Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing

Fang, Wen; Yang, Max; Xing, Yifan; Lepora, Nathan F.; Zhang, Dandan

doi:10.48550/arxiv.2303.02708

Cited by 2 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While Halwani et al [24] achieve better results, this is done using a CNN operating on a conventional camera, hence requiring a source of illumination, being susceptible to motion blur, as well as being computationally more expensive as we show in section ??. The same applies to Tac-VGNN [31], which uses a GNN. However, their GNNs operate synchronously on graphs constructed using a conventional camera, where graph nodes are made of internal markers.…”

Section: Benchmark Resultsmentioning

confidence: 99%

“…Failure to abide by perpendicularity requirements leads to an increase in bending stress and a decrease in fatigue life, thus lowering the reliability of aircraft parts [28,29]. Several other works in the literature use VBTS for contact angle prediction [14,30,31]. Lepora et al [14] use a CNN on binarized images from the camera to estimate the contact pose.…”

Section: Of 14mentioning

confidence: 99%

“…Psomopoulou et al [30] also use a CNN to estimate the contact angle while grasping an object. Finally, [31] extract the markers' positions using blob detection, then construct a 2D graph with markers as nodes using Delaunay triangulation. The graphs are then processed using a graph neural network to predict contact angle.…”

Section: Of 14mentioning

confidence: 99%

See 2 more Smart Citations

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

Sajwani¹,

Ayyad²,

Alkendi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Vision-based tactile sensors (VBTS) have become the de facto method of giving robots the ability to obtain tactile feedback from their environment. Unlike other solutions to tactile sensing, VBTS offers high spatial resolution feedback without compromising on instrumentation costs or incurring additional maintenance expenses. However, conventional cameras used in VBTS have a fixed update rate and output redundant data, leading to computational overhead downstream. In this work, we present a neuromorphic vision-based tactile sensor (N-VBTS) that employs observations from an event-based camera for contact angle prediction. Particularly, we design and develop a novel graph neural network, dubbed TactiGraph, that asynchronously operates on graphs constructed from raw N-VBTS streams exploiting their spatiotemporal correlations to perform predictions. Although conventional VBTS uses an internal illumination source, TactiGraph is reported to perform efficiently in both scenarios, with and without an internal illumination source. Rigorous experimental results revealed that TactiGraph achieved a mean absolute error of 0.62∘ in predicting the contact angle and was faster and more efficient than both conventional VBTS and other N-VBTS, with lower instrumentation costs. Specifically, N-VBTS requires only 5.5% of the compute-time needed by VBTS when both are tested on the same scenario.

show abstract

Section: Benchmark Resultsmentioning

confidence: 99%

Section: Of 14mentioning

confidence: 99%

See 1 more Smart Citation

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

Sajwani¹,

Ayyad²,

Alkendi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Failure to abide by perpendicularity requirements leads to an increase in bending stress and a decrease in fatigue life, thus lowering the reliability of aircraft parts [ 32 , 33 ]. Several other works in the literature use VBTS for contact angle prediction [ 19 , 34 , 35 ]. Lepora et al [ 19 ] use a CNN on binarized images from a camera to estimate the contact pose.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, Ref. [ 35 ] extract the markers’ positions using blob detection, then construct a 2D graph with markers as nodes using Delaunay triangulation. The graphs are then processed using a graph neural network to predict the contact angle.…”

Section: Introductionmentioning

confidence: 99%

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

Sajwani

Ayyad

Alkendi

et al. 2023

Sensors

View full text Add to dashboard Cite

Vision-based tactile sensors (VBTSs) have become the de facto method for giving robots the ability to obtain tactile feedback from their environment. Unlike other solutions to tactile sensing, VBTSs offer high spatial resolution feedback without compromising on instrumentation costs or incurring additional maintenance expenses. However, conventional cameras used in VBTS have a fixed update rate and output redundant data, leading to computational overhead.In this work, we present a neuromorphic vision-based tactile sensor (N-VBTS) that employs observations from an event-based camera for contact angle prediction. In particular, we design and develop a novel graph neural network, dubbed TactiGraph, that asynchronously operates on graphs constructed from raw N-VBTS streams exploiting their spatiotemporal correlations to perform predictions. Although conventional VBTSs use an internal illumination source, TactiGraph is reported to perform efficiently in both scenarios (with and without an internal illumination source) thus further reducing instrumentation costs. Rigorous experimental results revealed that TactiGraph achieved a mean absolute error of 0.62∘ in predicting the contact angle and was faster and more efficient than both conventional VBTS and other N-VBTS, with lower instrumentation costs. Specifically, N-VBTS requires only 5.5% of the computing time needed by VBTS when both are tested on the same scenario.

show abstract

Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing

Cited by 2 publications

References 0 publications

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

TactiGraph: An Asynchronous Graph Neural Network for Contact Angle Prediction Using Neuromorphic Vision-Based Tactile Sensing

Contact Info

Product

Resources

About