Vibrotactile Recognition and Categorization of Surfaces by a Humanoid Robot

Sinapov, Jivko; Sukhoy, Vladimir; Sahai, Ranjana; Stoytchev, Alexander

doi:10.1109/tro.2011.2127130

Cited by 149 publications

(100 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…an attached 3-axis accelerometer in order to classify 20 different surfaces through Support Vector Machine (SVM) and k-nearest neighbor (k-NN) learning techniques [9]. Jamali et al fabricated a biologically inspired artificial finger composed of silicon with two PVDF pressure sensors and two strain gauges.…”

Section: B Backgroundmentioning

confidence: 99%

Re-using prior tactile experience by robotic hands to discriminate in-hand objects via texture properties

Kaboli

Walker

Cheng

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-This paper proposes an online tactile transfer learning strategy for discriminating objects through the surface texture properties via a robotic hand and an artificial robotic skin. The proposed method has the ability to autonomously select and exploit the previously learned multiple texture models while discriminating new textures with a very few available training samples or even one. The experimental results show that employing the proposed method and 10 prior texture models, the robotic hand could discriminate 12 objects via their surface textures with 97% and 100% recognition accuracy with only one and ten training samples respectively. Moreover, the experimental outcomes illustrate that our proposed algorithm is robust against of any negative tactile knowledge transfer.

show abstract

Section: B Backgroundmentioning

confidence: 99%

Re-using prior tactile experience by robotic hands to discriminate in-hand objects via texture properties

Kaboli

Walker

Cheng

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Dynamic refers to robotic setups that perform exploratory movements across the surface to accumulate sensor data. Accelerometers have been used as dynamic vibration sensors for texture discrimination in [6], [7] and [8]. By using only the signal variance of two spatially separated vibration sensors, four different textures could be differentiated in [9].…”

Section: Introductionmentioning

confidence: 99%

“…Other studies have used multiple exploratory movements to boost classification accuracy. For instance, Sinapov et al [8] used five exploratory movements with varying direction and speed, and analyzed the spectrotemporal features to classify twenty naturalistic fine textures with 80% accuracy. Another study kept executing exploratory movements until at least 80% of the movements indicated a specific texture [10].…”

Section: Introductionmentioning

confidence: 99%

Human-Inspired Neurorobotic System for Classifying Surface Textures by Touch

Friedl

Voelker

Peer

et al. 2016

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-Giving robots the ability to classify surface textures requires appropriate sensors and algorithms. Inspired by the biology of human tactile perception, we implement a neurorobotic texture classifier with a recurrent spiking neural network, using a novel semi-supervised approach for classifying dynamic stimuli. Input to the network is supplied by accelerometers mounted on a robotic arm. The sensor data is encoded by a heterogeneous population of neurons, modeled to match the spiking activity of mechanoreceptor cells. This activity is convolved by a hidden layer using bandpass filters to extract nonlinear frequency information from the spike trains. The resulting high-dimensional feature representation is then continuously classified using a neurally implemented support vector machine. We demonstrate that our system classifies 18 metal surface textures scanned in two opposite directions at a constant velocity. We also demonstrate that our approach significantly improves upon a baseline model that does not use the described feature extraction. This method can be performed in real-time using neuromorphic hardware, and can be extended to other applications that process dynamic stimuli online.

show abstract

“…A multisensorial approach can be used for improving the fabric classification as in [4], where data coming from RGB-D, tactile, and photometric stereo sensors are used, but when only one sensor modality is available, the challenge is to find a fabric exploration technique that allow to detect all its discriminative characteristics and also to determine which are the sensor data features that are most effective for discriminating the different type of fabrics. Different approaches have been used to explore object properties, implementing different exploratory behaviours like tapping, sliding, pressing and rubbing [5], [6] showing that there is no predominant way to explore an object, and it usually depends on used sensing modality and on the features to extract. Object classification algorithms are based on a discriminative set of features defined in both time and frequency domains.…”

Section: Introductionmentioning

confidence: 99%

A tactile-based fabric learning and classification architecture

khan

Khosravi

Denei

et al. 2016

2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)

View full text Add to dashboard Cite

Abstract-This paper proposes an architecture for tactile-based fabric learning and classification. The architecture is based on a number of SVM-based learning units, which we call fabric classification cores, specifically trained to discriminate between two fabrics. Each core is based on a specific subset of the fully available set of features, on the basis of their discriminative value, determined using the p-value. During fabric recognition, each core casts a vote. The architecture collects votes and provides an overall classification result. We tested seventeen different fabrics, and the result showed that classification errors are negligible.

show abstract

Vibrotactile Recognition and Categorization of Surfaces by a Humanoid Robot

Cited by 149 publications

References 32 publications

Re-using prior tactile experience by robotic hands to discriminate in-hand objects via texture properties

Re-using prior tactile experience by robotic hands to discriminate in-hand objects via texture properties

Human-Inspired Neurorobotic System for Classifying Surface Textures by Touch

A tactile-based fabric learning and classification architecture

Contact Info

Product

Resources

About