We propose a new benchmarking protocol to evaluate algorithms for bimanual robotic manipulation semi-deformable objects. The benchmark is inspired from two real-world applications: (a) watchmaking craftsmanship, and (b) belt assembly in automobile engines. We provide two setups that try to highlight the following challenges: (a) manipulating objects via a tool, (b) placing irregularly shaped objects in the correct groove, (c) handling semideformable objects, and (d) bimanual coordination. We provide CAD drawings of the task pieces that can be easily 3D printed to ensure ease of reproduction, and detailed description of tasks and protocol for successful reproduction, as well as meaningful metrics for comparison. We propose four categories of submission in an attempt to make the benchmark accessible to a wide range of related fields spanning from adaptive control, motion planning to learning the tasks through trial-and-error learning. Index Terms-Performance evaluation and benchmarking, dual arm manipulation, model learning for control, dexterous manipulation. I. INTRODUCTION A VARIETY of industrial tasks are still performed by humans today, as they require high-level precision and dexterity not yet available in robots. These tasks require the use of prehensile instruments, such as screwdrivers or tweezers, to grasp, insert, and manipulate tiny and deformable objects. Examples of such tasks are common in watchmaking craftsmanship, where both assembling and screwing are the core actions in the whole process, and in pharmaceutical industry, to handle pipettes and vials. There is interest to automatize parts of these tasks [1]. Such precise manipulation can also be

No abstract

Dynamical Systems (DS) are fundamental to the modeling and understanding of time evolving phenomena, and find application in physics, biology and control. As determining an analytical description of the dynamics is often difficult, data-driven approaches are preferred for identifying and controlling nonlinear DS with multiple equilibrium points. Identification of such DS has been treated largely as a supervised learning problem. Instead, we focus on a unsupervised learning scenario where we know neither the number nor the type of dynamics. We propose a Graph-based spectral clustering method that takes advantage of a velocity-augmented kernel to connect data-points belonging to the same dynamics, while preserving the natural temporal evolution. We study the eigenvectors and eigenvalues of the Graph Laplacian and show that they form a set of orthogonal embedding spaces, one for each sub-dynamics. We prove that there always exist a set of 2-dimensional embedding spaces in which the sub-dynamics are linear, and n-dimensional embedding where they are quasi-linear. We compare the clustering performance of our algorithm to Kernel K-Means, Spectral Clustering and Gaussian Mixtures and show that, even when these algorithms are provided with the true number of sub-dynamics, they fail to cluster them correctly. We learn a diffeomorphism from the Laplacian embedding space to the original space and show that the Laplacian embedding leads to good reconstruction accuracy and a faster training time through an exponential decaying loss, compared to the state of the art diffeomorphism-based approaches.

No abstract

Accurate air temperature measurements made by surface meteorological stations are demanded by climate research programs for various uses. Heating of the temperature sensor due to inadequate coupling with the environment can lead to significant errors. Therefore, accurate in-situ temperature measurements require shielding the sensor from exposure to direct and reflected solar radiation, while also allowing the sensor to be brought into contact with atmospheric air at the ambient temperature. The difficulty in designing a radiation shield for such a temperature sensor lies in satisfying these two conditions simultaneously. In this paper, we perform a computational fluid dynamics analysis of mechanically aspirated radiation shields (MARS) to study the effect of geometry, wind speed, and interplay of multiple heat transfer processes. Finally, an artificial neural network model is developed to learn the relationship between the temperature error and specified input variables. The model is then used to perform a sensitivity analysis and design optimization.