A Tactile Sensor-Based Architecture for Collaborative Assembly Tasks with Heavy-Duty Robots

Grella, Francesco; Baldini, Giulia; Canale, Roberto; Sagar, Keerthi; Wang, Si Ao; Albini, Alessandro; Jilich, Michal; Cannata, Giorgio; Zoppi, Matteo

doi:10.1109/icar53236.2021.9659322

Cited by 6 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally used in the medical and biomedical industry for prosthetic rehabilitation or robotic surgery applications ( Al-Handarish et al, 2020 ), tactile technology is now common in robotics. Grasping and manipulation tasks exploit tactile sensors for contact point estimation, surface normals, slip detections, and edge or curvature measurements ( Kuppuswamy et al, 2020 ), ( Dahiya and Valle, 2008 ), while recent applications for physical HRI are proposed by Grella et al (2021 ). These sensors can provide dense and detailed contact information, especially in occluded spaces where vision is unreliable.…”

Section: Methods and Recent Developmentsmentioning

confidence: 99%

“… Li et al (2018b ) mounted pressure sensors on a three-finger gripper and used an SVM for stability prediction; despite the 90% accuracy, the limited performance of SVMs is acknowledged in the previous papers, and the authors encourage the use of more complex algorithms. Grella et al (2021 ) used a tactile skin for an industrial pHRI application gripper by human detection via a simple DNN called HandsNet. Wan et al (2016 ) proposed various LSTM-based DNNs and Pixel Motion to predict contact detection from tactile images generated from the FingerVision sensor, achieving 98.5% accuracy.…”

Section: Methods and Recent Developmentsmentioning

confidence: 99%

See 1 more Smart Citation

Learning-based robotic grasping: A review

2023

View full text Add to dashboard Cite

As personalization technology increasingly orchestrates individualized shopping or marketing experiences in industries such as logistics, fast-moving consumer goods, and food delivery, these sectors require flexible solutions that can automate object grasping for unknown or unseen objects without much modification or downtime. Most solutions in the market are based on traditional object recognition and are, therefore, not suitable for grasping unknown objects with varying shapes and textures. Adequate learning policies enable robotic grasping to accommodate high-mix and low-volume manufacturing scenarios. In this paper, we review the recent development of learning-based robotic grasping techniques from a corpus of over 150 papers. In addition to addressing the current achievements from researchers all over the world, we also point out the gaps and challenges faced in AI-enabled grasping, which hinder robotization in the aforementioned industries. In addition to 3D object segmentation and learning-based grasping benchmarks, we have also performed a comprehensive market survey regarding tactile sensors and robot skin. Furthermore, we reviewed the latest literature on how sensor feedback can be trained by a learning model to provide valid inputs for grasping stability. Finally, learning-based soft gripping is evaluated as soft grippers can accommodate objects of various sizes and shapes and can even handle fragile objects. In general, robotic grasping can achieve higher flexibility and adaptability, when equipped with learning algorithms.

show abstract

Section: Methods and Recent Developmentsmentioning

confidence: 99%

Section: Methods and Recent Developmentsmentioning

confidence: 99%

Learning-based robotic grasping: A review

2023

View full text Add to dashboard Cite

show abstract

“…This paper presents a performance analysis of an architecture which allows a human operator to physically interact with an industrial robot. The system architecture and methodology are already presented in detail in [11] and [12], so it will only be briefly reviewed in this section. Our pipeline builds a 2D representation identified as tactile image from raw tactile data, which is then processed by a binary classifier based on a convolutional neural network which outputs the probability of both hand and non-hand classes.…”

Section: Voluntary Interaction Detection Architecturementioning

confidence: 99%

“…The training set was acquired from human subjects touching and grasping the skin-covered forearm of a robot. In order to improve accuracy on images acquired from the handle we performed a fine-tuning of the network which is presented in detail in [12].…”

Section: Voluntary Interaction Detection Architecturementioning

confidence: 99%

“…The training procedure led to and accuracy of 98.08% and 94.61% on the validation and test sets respectively. The work depicted in [12] also presents an early performance analysis of the detection system on the Jetson Nano board. Results showed a slightly better performance of fp16 against fp32, but the analysis was more conceived as a proof-of-concept for the system and has several differences from the study proposed in this article.…”

Section: Voluntary Interaction Detection Architecturementioning

confidence: 99%

See 1 more Smart Citation

Tactile-Based Human-Robot Collaboration: A Performance Analysis

Grella

Canale²,

Giovinazzo³

et al. 2022

Lecture Notes in Networks and Systems

Self Cite

View full text Add to dashboard Cite

In this paper we present a performance analysis of a perceptual architecture for industrial robots based on tactile sensing. We have developed a human-robot interface based on sensing devices which can be fixed on the robot body or the gripper. The devices are cylindershaped handles covered with tactile sensors, which can be intuitively grasped by an operator. Tactile data are fed into a neural network in order to recognize human touch during grasp, thus providing an enabling command for the control system. We provide an inference time comparison between two computing architectures: a desktop workstation with an high-performance GPU and an embedded solution based on the NVIDIA Jetson Nano board. We also compare inference time obtained from three instances of the neural network, compiled with three different engines: Keras, TensorRT floating-point 16 and TensorRT floating-point 32, showing that numerically optimized models allow to perform inference also on the embedded board without violating timing constraints imposed by data acquisition. Moreover, we assess the robustness of touch recognition when the user is wearing work gloves, showing that the difference from the bare-hand case is negligible.

show abstract