Related papers: Using Synthetic Data and Deep Networks to Recogniz…
Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic benchmark, encompassing 1319 objects, 8270 scenes, and 427 million grasps.…
Task-oriented grasping, which involves grasping specific parts of objects based on their functions, is crucial for developing advanced robotic systems capable of performing complex tasks in dynamic environments. In this paper, we propose a…
Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However,…
We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization. We show that surfaces…
This paper introduces Action Image, a new grasp proposal representation that allows learning an end-to-end deep-grasping policy. Our model achieves $84\%$ grasp success on $172$ real world objects while being trained only in simulation on…
The ability to segment unknown objects in depth images has potential to enhance robot skills in grasping and object tracking. Recent computer vision research has demonstrated that Mask R-CNN can be trained to segment specific categories of…
In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning…
Vision-based models for robotic grasping automate critical, repetitive, and draining industrial tasks. Existing approaches are typically limited in two ways: they either target a single gripper and are potentially applied on costly dual-arm…
To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and analytic grasp metrics generated from thousands of 3D models from Dex-Net…
We propose a novel approach to multi-fingered grasp planning leveraging learned deep neural network models. We train a voxel-based 3D convolutional neural network to predict grasp success probability as a function of both visual information…
Learning robotic grasps from visual observations is a promising yet challenging task. Recent research shows its great potential by preparing and learning from large-scale synthetic datasets. For the popular, 6 degree-of-freedom (6-DOF)…
In this paper, we propose a novel object-level mapping system that can simultaneously segment, track, and reconstruct objects in dynamic scenes. It can further predict and complete their full geometries by conditioning on reconstructions…
Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the…
We propose a novel approach to multi-fingered grasp planning leveraging learned deep neural network models. We train a convolutional neural network to predict grasp success as a function of both visual information of an object and grasp…
This work provides an architecture that incorporates depth and tactile information to create rich and accurate 3D models useful for robotic manipulation tasks. This is accomplished through the use of a 3D convolutional neural network (CNN).…
In this paper, we address the shape-from-shading problem by training deep networks with synthetic images. Unlike conventional approaches that combine deep learning and synthetic imagery, we propose an approach that does not need any…
Robotic manipulation systems operating in complex environments rely on perception systems that provide information about the geometry (pose and 3D shape) of the objects in the scene along with other semantic information such as object…
Generating high-quality instance-wise grasp configurations provides critical information of how to grasp specific objects in a multi-object environment and is of high importance for robot manipulation tasks. This work proposed a novel…
Great success has been achieved in the 6-DoF grasp learning from the point cloud input, yet the computational cost due to the point set orderlessness remains a concern. Alternatively, we explore the grasp generation from the RGB-D input in…
Grasp detection of novel objects in unstructured environments is a key capability in robotic manipulation. For 2D grasp detection problems where grasps are assumed to lie in the plane, it is common to design a fully convolutional neural…