Tactile control based on Gaussian images and its application in bi-manual manipulation of deformable objects

Delgado, Ángel Acuña; Ramón, Juan Antonio Corrales; Mezouar, Youcef; Lequièvre, Laurent; Jara, Carlos A.; Torres, Fernando

doi:10.1016/j.robot.2017.04.017

Cited by 22 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Afterwards, manipulation tasks are planned and performed mostly by readjusting the fingers' positions and applied forces. In [101], they used tactile images created by dynamic Gaussians as a common representation for tactile data. This representation allows merging data from sensors with different resolutions and provides a high-level interface for controlling the pressure applied by each finger.…”

Section: D Objectsmentioning

confidence: 99%

Multi-Modal Sensing and Robotic Manipulation of Non-Rigid Objects: A Survey

2018

View full text Add to dashboard Cite

This paper aims to provide a comprehensive survey of recent advancements in modelling and autonomous manipulation of non-rigid objects. It first summarizes the recent advances in sensing and modelling of such objects with a focus on describing the methods and technologies used to measure their shape and estimate their material and physical properties. Formal representations considered to predict the deformation resulting from manipulation of non-rigid objects are then investigated. The third part provides a survey of planning and control strategies exploited to operate dexterous robotic systems while performing various tasks on objects made of different non-rigid materials.

show abstract

Section: D Objectsmentioning

confidence: 99%

Multi-Modal Sensing and Robotic Manipulation of Non-Rigid Objects: A Survey

2018

View full text Add to dashboard Cite

show abstract

“…Some other works define the contact force as the weighted sum of tactile measurements. Delgado et al [15] proposed creating a tactile image using a mixture of Gaussian with dynamic deviations. The tactile image was used to compute the position and magnitude of the contact force, which guided the grasp adaptation.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, the trained models were unable to generalize to new sensors. The work at hand is inspired by the work from Delgado et al [15] and Zapata-Impala et al [6] that represent tactile data as tactile images. Different from these two works that use a weighted sum method, we first determine the contact region of the fingertip by using a Gaussian mixture model and calculate the force based on the electronic impedance with a high likelihood.…”

Section: Related Workmentioning

confidence: 99%

“…This controller drives the robotic hand to adjust its grasping force so as to track the desired contact configuration and to avoid slippage [12,13]. One crucial technique of the force feedback control is to estimate the contact force from tactile data, which is taken as a feedback signal for the feedback controller [14,15]. Owing to the high-dimensionality of tactile data, most of the previous works define the contact force as a weighted sum of tactile data [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

“…One crucial technique of the force feedback control is to estimate the contact force from tactile data, which is taken as a feedback signal for the feedback controller [14,15]. Owing to the high-dimensionality of tactile data, most of the previous works define the contact force as a weighted sum of tactile data [14][15][16]. Those works ignore the computation of the contact region on the tactile sensor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Grasping Force Control of Multi-Fingered Robotic Hands through Tactile Sensing for Object Stabilization

Deng

Jonetzko

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Grasping force control is important for multi-fingered robotic hands to stabilize the grasped object. Humans are able to adjust their grasping force and react quickly to instabilities through tactile sensing. However, grasping force control through tactile sensing with robotic hands is still relatively unexplored. In this paper, we make use of tactile sensing for multi-fingered robot hands to adjust the grasping force to stabilize unknown objects without prior knowledge of their shape or physical properties. In particular, an online detection module based on Deep Neural Network (DNN) is designed to detect contact events and object material simultaneously from tactile data. In addition, a force estimation method based on Gaussian Mixture Model (GMM) is proposed to compute the contact information (i.e., contact force and contact location) from tactile data. According to the results of tactile sensing, an object stabilization controller is then employed for a robotic hand to adjust the contact configuration for object stabilization. The spatio-temporal property of tactile data is exploited during tactile sensing. Finally, the effectiveness of the proposed framework is evaluated in a real-world experiment with a five-fingered Shadow Dexterous Hand equipped with BioTac sensors.

show abstract