Finger contact sensing and the application in dexterous hand manipulation

Liu, Hongbin; Nguyen, Kien Cuong; Perdereau, Véronique; Bimbo, João; Back, Junghwan; Godden, Matthew; Seneviratne, Lakmal; Althoefer, Kaspar

doi:10.1007/s10514-015-9425-4

Cited by 53 publications

(53 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tactile sensors should be either: a) flexible and appropriately shaped to envelop a given surface, as in iCub tactile fingertip sensors ( Figure 11(a, b) [103]; b) rigid and shaped as an attachment part, e.g. [34] or [104] where a 3D-shaped tactile sensing array and an ellipsoid F/T sensor (Figure 11(c) and (e) ) replace the fingertips of the Shadow robot hand [98]. In another version of the Shadow robot Hand with the integrated BioTac multimodal tactile sensor, each finger loses one DoF (Figure 11(d)), -the sensor is as big as the two last links, distal and middle phalanges of the human index finger.…”

Section: Issues Related To the Shape Of The Attachment Surfacementioning

confidence: 99%

Tactile sensing in dexterous robot hands — Review

Kappassov¹,

Ramón²,

Perdereau³

2015

Robotics and Autonomous Systems

Self Cite

651

358

View full text Add to dashboard Cite

show abstract

Section: Issues Related To the Shape Of The Attachment Surfacementioning

confidence: 99%

Tactile sensing in dexterous robot hands — Review

Kappassov¹,

Ramón²,

Perdereau³

2015

Robotics and Autonomous Systems

Self Cite

651

358

View full text Add to dashboard Cite

show abstract

“…The estimation errors of normal force and friction force were less than 0.04N for the rigid finger. It has also been shown in [27], the contact sensing algorithm can also be extended to fingertip covered with soft layers, allowing the proposed controller work for compliant fingertips as well.…”

Section: A Simulation Resultsmentioning

confidence: 99%

Stable Grip Control on Soft Objects With Time-Varying Stiffness

et al. 2016

Self Cite

View full text Add to dashboard Cite

Abstract-Humans can hold a live animal like a hamster without overly squeezing despite the fact that its soft body undergoes impedance and size variations due to breathing and wiggling. Though the exact nature of such biological motor controllers is not known, existing literature suggests that they maintain metastable interactions with dynamic objects based on prediction rather than reaction. Most robotic gripper controllers find such tasks very challenging mainly due to hard constraints imposed on stability of closed loop control and inadequate rate of convergence of adaptive controller parameters. This paper presents experimental and numerical simulation results of a control law based on a relaxed stability criterion of reducing the probability of failure to maintain a stable grip on a soft object that undergoes temporal variations in its internal impedance. The proposed controller uses only three parameters to interpret the probability of failure estimated using a history of grip forces to adjust the grip on the dynamic object. Here we demonstrate that the proposed controller can maintain smooth and stable grip tightening and relaxing when the object undergoes random impedance variations, compared to a reactive controller that involves a similar number of controller parameters.

show abstract

“…7 that shows an overall accuracy of 83.3% was obtained. It can be noticed that most objects can be recognized successfully; however, some are still assigned to wrong labels, especially those with similar local shapes, e.g., different pliers (6,7,8) or scissors (11,12). These objects are expected to be further classified by utilizing distribution of their local features in future work.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…In the view of hardware, multiple tactile sensors have been developed using various sensing principles [1]- [5], e.g., capacitive, piezoelectric, optical, resistive and ultrasonic etc. In the meantime, some researchers contributed to decoding the conveyed message by the tactile sensors to retrieve the information of interacted object, such as contact locations [6], [7], slippage [8], object pose [9] and surface textures [10]- [12]. As defined in [13], the object characteristics can mainly be divided into two categories, i.e., material and geometric properties.…”

Section: Introductionmentioning

confidence: 99%

Tactile Object Recognition with Semi-Supervised Learning

Luo

Liu

Althoefer

et al. 2015

Intelligent Robotics and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. This paper introduced a novel approach to recognize objects with tactile images by utilizing semi-supervised learning approaches. In tactile object recognition, the data are normally insufficient to build robust training models. Thus the model of Ensemble Manifold Regularization, which combines concepts of multi-view learning and semi-supervised learning, is adapted in tactile sensing to achieve better recognition accuracy. Different outputs of classic bag of words with different dictionary sizes are considered as different views to produce an optimized one based on multiple graphs learning optimization. In the experiments 12 objects were used to compare the classification performances of our proposed approach and the classic BoW model and it is proved that our proposed method outperforms the classic BoW framework and objects with similar features can be better classified.

show abstract

Finger contact sensing and the application in dexterous hand manipulation

Cited by 53 publications

References 45 publications

Tactile sensing in dexterous robot hands — Review

Tactile sensing in dexterous robot hands — Review

Stable Grip Control on Soft Objects With Time-Varying Stiffness

Tactile Object Recognition with Semi-Supervised Learning

Contact Info

Product

Resources

About