Search

Localization and manipulation of features such as buttons, snaps, or grommets embedded in fabrics and other flexible materials is a difficult robotics problem. Approaches that rely too much on sensing and localization that occurs before touching the material are likely to fail because the flexible material can move when the robot actually makes contact. This paper experimentally explores the possibility to use proprioceptive and load-based tactile information to localize features embedded in flexible materials during robot manipulation. In our experiments, Robonaut 2, a robot with human-like hands and arms, uses particle filtering to localize features based on proprioceptive and tactile measurements. Our main contribution is to propose a method to interact with flexible materials that reduces the state space of the interaction by forcing the material to comply in repeatable ways. Measurements are matched to a “haptic map,” which is created during a training phase, that describes expected measurements as a low-dimensional function of state. We evaluate localization performance when using proprioceptive information alone and when tactile data are also available. The two types of measurements are shown to contain complementary information. We find that the tactile measurement model is critical to localization performance and propose a series of models that offer increasingly better accuracy. Finally, this paper explores the localization approach in the context of two flexible material insertion tasks that are relevant to manufacturing applications.

The prevalence of datasets that can be represented as networks has recently fueled a great deal of work in the area of Relational Machine Learning (RML). Due to the statistical correlations between linked nodes in the network, many RML methods focus on predicting node features (i.e., labels) using the network relationships. However, many domains are comprised of a single, partially-labeled network. Thus, relational versions of Expectation Maximization (i.e., R-EM), which jointly learn parameters and infer the missing labels, can outperform methods that learn parameters from the labeled data and apply them for inference on the unlabeled nodes. Although R-EM methods can significantly improve predictive performance in networks that are densely labeled, they do not achieve the same gains in sparsely labeled networks and can perform worse than RML methods. In this work, we show the fixed-point methods that R-EM uses for approximate learning and inference result in errors that prevent convergence in sparsely labeled networks. We then propose two methods that do not experience this problem. First, we develop a Relational Stochastic EM (R-SEM) method, which uses stochastic parameters that are not as susceptible to approximation errors. Then we develop a Relational Data Augmentation (R-DA) method, which integrates over a range of stochastic parameter values for inference. R-SEM and R-DA can use any collective RML algorithm for learning and inference in partially labeled networks. We analyze their performance with two RML learners over four real world datasets, and show that they outperform independent learning, RML and R-EM -- particularly in sparsely labeled networks.

Many interesting domains in machine learning can be viewed as networks, with relationships (e.g., friendships) connecting items (e.g., individuals). The Active Exploration (AE) task is to identify all items in a network with a desired trait (i.e., positive labels) given only partial information about the network. The AE process iteratively queries for labels or network structure within a limited budget; thus, accurate predictions prior to making each query is critical to maximizing the number of positives gathered. However, the targeted AE query process produces partially observed networks that can create difficulties for predictive modeling. In particular, we demonstrate that these partial networks can exhibit extreme label correlation bias, which makes it difficult for conventional relational learning methods to accurately estimate relational parameters. To overcome this issue, we model the joint distribution of possible edges and labels to improve learning and inference. Our proposed method, Probabilistic Relational Expectation Maximization (PR-EM), is the first AE approach to accurately learn the complex dependencies between attributes, labels, and structure to improve predictions. PR-EM utilizes collective inference over the missing relationships in the partial network to jointly infer unknown item traits. Further, we develop a linear inference algorithm to facilitate efficient use of PR-EM in large networks. We test our approach on four real world networks, showing that AE with PR-EM gathers significantly more positive items compared to state-of-the-art methods.

A key challenge in the social network community is the problem of network generation -- that is, how can we create synthetic networks that match characteristics traditionally found in most real world networks? Important characteristics that are present in social networks include a power law degree distribution, small diameter, and large amounts of clustering. However, most current network generators, such as the Chung Lu and Kronecker models, largely ignore the clustering present in a graph and focus on preserving other network statistics, such as the power law distribution. Models such as the exponential random graph model have a transitivity parameter that can capture clustering, but they are computationally difficult to learn, making scaling to large real world networks intractable. In this work, we propose an extension to the Chung Lu random graph model, the Transitive Chung Lu (TCL) model, which incorporates the notion transitive edges. Specifically, it combines the standard Chung Lu model with edges that are formed through transitive closure (e.g., by connecting a 'friend of a friend'). We prove TCL's expected degree distribution is equal to the degree distribution of the original input graph, while still providing the ability to capture the clustering in the network. The single parameter required by our model can be learned in seconds on graphs with millions of edges, networks can be generated in time that is linear in the number of edges. We demonstrate the performance of TCL on four real-world social networks, including an email dataset with hundreds of thousands of nodes and millions of edges, showing TCL generates graphs that match the degree distribution, clustering coefficients and hop plots of the original networks.

Segmentation, or partitioning images into internally homogeneous regions, is an important first step in many Computer Vision tasks. In this paper, we attack the segmentation problem using an ensemble of low cost image segmentations. These segmentations are reconciled by applying recent techniques from the consensus clustering literature which exploit a Non-negative Matrix Factorization (NMF) framework. We describe extensions to these methods that scale them for large images and also incorporate smoothness constraints. This framework allows us to uniformly and easily combine segmentations from different algorithms or feature modalities. We then demonstrate that popular bottom up image segmentation algorithms, Mean Shift and Efficient Graph Based segmentation, perform no better than our simple combination of multiple image segmentations derived from k-means clustering (of various feature spaces) or from “naive” RGB quantizations. The algorithms are evaluated on the Berkeley image segmentation dataset.

Pyramids have received a great deal of interest as a data structure for use in hierarchical computer vision. This paper describes a language for the description of pyramid algorithms, supporting conceptually parallel pattern-matching and arithmetic operations. The language is defined by adding constructs from a notation for pyramid algorithms called Hierarchical Cellular Logic to the general-purpose programming language C. Initially developed to support vision research on PCLIP II, a cellular processor with a pyramidal interconnection topology, the language is also implementable on a wide range of parallel architectures.

In this panel the group discuss the future research directions for visual languages and plan for a workshop to be held prior to VL2000 next year. Participation of all will be welcome to formulate the agenda for this workshop.