Part-based grasp planning for familiar objects

Vahrenkamp, Nikolaus; Westkamp, Leonard; Yamanobe, Natsuki; Aksoy, Eren Erdal; Asfour, Tamim

doi:10.1109/humanoids.2016.7803382

Cited by 50 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding transferring grasping skills, we tackle the problem of requiring a fully observed [22] or a non-occluded [20] object by exploiting the geometrical information residing in our learned categorical model. Unlike [25] we model shape and grasping not for single known instances, but for object categories, which gives us the possibility to learn typical shape variations and to infer grasping information even when parts of the object are not observed.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Transferring Category-Based Functional Grasping Skills by Latent Space Non-Rigid Registration

Rodríguez

Behnke

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Objects within a category are often similar in their shape and usage. When we-as humans-want to grasp something, we transfer our knowledge from past experiences and adapt it to novel objects. In this paper, we propose a new approach for transferring grasping skills that accumulates grasping knowledge into a category-level canonical model. Grasping motions for novel instances of the category are inferred from geometric deformations between the observed instance and the canonical shape. Correspondences between the shapes are established by means of a non-rigid registration method that combines the Coherent Point Drift approach with subspace methods. By incorporating category-level information into the registration, we avoid unlikely shapes and focus on deformations actually observed within the category. Control poses for generating grasping motions are accumulated in the canonical model from grasping definitions of known objects. According to the estimated shape parameters of a novel instance, the control poses are transformed towards it. The category-level model makes our method particularly relevant for on-line grasping, where fullyobserved objects are not easily available. This is demonstrated through experiments in which objects with occluded handles are successfully grasped.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Based on segmented objects according to their RGB-D appearance, Vahrenkamp et al [20] transfer grasp poses from a set of template grasps. Ficuciello et al [21] developed an approach to confer grasping capabilities based on a reinforcement learning technique and postural synergies.…”

Section: B Transferring Grasping Skillsmentioning

confidence: 99%

Transferring Category-Based Functional Grasping Skills by Latent Space Non-Rigid Registration

Rodríguez

Behnke

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Fine-grained grasping planning and control often involves 3D modeling of object shape, modeling dynamics of robot hands, and local surface modeling [11], [18], [14], [37], [20], [36], [22], [21]. Some work focused on analytic modeling of robotic grasps with known object shape information [11], [18].…”

Section: Related Workmentioning

confidence: 99%

“…Li et al [20] investigated the hand pose estimation in robotic grasping by decoupling contact points and hand configuration with parametrized object shape. Building upon the compositional aspect of everyday objects, Vahrenkamp et al [36] proposed a part-based model for robotic grasping that has better generalization to novel object. Very recently, effort was also made in building DexNet [22], [21], a large-scale point cloud database for planar grasping (from top-down).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning 6-DOF Grasping Interaction via Deep Geometry-Aware 3D Representations

Yan¹,

Hsu

Khansari³

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

106

View full text Add to dashboard Cite

This paper focuses on the problem of learning 6-DOF grasping with a parallel jaw gripper in simulation. Our key idea is constraining and regularizing grasping interaction learning through 3D geometry prediction. We introduce a deep geometry-aware grasping network (DGGN) that decomposes the learning into two steps. First, we learn to build mental geometry-aware representation by reconstructing the scene (i.e., 3D occupancy grid) from RGBD input via generative 3D shape modeling. Second, we learn to predict grasping outcome with its internal geometry-aware representation. The learned outcome prediction model is used to sequentially propose grasping solutions via analysis-by-synthesis optimization. Our contributions are fourfold: (1) To best of our knowledge, we are presenting for the first time a method to learn a 6-DOF grasping net from RGBD input; (2) We build a grasping dataset from demonstrations in virtual reality with rich sensory and interaction annotations. This dataset includes 101 everyday objects spread across 7 categories, additionally, we propose a data augmentation strategy for effective learning; (3) We demonstrate that the learned geometry-aware representation leads to about 10% relative performance improvement over the baseline CNN on grasping objects from our dataset. (4) We further demonstrate that the model generalizes to novel viewpoints and object instances.

show abstract