Evaluation of perpendicularity methods for a robotic end effector from aircraft industry

Santos, Kleber Roberto da Silva; Carvalho, Gustavo Melo de; Tricarico, Rodrigo Tanure; Ferreira, Luiz Fernando Lapetina Rocha; Villani, Emília; Suterio, Ricardo

doi:10.1109/induscon.2018.8627218

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The video stream of the imaging device is processed by a convolutional neural network (CNN). Ensuring perpendicularity is crucial when working in the aerospace manufacturing industry [25][26][27]. 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].…”

Section: Of 14mentioning

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

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%

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

“…According to the principles employed, methods for normal positioning can be categorized as direct laser displacement sensor measurement, reference hole compensation, and projection texture analysis. Among these, laser displacement sensors are the most widely used [19][20][21][22][23][24][25][26]. Zhang et al [27] proposed a theoretical method for spatially determining the normal using four points, calculating the theoretical normal, and adjusting the robot posture through an algorithm to achieve normal positioning during robotic drilling.…”

Section: Introductionmentioning

confidence: 99%

An innovative normal self-positioning method with gravity and friction compensation for wall-climbing drilling robot in aircraft assembly

Xu,

Geng,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

In aircraft manufacturing, the normal accuracy of fastening holes is crucial for the performance and lifetime of the aircraft. However, industrial robots face challenges in achieving precise normal positioning, marked by insufficient rigidity and error amplification. Contemporary methodologies frequently rely extensively on external sensors, encountering limitations in the presence of spatial constraints and low-light conditions. In response to these challenges, this paper presents a wall-climbing drilling robot specifically designed for operation within confined spaces. It innovatively employs an expansion self-positioning mechanism, coupled with robotic joint torque compensation control, to achieve precise normal positioning. The methodology relies on established drilling templates to determine hole positions and normals. By coordinating machinery and control efforts, the robot spindle axis aligns precisely with the axis of the drilling template sleeve, ensuring accurate normal positioning. The paper provides a comprehensive analysis of the mechanical principles governing the expansion self-positioning of the robot and introduces the joint torque compensation control method. The accuracy and effectiveness of the proposed approach are rigorously validated through a series of meticulous drilling experiments. Results demonstrate a significant improvement in the drilling normal accuracy of the wall-climbing drilling robot, meeting the stringent requirements for normal accuracy in aircraft assembly holes.

show abstract

“…The video stream of the imaging device is processed by a convolutional neural network (CNN). Ensuring perpendicularity is crucial when working in the aerospace manufacturing industry [ 29 , 30 , 31 ]. 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 ].…”

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

Evaluation of perpendicularity methods for a robotic end effector from aircraft industry

Cited by 7 publications

References 11 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

An innovative normal self-positioning method with gravity and friction compensation for wall-climbing drilling robot in aircraft assembly

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

Contact Info

Product

Resources

About