Geometric Conformity Study of a Fin Ray Gripper Utilizing Active Haptic Control

Basson, Christian Ivan; Bright, Glen

doi:10.1109/icca.2019.8899497

Cited by 14 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other designs have moved away from the finger style approach, incorporating sensors in a larger compliant system (Petković et al, 2014 ). With regards to the finger style FRE grippers, sensors have placed on the surface for use within a haptic feedback system (Basson and Bright, 2019 ). These sensors however impact the way that gripper deforms on initial contact and demonstrated a slow system response.…”

Section: Current Literaturementioning

confidence: 99%

A Deep Learning Method for Vision Based Force Prediction of a Soft Fin Ray Gripper Using Simulation Data

Barrie

Pandya²,

Pandya

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

Soft robotic grippers are increasingly desired in applications that involve grasping of complex and deformable objects. However, their flexible nature and non-linear dynamics makes the modelling and control difficult. Numerical techniques such as Finite Element Analysis (FEA) present an accurate way of modelling complex deformations. However, FEA approaches are computationally expensive and consequently challenging to employ for real-time control tasks. Existing analytical techniques simplify the modelling by approximating the deformed gripper geometry. Although this approach is less computationally demanding, it is limited in design scope and can lead to larger estimation errors. In this paper, we present a learning based framework that is able to predict contact forces as well as stress distribution from soft Fin Ray Effect (FRE) finger images in real-time. These images are used to learn internal representations for deformations using a deep neural encoder, which are further decoded to contact forces and stress maps using separate branches. The entire network is jointly learned in an end-to-end fashion. In order to address the challenge of having sufficient labelled data for training, we employ FEA to generate simulated images to supervise our framework. This leads to an accurate prediction, faster inference and availability of large and diverse data for better generalisability. Furthermore, our approach is able to predict a detailed stress distribution that can guide grasp planning, which would be particularly useful for delicate objects. Our proposed approach is validated by comparing the predicted contact forces to the computed ground-truth forces from FEA as well as real force sensor. We rigorously evaluate the performance of our approach under variations in contact point, object material, object shape, viewing angle, and level of occlusion.

show abstract

Section: Current Literaturementioning

confidence: 99%

A Deep Learning Method for Vision Based Force Prediction of a Soft Fin Ray Gripper Using Simulation Data

Barrie

Pandya²,

Pandya

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…By leveraging material softness, they usually feature passive compliance [16], [17], [18] and underactuation [7], [19], [20], leading to a simple control during grasping. Inspired by the Fin-Ray Effect, [16] proposed a novel compliant lattice-structure fingers to enhance grasp robustness and has been widely used in [16], [21], [22]. Most of these grippers have only one actuator, and the adaptive nature of such finger design can quickly achieve form closure of the target object.…”

Section: A Soft Robotic Fingers and Grippersmentioning

confidence: 99%

Learning-based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping

Yang

Han

Guo

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a novel design of a soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping. Machine learning methods are used to train a model for real-time prediction of force, torque, and contact using the tactile data collected. We further integrated such fingers in a reconfigurable gripper design with three fingers so that the finger arrangement can be actively adjusted in real-time based on the tactile data collected during grasping, achieving the process of rigid-soft interactive grasping. Detailed sensor calibration and experimental results are also included to further validate the proposed design for enhanced grasping robustness.

show abstract

“…This work is focused on gripers with passively adaptive structures using the Fin Ray effect [4]. This effect is based on the biomechanical principles of fish fins [13]. After pressing the object on the FinRay finger, the finger flexibly wraps around it [1].…”

Section: Introductionmentioning

confidence: 99%

“…Several studies have already been conducted on Fin Ray structures. Some of them dealt with the dependence of the gripping force on the deformation of the finger when changing the internal geometry and filling [4,13,18], or deal with mathematical models [1] or simulation [1,19]. Some works evaluate the suitability of given fingers only for deformation at the point of contact according to the load [4,13].…”

Section: Introductionmentioning

confidence: 99%

“…Some of them dealt with the dependence of the gripping force on the deformation of the finger when changing the internal geometry and filling [4,13,18], or deal with mathematical models [1] or simulation [1,19]. Some works evaluate the suitability of given fingers only for deformation at the point of contact according to the load [4,13]. Other work [15] evaluate the suitability only for the maximum deformation at the endpoint of the finger.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structural Optimization Method of a FinRay Finger for the Best Wrapping of Object

et al. 2021

View full text Add to dashboard Cite

Soft gripping, in which the gripper adapts to differently shaped objects, is in great demand for use in unknown or dynamically changing environments and is one of the main research subjects in soft robotics. Several systems have already been created, one of which is a passive shape-adaptable finger based on the FinRay effect. The geometric shape of this finger ensures that the finger wraps around the object it grips. FinRay fingers have been studied in several studies, which have changed the internal structure and examined how gripping force’s dependence on finger deformation changes. So far, however, no specific way has been determined to evaluate the proposed finger regarding its ability to wrap around the object. This work comes up with a new and simple method to evaluate the finger’s wrapping around the object mathematically. Based on this evaluation method, several different patterns of the internal structure of FinRay fingers were tested. The fingers were first tested in a simulation program, which simulated a steel roller indentation with a diameter of 20 mm in the middle of the finger’s contact surface. Based on the simulation results, selected types of structure were made by the Fused Filament Fabrication method from a flexible filament and tested on a real test rig to verify the results of the simulation and compare it with the real behaviour. According to the methodology used, the results show that the most suitable structure of the selected tested fingers from the point of view of wrapping the finger around the object is a structure without internal filling. Designers can simply use the new evaluation method to compare their designed finger variants and select the most suitable one according to the ability to wrap around the gripped object. They can also use graphs from this work’s results and determine the finger’s dimensions without internal filling according to the required forces and deflection.

show abstract

Geometric Conformity Study of a Fin Ray Gripper Utilizing Active Haptic Control

Cited by 14 publications

References 14 publications

A Deep Learning Method for Vision Based Force Prediction of a Soft Fin Ray Gripper Using Simulation Data

A Deep Learning Method for Vision Based Force Prediction of a Soft Fin Ray Gripper Using Simulation Data

Learning-based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping

Structural Optimization Method of a FinRay Finger for the Best Wrapping of Object

Contact Info

Product

Resources

About