Bayesian tactile object recognition: Learning and recognising objects using a new inexpensive tactile sensor

Corradi, Tadeo; Hall, Peter M.; Iravani, Pejman

doi:10.1109/icra.2015.7139744

Cited by 19 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BACKGROUND This paper investigates how information can be obtained from tactile data using dimensionality reduction, focussing on principal component analysis (PCA). The most common application of PCA to robot touch has been for a lowdimensional feature extraction preprocessing step before classification [11]- [13]; such approaches have been applied to Zernike moments of the data [11], to the Fast Fourier Transform of the data [12], [13] and on the full tactile images (matrix of pressure values at each taxel) [13]. Another application has been for estimating object pose from touch, by applying PCA to tactile data that is then matched with a point cloud of an object of interest [14].…”

Section: Introductionmentioning

confidence: 99%

Principal Components of Touch

Aquilina

Barton

Lepora

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Our human sense of touch enables us to manipulate our surroundings; therefore, complex robotic manipulation will require artificial tactile sensing. Typically tactile sensor arrays are used in robotics, implying that a straightforward way of interpreting multidimensional data is required. In this paper we present a simple visualisation approach based on applying principal component analysis (PCA) to systematically collected sets of tactile data. We apply the visualisation approach to 4 different types of tactile sensor, encompassing fingertips and vibrissal arrays. The results show that PCA can reveal structure and regularities in the tactile data, which also permits the use of simple classifiers such as k-NN to achieve good inference. Additionally, the Euclidean distance in principal component space gives a measure of sensitivity, which can aid visualisation and also be used to find regions in the tactile input space where the sensor is able to perceive with higher accuracy. We expect that these observations will generalise, and thus offer the potential for novel control methods based on touch.

show abstract

Section: Introductionmentioning

confidence: 99%

Principal Components of Touch

Aquilina

Barton

Lepora

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Another approach is to recognize the contact shapes by extracting shape features from pressure distributions within tactile images. The image descriptors from computer vision have been applied to represent the local contact patterns, e.g., image moments [5], [29], [30], SIFT based features [5], [21] and raw readings [20], [31]. However, there is only a limited number of approaches available for recovering the global object shape by analyzing pressure distributions in tactile images collected at different contact locations.…”

Section: Literature Reviewmentioning

confidence: 99%

iCLAP: shape recognition by combining proprioception and touch sensing

et al. 2018

View full text Add to dashboard Cite

For humans, both the proprioception and touch sensing are highly utilized when performing haptic perception. However, most approaches in robotics use only either proprioceptive data or touch data in haptic object recognition. In this paper, we present a novel method named Iterative Closest Labeled Point (iCLAP) to link the kinesthetic cues and tactile patterns fundamentally and also introduce its extensions to recognize object shapes. In the training phase, the iCLAP first clusters the features of tactile readings into a codebook and assigns these features with distinct label numbers. A 4D point cloud of the object is then formed by taking the label numbers of the tactile features as an additional dimension to the 3D sensor positions; hence, the two sensing modalities are merged to achieve a synthesized perception of the touched object. Furthermore, we developed and validated hybrid fusion strategies, product based and weighted sum based, to combine decisions obtained from iCLAP and single sensing modalities. Extensive experimentation demonstrates a dramatic improvement of object recognition using the proposed methods and it shows great potential to enhance robot perception ability.

show abstract

“…In total, four different features are used and compared, i.e., the Tactile-SIFT descriptors proposed in our previous work [17] and three previous features in the literature, i.e., Zernike moments (the best performing feature used in [15]), normalized Hu's moments [22], raw image moments (up to order 2) [23]. Based on [17], the dictionary size k was set to 50 through the experiments.…”

Section: A Recognition Performances Of Bow Framework With Different mentioning

confidence: 99%

“…6. The recognition rates with tactile information only (BoW) against different number of touches, using our Tactile-SIFT descriptors [17], Zernike moments [15], normalized Hu's moments [22] and raw image moments [23] respectively.…”

Section: A Recognition Performances Of Bow Framework With Different mentioning

confidence: 99%

“…Schneider et al [6] first adapted the Bag-of-Words framework in the tactile object recognition and took tactile images as features directly. In [2] and [15], various feature descriptors from computer vision were studied in tactile image processing. Using a high resolution tactile imager named GelSight, Li et al [16] employed binary descriptors to match features extracted from tactile readings and created tactile maps of objects.…”

Section: B Tactile Patterns Based Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Iterative Closest Labeled Point for tactile object shape recognition

Luo

Mou

Althoefer

et al. 2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Tactile data and kinesthetic cues are two important sensing sources in robot object recognition and are complementary to each other. In this paper, we propose a novel algorithm named Iterative Closest Labeled Point (iCLAP) to recognize objects using both tactile and kinesthetic information. The iCLAP first assigns different local tactile features with distinct label numbers. The label numbers of the tactile features together with their associated 3D positions form a 4D point cloud of the object. In this manner, the two sensing modalities are merged to form a synthesized perception of the touched object. To recognize an object, the partial 4D point cloud obtained from a number of touches iteratively matches with all the reference cloud models to identify the best fit. An extensive evaluation study with 20 real objects shows that our proposed iCLAP approach outperforms those using either of the separate sensing modalities, with a substantial recognition rate improvement of up to 18%.

show abstract

Bayesian tactile object recognition: Learning and recognising objects using a new inexpensive tactile sensor

Cited by 19 publications

References 21 publications

Principal Components of Touch

Principal Components of Touch

iCLAP: shape recognition by combining proprioception and touch sensing

Iterative Closest Labeled Point for tactile object shape recognition

Contact Info

Product

Resources

About