Search

In order to function in unstructured environments, robots need the ability to recognize unseen objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task typically does not exist for most robotic settings, which motivates the use of synthetic data. Our proposed method, UOIS-Net, separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. UOIS-Net is comprised of two stages: first, it operates only on depth to produce object instance center votes in 2D or 3D and assembles them into rough initial masks. Secondly, these initial masks are refined using RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is non-photorealistic. To train our method, we introduce a large-scale synthetic dataset of random objects on tabletops. We show that our method can produce sharp and accurate segmentation masks, outperforming state-of-the-art methods on unseen object instance segmentation. We also show that our method can segment unseen objects for robot grasping., Comment: Journal version of arXiv:1907.13236

Decorin is a stromal-derived prototype member of the small leucine-rich proteoglycan gene family. In addition to its functions as a regulator of collagen fibrillogenesis and TGF-β activity soluble decorin acts as a pan-receptor tyrosine kinase (RTK) inhibitor. Decorin binds to various RTKs including EGFR HER2 HGFR/Met VEGFR2 TLR and IGFR. Although the molecular mechanism for the action of decorin on these receptors is not entirely elucidated overall decorin evokes transient activation of these receptors with suppression of downstream signaling cascades culminating in growth inhibition followed by their physical downregulation via caveosomal internalization and degradation. In the case of Met decorin leads to decreased β-catenin signaling pathway and growth suppression. As most of these RTKs are responsible for providing a growth advantage to cancer cells the result of decorin treatment is oncosuppression. Another decorin-driven mechanism to restrict cancer growth and dissemination is by impeding angiogenesis via vascular endothelial growth factor receptor 2 (VEGFR2) and the concurrent activation of protracted endothelial cell autophagy. In this review we will dissect the multiple roles of decorin in cancer biology and its potential use as a next-generation protein-based adjuvant therapy to combat cancer.

Proteoglycans and selected extracellular matrix constituents are emerging as intrinsic and critical regulators of evolutionarily conversed, intracellular catabolic pathways. Often, these secreted molecules evoke sustained autophagy in a variety of cell types, tissues, and model systems. The unique properties of proteoglycans have ushered in a paradigmatic shift to broaden our understanding of matrix-mediated signaling cascades. The dynamic cellular pathway controlling autophagy is now linked to an equally dynamic and fluid signaling network embedded in a complex meshwork of matrix molecules. A rapidly emerging field of research encompasses multiple matrix-derived candidates, representing a menagerie of soluble matrix constituents including decorin, biglycan, endorepellin, endostatin, collagen VI and plasminogen kringle 5. These matrix constituents are pro-autophagic and simultaneously anti-angiogenic. In contrast, perlecan, laminin α2 chain, and lumican have anti-autophagic functions. Mechanistically, each matrix constituent linked to intracellular catabolic events engages a specific cell surface receptor that often converges on a common core of the autophagic machinery including AMPK, Peg3 and Beclin 1. We consider this matrix-evoked autophagy as non-canonical given that it occurs in an allosteric manner and is independent of nutrient availability or prevailing bioenergetics control. We propose that matrix-regulated autophagy is an important outside-in signaling mechanism for proper tissue homeostasis that could be therapeutically leveraged to combat a variety of diseases.

We present online prediction methods for time series that let us explicitly handle nonstationary artifacts (e.g. trend and seasonality) present in most real time series. Specifically, we show that applying appropriate transformations to such time series before prediction can lead to improved theoretical and empirical prediction performance. Moreover, since these transformations are usually unknown, we employ the learning with experts setting to develop a fully online method (NonSTOP-NonSTationary Online Prediction) for predicting nonstationary time series. This framework allows for seasonality and/or other trends in univariate time series and cointegration in multivariate time series. Our algorithms and regret analysis subsume recent related work while significantly expanding the applicability of such methods. For all the methods, we provide sub-linear regret bounds using relaxed assumptions. The theoretical guarantees do not fully capture the benefits of the transformations, thus we provide a data-dependent analysis of the follow-the-leader algorithm that provides insight into the success of using such transformations. We support all of our results with experiments on simulated and real data.

We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of our framework for object discovery, we conduct experiments on commonly used datasets for motion segmentation, where we achieve state-of-the-art performance.

We present an approach for asymptotically optimal motion planning for kinodynamic systems with arbitrary nonlinear dynamics amid obstacles. Optimal sampling-based planners like RRT*, FMT*, and BIT* when applied to kinodynamic systems require solving a two-point boundary value problem (BVP) to perform exact connections between nodes in the tree. Two-point BVPs are non-trivial to solve, hence the prevalence of alternative approaches that focus on specific instances of kinodynamic systems, use approximate solutions to the two-point BVP, or use random propagation of controls. In this work, we explore the feasibility of exploiting recent advances in numerical optimal control and optimization to solve these two-point BVPs for arbitrary kinodynamic systems and how they can be integrated with existing optimal planning algorithms. We combine BIT* with a two-point BVP solver that uses sequential quadratic programming (SQP). We consider the problem of computing minimum-time trajectories. Since the duration of trajectories is not known a-priori, we include the time-step as part of the optimization to allow SQP to optimize over the duration of the trajectory while keeping the number of discrete steps fixed for every connection attempted. Our experiments indicate that using a two-point BVP solver in the inner-loop of BIT* is competitive with the state-of-the-art in sampling-based optimal planning that explicitly avoids the use of two-point BVP solvers.

In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control. We use a feature-based representation of the dynamics that allows the dynamics model to be fitted with a simple least squares procedure, and the features are identified from a high-level specification of the robot's morphology, consisting of the number and connectivity structure of its links. Model predictive control is then used to choose the actions under an optimistic model of the dynamics, which produces an efficient and goal-directed exploration strategy. We present real time experimental results on standard benchmark problems involving the pendulum, cartpole, and double pendulum systems. Experiments indicate that our method is able to learn a range of benchmark tasks substantially faster than the previous best methods. To evaluate our approach on a realistic robotic control task, we also demonstrate real time control of a simulated 7 degree of freedom arm., Comment: 8 pages