Learning to grasp by using visual information

Anglani, A.; Taurisano, F.; Giuseppe, R. De; Distante, Cosimo

doi:10.1109/cira.1999.809933

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moving away from the limitations of two-dimensional grasps of planar objects, Anglani et al propose a grasping algorithm by utilizing a controller capable of learning in a trial-and-error methodology [1]. Even though the paper is focused on the different problem of visual servoing, it encompasses some nice and surprising results such as running the learning phase of the algorithm in simulation, transporting the results on the real platform, and achieving good experimental results.…”

Section: Related Workmentioning

confidence: 98%

Efficient grasping of novel objects through dimensionality reduction

Balaguer

Carpin

2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

A learning method capable of empowering a robot to successfully grasp a novel object through vision has recently been demonstrated, and generated much interest in the robotics community. In this paper we carefully analyze this new approach and apply dimensionality reduction techniques to decrease the number of features that need to be computed in order to classify whether a given pixel in an image is associated with a good or bad grasping point. Exploiting the ideas behind principal component analysis, we formulate two hypotheses about possible ways to eliminate certain features from training and classification. We then experimentally verify that the feature reduction significantly improves speed while retaining classification accuracy. Overall, the combination of the two hypotheses leads to a speedup factor of almost ten. The hypotheses are validated on third party synthetic data and also demonstrated on a seven degrees-of-freedom manipulator.

show abstract

Section: Related Workmentioning

confidence: 98%

Efficient grasping of novel objects through dimensionality reduction

Balaguer

Carpin

2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Novel concepts such as visual recognition [1], object avoidance [10], moving targets [10], switching control [7], grasp quality measures [8], force feedback [9], and force control [3] were proposed. Such techniques determine an adequate trajectory for the gripper to reach and grasp an object.…”

mentioning

confidence: 99%

“…Further, human fingers use tactile sensing to feel the texture of the object so that the required forces can be applied to manipulate the object without any slippage. Based on grasping operations typically performed by humans, several methods [1], [3], [4], [7]- [10] have been proposed for robot grippers. These methods involve making contact with the object at the right location and orientation by traveling along a predefined path by assuming that the properties of the object are known accurately.…”

mentioning

confidence: 99%

Adaptive Critic Neural Network-Based Object Grasping Control Using a Three-Finger Gripper

Jagannathan

Galan

2004

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Grasping of objects has been a challenging task for robots. The complex grasping task can be defined as object contact control and manipulation subtasks. In this paper, object contact control subtask is defined as the ability to follow a trajectory accurately by the fingers of a gripper. The object manipulation subtask is defined in terms of maintaining a predefined applied force by the fingers on the object. A sophisticated controller is necessary since the process of grasping an object without a priori knowledge of the object's size, texture, softness, gripper, and contact dynamics is rather difficult. Moreover, the object has to be secured accurately and considerably fast without damaging it. Since the gripper, contact dynamics, and the object properties are not typically known beforehand, an adaptive critic neural network (NN)-based hybrid position/force control scheme is introduced. The feedforward action generating NN in the adaptive critic NN controller compensates the nonlinear gripper and contact dynamics. The learning of the action generating NN is performed on-line based on a critic NN output signal. The controller ensures that a three-finger gripper tracks a desired trajectory while applying desired forces on the object for manipulation. Novel NN weight tuning updates are derived for the action generating and critic NNs so that Lyapunov-based stability analysis can be shown. Simulation results demonstrate that the proposed scheme successfully allows fingers of a gripper to secure objects without the knowledge of the underlying gripper and contact dynamics of the object compared to conventional schemes.

show abstract

“…Consequently, the non-horizontality of the ground and the large positioning errors of the mobile base may cause the pick or place task to fail. Beyond the conventional visual servo control methods referred to above, behavior-based methods for visual servo control have already been developed in the literature (Anglani et al, 1999;Kim et al, 2001;Wasik & Saffiotti, 2002, 2003. A behavior-based system has been proposed to perform grasping tasks in an unstructured environment, in cases in which the position of the targets is not already known (Wasik & Saffiotti, 2002, 2003.…”

Section: Introductionmentioning

confidence: 99%