Abstract-We consider the problem of estimating detailed 3-d structure from a single still image of an unstructured environment. Our goal is to create 3-d models which are both quantitatively accurate as well as visually pleasing.For each small homogeneous patch in the image, we use a Markov Random Field (MRF) to infer a set of "plane parameters" that capture both the 3-d location and 3-d orientation of the patch. The MRF, trained via supervised learning, models both image depth cues as well as the relationships between different parts of the image. Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene; this enables the algorithm to capture much more detailed 3-d structure than does prior art, and also give a much richer experience in the 3-d flythroughs created using image-based rendering, even for scenes with significant non-vertical structure.Using this approach, we have created qualitatively correct 3-d models for 64.9% of 588 images downloaded from the internet. We have also extended our model to produce large scale 3d models from a few images.

Abstract-We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. In this work, we apply a deep learning approach to solve this problem, which avoids time-consuming hand-design of features. This presents two main challenges. First, we need to evaluate a huge number of candidate grasps. In order to make detection fast, as well as robust, we present a two-step cascaded structure with two deep networks, where the top detections from the first are re-evaluated by the second. The first network has fewer features, is faster to run, and can effectively prune out unlikely candidate grasps. The second, with more features, is slower but has to run only on the top few detections. Second, we need to handle multimodal inputs well, for which we present a method to apply structured regularization on the weights based on multimodal group regularization. We demonstrate that our method outperforms the previous state-of-the-art methods in robotic grasp detection, and can be used to successfully execute grasps on a Baxter robot.

Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it. Spatiotemporal graphs are a popular tool for imposing such highlevel intuitions in the formulation of real world problems. In this paper, we propose an approach for combining the power of high-level spatio-temporal graphs and sequence learning success of Recurrent Neural Networks (RNNs). We develop a scalable method for casting an arbitrary spatiotemporal graph as a rich RNN mixture that is feedforward, fully differentiable, and jointly trainable. The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps. The evaluations of the proposed approach on a diverse set of problems, ranging from modeling human motion to object interactions, shows improvement over the state-of-the-art with a large margin. We expect this method to empower new approaches to problem formulation through high-level spatio-temporal graphs and Recurrent Neural Networks. Links: WebCorresponding Structural-RNN Spatio-temporal graph representation Problem (e.g. Activity)Activity Affordance RNN Activity Affordance Activity Affordance

We consider the problem of grasping novel objects, specifically ones that are being seen for the first time through vision. Grasping a previously unknown object, one for which a 3-d model is not available, is a challenging problem. Further, even if given a model, one still has to decide where to grasp the object. We present a learning algorithm that neither requires, nor tries to build, a 3-d model of the object. Given two (or more) images of an object, our algorithm attempts to identify a few points in each image corresponding to good locations at which to grasp the object. This sparse set of points is then triangulated to obtain a 3-d location at which to attempt a grasp. This is in contrast to standard dense stereo, which tries to triangulate every single point in an image (and often fails to return a good 3-d model). Our algorithm for identifying grasp locations from an image is trained via supervised learning, using synthetic images for the training set. We demonstrate this approach on two robotic manipulation platforms. Our algorithm successfully grasps a wide variety of objects, such as plates, tape-rolls, jugs, cellphones, keys, screwdrivers, staplers, a thick coil of wire, a strangely shaped power horn, and others, none of which were seen in the training set. We also apply our method to the task of unloading items from dishwashers.

Understanding human activities and object affordances are two very important skills, especially for personal robots which operate in human environments. In this work, we consider the problem of extracting a descriptive labeling of the sequence of sub-activities being performed by a human, and more importantly, of their interactions with the objects in the form of associated affordances. Given a RGB-D video, we jointly model the human activities and object affordances as a Markov random field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural support vector machine (SSVM) approach, where labelings over various alternate temporal segmentations are considered as latent variables. We tested our method on a challenging dataset comprising 120 activity videos collected from 4 subjects, and obtained an accuracy of 79.4% for affordance, 63.4% for sub-activity and 75.0% for high-level activity labeling. We then demonstrate the use of such descriptive labeling in performing assistive tasks by a PR2 robot.

Abstract-Given an image and an aligned depth map of an object, our goal is to estimate the full 7-dimensional gripper configuration-its 3D location, 3D orientation and the gripper opening width. Recently, learning algorithms have been successfully applied to grasp novel objects-ones not seen by the robot before. While these approaches use low-dimensional representations such as a 'grasping point' or a 'pair of points' that are perhaps easier to learn, they only partly represent the gripper configuration and hence are sub-optimal.We propose to learn a new 'grasping rectangle' representation: an oriented rectangle in the image plane. It takes into account the location, the orientation as well as the gripper opening width. However, inference with such a representation is computationally expensive. In this work, we present a two step process in which the first step prunes the search space efficiently using certain features that are fast to compute. For the remaining few cases, the second step uses advanced features to accurately select a good grasp. In our extensive experiments, we show that our robot successfully uses our algorithm to pick up a variety of novel objects.

Abstract-An important aspect of human perception is anticipation, which we use extensively in our day-to-day activities when interacting with other humans as well as with our surroundings. Anticipating which activities will a human do next (and how) can enable an assistive robot to plan ahead for reactive responses in human environments. Furthermore, anticipation can even improve the detection accuracy of past activities. The challenge, however, is two-fold: We need to capture the rich context for modeling the activities and object affordances, and we need to anticipate the distribution over a large space of future human activities.In this work, we represent each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances. We then consider each ATCRF as a particle and represent the distribution over the potential futures using a set of particles. In extensive evaluation on CAD-120 human activity RGB-D dataset, we first show that anticipation improves the state-of-the-art detection results. For new subjects (not seen in the training set), we obtain an activity anticipation accuracy (defined as whether one of top three predictions actually happened) of 75.4%, 69.2% and 58.1% for an anticipation time of 1, 3 and 10 seconds respectively. Finally, we also use our algorithm on a robot for performing a few reactive responses.

We consider the task of 3-d depth estimation from a single still image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which include forests, sidewalks, trees, buildings, etc.) and their corresponding ground-truth depthmaps. Then, we apply supervised learning to predict the value of the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a hierarchical, multiscale Markov Random Field (MRF) that incorporates multiscale local-and global-image features, and models the depths and the relation between depths at different points in the image. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps. We further propose a model that incorporates both monocular cues and stereo (triangulation) cues, to obtain significantly more accurate depth estimates than is possible using either monocular or stereo cues alone.