Search for: All records

Variable stiffness grippers can adapt to objects with different shapes and gripping forces. This paper presents a novel variable stiffness gripper (VSG) based on the Fin Ray effect that can adjust stiffness discretely. The main structure of the gripper includes the compliant frame, rotatable ribs, and the position limit components attached to the compliant frame. The stiffness of the gripper can be adjusted by rotating the specific ribs in the frame. There are four configurations for the gripper that were developed in this research: a) all ribs OFF (Flex) mode; b) upper ribs ON and lower ribs OFF (Hold) mode; c) upper ribs OFF and lower ribs ON (Pinch) mode; d) all ribs ON (Clamp) mode. Different configurations can provide various stiffness for the gripper’s finger to adapt the objects with different shapes and weights. To optimize the design, the stiffness analysis under various configurations and force conditions was implemented by finite element analysis (FEA). The 3-D printed prototypes were constructed to verify the feature and performance of the design concept of the VSG compared with the FEA results. The design of the VSG provides a novel idea for industrial robots and collaborative robots on adaptive grasping. 

SimSnap responds to the need for a technology-based tool that supports learning at three social planes—individual, small group, and whole-class—while being easy to deploy with minimal technology overhead costs during their uptake. While much research has examined the efficacy of large-scale collaborative systems and individual-oriented learning systems, the intersection of and the movement between the three social planes is under explored. SimSnap is a cross-device, tablet-based platform that facilitates learning science concepts for middle school students through interactive simulations. Students in physical proximity can ‘snap’ their devices together to collaborate on learning activities. SimSnap enables real-time transition between individual and group activities in a classroom by offering reconfigurable simulations. SimSnap also provides an environment where open-ended and task-specific learning trajectories can be explored to maximize students’ learning potential. In this iteration of SimSnap, we have designed and implemented our first curriculum on SimSnap, focusing on plant biology, ecosystems, and genetics. 

A modal decomposition is a useful tool that deconstructs the statistical dependence between two random variables by decomposing their joint distribution into orthogonal modes. Historically, modal decompositions have played important roles in statistics and information theory, e.g., in the study of maximal correlation. They are defined using the singular value decompo- sitions of divergence transition matrices (DTMs) and conditional expectation operators corresponding to joint distributions. In this paper, we first characterize the set of all DTMs, and illustrate how the associated conditional expectation operators are the only weak contractions among a class of natural candidates. While modal decompositions have several modern machine learning applications, such as feature extraction from categorical data, the sample complexity of estimating them in such scenarios has not been analyzed. Hence, we also establish some non-asymptotic sample complexity results for the problem of estimating dominant modes of an unknown joint distribution from training data. 

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational advantage. However, the fact that the stochastic gradient is a biased estimator of the full gradient with correlated samples has led to the lack of theoretical understanding of how SGD behaves under correlated settings and hindered its use in such cases. In this paper, we focus on the Gaussian process (GP) and take a step forward towards breaking the barrier by proving minibatch SGD converges to a critical point of the full loss function, and recovers model hyperparameters with rate O(1/K) up to a statistical error term depending on the minibatch size. Numerical studies on both simulated and real datasets demonstrate that minibatch SGD has better generalization over state-of-the-art GP methods while reducing the computational burden and opening a new, previously unexplored, data size regime for GPs.