2020
DOI: 10.1109/tii.2019.2898264
|View full text |Cite
|
Sign up to set email alerts
|

A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects

Abstract: This paper addresses the recognition of daily-life objects by a robot equipped with tactile sensors. The main contribution is a deep learning framework that can recognize objects already touched as well as objects never touched before. To this end, we train a Deconvolutional Neural Network that generates synthetic tactile data for novel classes. Then, we use both these synthetic data and the real data collected by touching objects, to train a Convolutional Neural Network to recognize both known (trained) objec… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
13
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 23 publications
(13 citation statements)
references
References 45 publications
0
13
0
Order By: Relevance
“…Abderrahmane et al [32] proposed generating tactile data from semantic descriptions of objects. They provided 19 binary haptic adjectives, which included information about the material and shape of the objects.…”
Section: Estimating Haptic Interaction From Visionmentioning
confidence: 99%
See 1 more Smart Citation
“…Abderrahmane et al [32] proposed generating tactile data from semantic descriptions of objects. They provided 19 binary haptic adjectives, which included information about the material and shape of the objects.…”
Section: Estimating Haptic Interaction From Visionmentioning
confidence: 99%
“…We are, therefore, limited as regards the amount of information processed about the object. Nevertheless, if the item is previously recognised, we could include in the learning pipeline a vector of characteristics describing it, as Abderrahmane et al [32] showed in their work. Then, our system would receive more information about the object.…”
Section: Limitationsmentioning
confidence: 99%
“…OSL has been implemented in tactile-based recognition network for object classification (Kaboli et al, 2016 ). As compared to vision, OSL has not received much attention in tactile recognition, much less in sensorized soft robotics (Abderrahmane et al, 2020 ). Due to lightweight training dataset, this learning approach also allow us to potentially scale up the training process in the future to include more variety of objects.…”
Section: Related Workmentioning
confidence: 99%
“…[70]. AI and CV can be used for tactile recognition [71] to resist the transmission of the SARS-COV-2 virus from various surfaces to the human body by recognizing objects already touched and objects not touched before [72].…”
Section: Diagnosis Of Covid-19 Using Aimentioning
confidence: 99%