Design and experimental evaluation of a sensorized parallel gripper with optical mirroring mechanism

Faris, Omar; Alyammahi, Huda; Suthar, Bhivraj; Muthusamy, Rajkumar; Shah, Umer Hameed; Hussain, Irfan; Gan, Dongming; Seneviratne, Lakmal; Zweiri, Yahya

doi:10.1016/j.mechatronics.2023.102955

Cited by 5 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some algorithms build on intermediate features such as marker position, optical flow, or depth [4,5,[8][9][10][11][12][13], while others build and train end-to-end models [11,[13][14][15]. The high resolution of VBTS allows robots to perform tasks such as detecting slip [16][17][18], estimating force distribution [5,19], classifying surface textures [20,21], and manipulating of small and soft objects [22,23] as well as many tasks that require dexterity and fine detailed pose estimation.…”

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

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: Of 14mentioning

confidence: 99%

“…Fariborz et al [33,34] use Conv-LSTMs on event-frames constructed from event streams to estimate contact forces. Faris et al [18] uses CNN over accumulated event heatmaps to detect slip. This approach is not asynchronous hence has downtime between constructed event-frames.…”

Section: Challenges With Event-based Vision and Existing Solutionsmentioning

confidence: 99%

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

“…For instance, a parallel gripper with an optical mirroring mechanism based on the Periscope principle is presented in [9], allowing for vision-based sensing to detect slipping during grasping. This gripper has proven to have high gripping reliability with various shapes and weights of gripping objects without slipping.…”

Section: Introductionmentioning

confidence: 99%

A novel rigid-soft gripper for safe and reliable object handling

Trinh,

Nguyen,

Pham

et al. 2024

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

This research paper proposes a novel robotic gripper that combines the advantages of both rigid and soft grippers. The challenge of developing robotic grippers that can handle a wide variety of objects with high precision, especially under harsh vibration is addressed. The gripper uses a main rigid structure for maintaining the stiffness of the robot hand and soft pads under air pressurization for handling the softly and flexibly the objects. The novel conceptual design and structural design are introduced. The gripper design and fabrication were validated through mathematical modelling, analysis, and experimental procedures. In particular, the deformation of the soft element is estimated using numerical simulation and mathematical calculation. Based on the estimation of the soft element's deformation, the contact force is analysed. The experiment confirms that the proposed gripper allows for safe interaction with a variety of grasped objects while maintaining diversity and stability during gripping movement, even under harsh vibration conditions with high frequency. This gripper design can be applied for handling a wide range of objects with varying sizes, masses, fragility, and placement positions. It is particularly useful when the gripping process necessitates both safe interaction and high reliability.

show abstract

“…Some algorithms build on intermediate features such as marker position, optical flow, or depth [ 3 , 10 , 11 , 14 , 15 , 16 , 17 , 18 ], while others build and train end-to-end models [ 3 , 18 , 19 , 20 ]. The high resolution of VBTS allows robots to perform tasks such as detecting slip [ 2 , 21 , 22 ], estimating force distribution [ 11 , 23 ], classifying surface textures [ 24 , 25 ], and manipulating small and soft objects [ 26 , 27 ] as well as many tasks that require dexterity and fine-detailed pose estimation.…”

Section: Introductionmentioning

confidence: 99%

“…Fariborz et al [ 48 , 49 ] use Conv-LSTMs on event-frames constructed from event streams to estimate contact forces. Faris et al [ 22 ] uses CNN over accumulated event heatmaps to detect slip. This approach is not asynchronous and hence has downtime between constructed event-frames.…”

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

Self Cite

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

Design and experimental evaluation of a sensorized parallel gripper with optical mirroring mechanism

Cited by 5 publications

References 21 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

A novel rigid-soft gripper for safe and reliable object handling

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

Contact Info

Product

Resources

About