Results 1 -
5 of
5
Deep Learning for Detecting Robotic Grasps
"... 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 hug ..."
Abstract
-
Cited by 22 (6 self)
- Add to MetaCart
(Show Context)
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. I.
PR2 Looking at Things: Ensemble Learning for Unstructured Information Processing with Markov Logic Networks
- In IEEE International Conference on Robotics and Automation (ICRA), Hong Kong
"... Abstract — We investigate the perception and reasoning task of answering queries about realistic scenes with objects of daily use perceived by a robot. A key problem implied by the task is the variety of perceivable properties of objects, such as their shape, texture, color, size, text pieces and lo ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
(Show Context)
Abstract — We investigate the perception and reasoning task of answering queries about realistic scenes with objects of daily use perceived by a robot. A key problem implied by the task is the variety of perceivable properties of objects, such as their shape, texture, color, size, text pieces and logos, that go beyond the capabilities of individual state-of-the-art perception methods. A promising alternative is to employ combinations of more specialized perception methods. In this paper we propose a novel combination method, which structures perception in a two-step process, and apply this method in our object perception system. In a first step, specialized methods annotate detected object hypotheses with symbolic information pieces. In the second step, the given query Q is answered by inferring the conditional probability P(Q | E), where E are the symbolic information pieces considered as evidence for the conditional probability. In this setting Q and E are part of a probabilistic model of scenes, objects and their annotations, which the perception method has beforehand learned a joint probability distribution of. Our proposed method has substantial advan-tages over alternative methods in terms of the generality of queries that can be answered, the generation of information that can actively guide perception, the ease of extension, the possibility of including additional kinds of evidences, and its potential for the realization of self-improving and-specializing perception systems. We show for object categorization, which is a subclass of the probabilistic inferences, that impressive categorization performance can be achieved combining the employed expert perception methods in a synergistic manner. I.
Exploiting Segmentation for Robust 3D Object Matching
"... Abstract — While Iterative Closest Point (ICP) algorithms have been successful at aligning 3D point clouds, they do not take into account constraints arising from sensor viewpoints. More recent beam-based models take into account sensor noise and viewpoint, but problems still remain. In particular, ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract — While Iterative Closest Point (ICP) algorithms have been successful at aligning 3D point clouds, they do not take into account constraints arising from sensor viewpoints. More recent beam-based models take into account sensor noise and viewpoint, but problems still remain. In particular, good optimization strategies are still lacking for the beam-based model. In situations of occlusion and clutter, both beam-based and ICP approaches can fail to find good solutions. In this paper, we present both an optimization method for beambased models and a novel framework for modeling observation dependencies in beam-based models using over-segmentations. This technique enables reasoning about object extents and works well in heavy clutter. We also make available a groundtruth 3D dataset for testing algorithms in this area. I.
ROBOSHERLOCK: Unstructured Information Processing for Robot Perception
"... Abstract — We present ROBOSHERLOCK, an open source software framework for implementing perception systems for robots performing human-scale everyday manipulation tasks. In ROBOSHERLOCK, perception and interpretation of realistic scenes is formulated as an unstructured information manage-ment (UIM) p ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract — We present ROBOSHERLOCK, an open source software framework for implementing perception systems for robots performing human-scale everyday manipulation tasks. In ROBOSHERLOCK, perception and interpretation of realistic scenes is formulated as an unstructured information manage-ment (UIM) problem. The application of the UIM principle supports the implementation of perception systems that can answer task-relevant queries about objects in a scene, boost object recognition performance by combining the strengths of multiple perception algorithms, support knowledge-enabled reasoning about objects and enable automatic and knowledge-driven generation of processing pipelines. We demonstrate the potential of the proposed framework by three feasibility studies of systems for real-world scene perception that have been built on top of ROBOSHERLOCK. I.
Pervasive ‘Calm’ ∗ Perception for Autonomous Robotic Agents
"... A major bottleneck in the realization of autonomous robotic agents performing complex manipulation tasks are the re-quirements that these tasks impose onto perception mech-anisms. There is a strong need to scale robot perception capabilities along two dimensions: First, the variations of appearances ..."
Abstract
- Add to MetaCart
(Show Context)
A major bottleneck in the realization of autonomous robotic agents performing complex manipulation tasks are the re-quirements that these tasks impose onto perception mech-anisms. There is a strong need to scale robot perception capabilities along two dimensions: First, the variations of appearances and perceptual properties that real-world ob-jects exhibit. Second, the variety of perceptual tasks, like categorizing and localizing, decomposing objects into their functional parts, perceiving the affordances they provide. This paper, addresses this need by organizing percep-tion into a two-stage process. First, a pervasive and ‘calm’ perceptual component runs continually and interprets the incoming image stream to form a general purpose hybrid (symbolic/sub-symbolic) belief state. This is used by the second component, the task-directed perception subsystem, to perform the respective perception tasks in a more in-formed way. We describe and discuss the first component and explain how it can manage realistic belief states, form a memory of past perceptual experiences, and compute valu-able perceptual attributes without delaying plan execution. It does so by exploiting that perception is not a one-shot task but rather a secondary task that is pervasively and calmly performed throughout the lifetime of the robot. We show system operating on a leading-edge manipulation platform.
