhaps surprisingly, the prediction which maximizes the utility for a range of such metrics takes a simple form. This results in simple and scalable procedures for optimizing complex metrics in practice. I will also outline how the same analysis gives optimal procedures for selecting point estimates from complex posterior distributions for structured objects such as graphs. Joint work with Nagarajan Natarajan, Bowei Yan, Kai Zhong, Pradeep Ravikumar and Inderjit Dhillon.
Organizers: Mijung Park
Writing and maintaining programs for robots poses some interesting challenges. It is hard to generalize them, as their targets are more than computing platforms. It can be deceptive to see them as input to output mappings, as interesting environments result in unpredictable inputs, and mixing reactive and deliberative behavior make intended outputs hard to define. Given the wide and fragmented landscape of components, from hardware to software, and the parties involved in providing and using them, integration is also a non-trivial aspect. The talk will illustrate the work ongoing at Fraunhofer IPA to tackle these challenges, how Open Source is its common trait, and how this translates into the industrial field thanks to the ROS-Industrial initiative.
Organizers: Vincent Berenz
We present a way to set the step size of Stochastic Gradient Descent, as the solution of a distance minimization problem. The obtained result has an intuitive interpretation and resembles the update rules of well known optimization algorithms. Also, asymptotic results to its relation to the optimal learning rate of Gradient Descent are discussed. In addition, we talk about two different estimators, with applications in Variational inference problems, and present approximate results about their variance. Finally, we combine all of the above, to present an optimization algorithm that can be used on both mini-batch optimization and Variational problems.
Organizers: Philipp Hennig
How do young children learn so much about the world, and so efficiently? This talk presents the recent studies investigating theoretically and empirically how children actively seek information in their physical and social environments as evidence to test and dynamically revise their hypotheses and theories over time. In particular, it will focus on how children adapt their active learning strategies. such as question-asking and explorative behavior, in response to the task characteristics, to the statistical structure of the hypothesis space, and to the feedback received. Such adaptiveness and flexibility is crucial to achieve efficiency in situations of uncertainty, when testing alternative hypotheses, making decisions, drawing causal inferences and solving categorization tasks.