Automatic preshaping for a dextrous hand from a simple description of objects

Bard, C.; Troccaz, Jocelyne

doi:10.1109/iros.1990.262507

Cited by 39 publications

(23 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional grasp planning relies on force analysis (FA), which computes the behaviour of an object subject to a grip via the laws of classical mechanics (Bicchi & Kumar, 2000). In recent years, a second trend emerged, whereby a direct mapping from vision to action is either engineered or learned from experience (Bard & Troccaz, 1990;Coelho et al, 2000;Kamon et al, 1996). When comparing one approach to the other, force analysis is the methodical, scrupulous approach, where one attempts to model the physical processes that occur at the interface of the object and the gripper.…”

Section: Related Workmentioning

confidence: 99%

One-shot learning and generation of dexterous grasps for novel objects

Kopicki

Detry

Adjigble

et al. 2015

The International Journal of Robotics Research

117

163

View full text Add to dashboard Cite

This paper presents a method for one-shot learning of dexterous grasps, and grasp generation for novel objects. A model of each grasp type is learned from a single kinesthetic demonstration, and several types are taught. These models are used to select and generate grasps for unfamiliar objects. Both the learning and generation stages use an incomplete point cloud from a depth camera -no prior model of object shape is used. The learned model is a product of experts, in which experts are of two types. The first is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second is the hand configuration model and is a density over the whole hand configuration. Grasp generation for an unfamiliar object optimises the product of these two model types, generating thousands of grasp candidates in under 30 seconds. The method is robust to incomplete data at both training and testing stages. When several grasp types are considered the method selects the highest likelihood grasp across all the types. In an experiment, the training set consisted of five different grasps, and the test set of forty-five previously unseen objects. The success rate of the first choice grasp is 84.4% or 77.7% if seven views or a single view of the test object are taken, respectively. Keywords learning, dexterous grasping * Authors Kopicki, Detry and Wyatt are identified as the primary authors of this work. Kopicki is identified as the first author. † Corresponding author; e-mail: jlw@cs.bham.ac.uk 2 IJRR -(-) Fig. 1. Leftmost image: Objects used, the four objects on the left were used solely for training, the remaining forty three objects on the right were solely used as novel test objects. Rightmost image: The Boris manipulation platform on which the experiments reported were carried out.

show abstract

Section: Related Workmentioning

confidence: 99%

One-shot learning and generation of dexterous grasps for novel objects

Kopicki

Detry

Adjigble

et al. 2015

The International Journal of Robotics Research

117

163

View full text Add to dashboard Cite

show abstract

“…Part-grasp associations have been previously suggested and studied by several research groups [2], [23], [36]. In the earlier work, the definition of parts was often either hard-coded [23], or driven by shape analysis [1], [2], [36].…”

Section: B Previous Work On Part-based Graspingmentioning

confidence: 99%

“…In the earlier work, the definition of parts was often either hard-coded [23], or driven by shape analysis [1], [2], [36]. There is however an increasing interest for defining parts based on grasping experience [10], [12], [15], [22], [37].…”

Section: B Previous Work On Part-based Graspingmentioning

confidence: 99%

Generalizing grasps across partly similar objects

Detry

Madry

et al. 2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-The paper starts by reviewing the challenges associated to grasp planning, and previous work on robot grasping. Our review emphasizes the importance of agents that generalize grasping strategies across objects, and that are able to transfer these strategies to novel objects. In the rest of the paper, we then devise a novel approach to the grasp transfer problem, where generalization is achieved by learning, from a set of grasp examples, a dictionary of object parts by which objects are often grasped. We detail the application of dimensionality reduction and unsupervised clustering algorithms to the end of identifying the size and shape of parts that often predict the application of a grasp. The learned dictionary allows our agent to grasp novel objects which share a part with previously seen objects, by matching the learned parts to the current view of the new object, and selecting the grasp associated to the best-fitting part. We present and discuss a proof-of-concept experiment in which a dictionary is learned from a set of synthetic grasp examples. While prior work in this area focused primarily on shape analysis (parts identified, e.g., through visual clustering, or salient structure analysis), the key aspect of this work is the emergence of parts from both object shape and grasp examples. As a result, parts intrinsically encode the intention of executing a grasp.

show abstract

“…Such preshaing issues are also important for a robot hand to grasp an object, especially either the robot hand or the object is moving quickly. There have been various works [1]- [11] concerning preshaping issues. Bard and Troccaz [1] have extracted the shape of object by vision and determined the hand preshape based on the information.…”

Section: Introductionmentioning

confidence: 99%

“…There have been various works [1]- [11] concerning preshaping issues. Bard and Troccaz [1] have extracted the shape of object by vision and determined the hand preshape based on the information. Kang and Ikeuchi [2] have computed various points leading to a successful grasping with the help of vision, and found the finger tip level preshaping where each finger tip easily reaches the computed point.…”

Section: Introductionmentioning

confidence: 99%

Basic Consideration on Preshaping for Capturing a Rotational Object

Higashimori

Kimura²,

Ishii³

et al. 2004

Proceedings of the 21st International Symposium on Automation and Robotics in Construction

View full text Add to dashboard Cite

Preshaping is an important issue for a robot hand to grasp a moving object successfully. Generally, a moving object in 3D space has rotational motion as well as translational one. This study discusses dynamic preshaping issue for such an object changing the posture momentarily. In this paper, we focus on determining the timing for grasping the object. We first show a strategy to extract candidates of timing for grasping. We also verify the proposed strategy by experiments using a high speed hand with the assistance of a high speed vision.

show abstract

Automatic preshaping for a dextrous hand from a simple description of objects

Cited by 39 publications

References 4 publications

One-shot learning and generation of dexterous grasps for novel objects

One-shot learning and generation of dexterous grasps for novel objects

Generalizing grasps across partly similar objects

Basic Consideration on Preshaping for Capturing a Rotational Object

Contact Info

Product

Resources

About