scholarly journals Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images

Robotica ◽  
2019 ◽  
Vol 38 (7) ◽  
pp. 1242-1262 ◽  
Author(s):  
Nutan Chen ◽  
Göran Westling ◽  
Benoni B. Edin ◽  
Patrick van der Smagt
Keyword(s):  
Neural Networks ◽  
Contact Surface ◽  
Force Estimation ◽  
Robotic Hands ◽  
Dexterous Manipulation ◽  
Color Distribution ◽  
Experimental Environment ◽  
Single Finger ◽  
Fingertip Forces ◽  
Surrounding Skin

SUMMARYThe study of dexterous manipulation has provided important insights into human sensorimotor control as well as inspiration for manipulation strategies in robotic hands. Previous work focused on experimental environment with restrictions. Here, we describe a method using the deformation and color distribution of the fingernail and its surrounding skin to estimate the fingertip forces, torques, and contact surface curvatures for various objects, including the shape and material of the contact surfaces and the weight of the objects. The proposed method circumvents limitations associated with sensorized objects, gloves, or fixed contact surface type. In addition, compared with previous single finger estimation in an experimental environment, we extend the approach to multiple finger force estimation, which can be used for applications such as human grasping analysis. Four algorithms are used, c.q., Gaussian process, convolutional neural networks, neural networks with fast dropout, and recurrent neural networks with fast dropout, to model a mapping from images to the corresponding labels. The results further show that the proposed method has high accuracy to predict force, torque, and contact surface.

scholarly journals The Role of Learning and Kinematic Features in Dexterous Manipulation: A Comparative Study with Two Robotic Hands

10.5772/56479 ◽  
2013 ◽  
Vol 10 (10) ◽  
pp. 340 ◽  
Author(s):  
Anna Lisa Ciancio ◽  
Loredana Zollo ◽  
Gianluca Baldassarre ◽  
Daniele Caligiore ◽  
Eugenio Guglielmelli
Keyword(s):  
Comparative Study ◽  
Robotic Hands ◽  
Dexterous Manipulation

Automated Design of Robotic Hands for In-Hand Manipulation Tasks

2020 ◽  
Vol 17 (01) ◽  
pp. 1950029
Author(s):  
Christopher Hazard ◽  
Nancy Pollard ◽  
Stelian Coros
Keyword(s):  
Kinematic Model ◽  
Automated Design ◽  
Robotic Hand ◽  
Motion Synthesis ◽  
Robotic Hands ◽  
Dexterous Manipulation ◽  
Grasp Planning ◽  
User Input ◽  
High Level

Grasp planning and motion synthesis for dexterous manipulation tasks are traditionally done given a pre-existing kinematic model for the robotic hand. In this paper, we introduce a framework for automatically designing hand topologies best suited for manipulation tasks given high-level objectives as input. Our pipeline is capable of building custom hand designs around specific manipulation tasks based on high-level user input. Our framework comprises of a sequence of trajectory optimizations chained together to translate a sequence of objective poses into an optimized hand mechanism along with a physically feasible motion plan involving both the constructed hand and the object. We demonstrate the feasibility of this approach by synthesizing a series of hand designs optimized to perform specified in-hand manipulation tasks of varying difficulty. We extend our original pipeline 32 to accommodate the construction of hands suitable for multiple distinct manipulation tasks as well as provide an in depth discussion of the effects of each non-trivial optimization term.

scholarly journals Predicting Fingertip Forces by Imaging Coloration Changes in the Fingernail and Surrounding Skin

2008 ◽  
Vol 55 (10) ◽  
pp. 2363-2371 ◽  
Author(s):  
Yu Sun ◽  
John M. Hollerbach ◽  
Stephen A. Mascaro
Keyword(s):  
Fingertip Forces ◽  
Surrounding Skin

scholarly journals Real-time Vehicle Roll Angle Estimation based on IoT low-cost devices and Neural Networks

2018 ◽  
Author(s):  
Javier Garcia-Guzman ◽  
Lisardo Prieto González ◽  
Jonatan Pajares Redondo ◽  
Mat Max Montalvo Martinez ◽  
María Jesús López Boada
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Low Cost ◽  
Roll Angle ◽  
Measurement Unit ◽  
Raspberry Pi ◽  
State Variables ◽  
Angle Estimation ◽  
Experimental Environment ◽  
Time Operation

Given the high number of vehicle-crash victims, it has been established as a priority to reduce this figure in the transportation sector. For this reason, many of the recent researches are focused on including control systems in existing vehicles, to improve their stability, comfort and handling. These systems need to know in every moment the behavior of the vehicle (state variables), among others, when the different maneuvers are performed, to actuate by means of the systems in the vehicle (brakes, steering, suspension) and, in this way, to achieve a good behavior. The main problem arises from the lack of ability to directly capture several required dynamic vehicle variables, such as roll angle, from low-cost sensors. Previous studies demonstrate that low-cost sensors can provide data in real-time with the required precision and reliability. Even more, other research works indicate that neural networks are efficient mechanisms to estimate roll angle. Nevertheless, it is necessary to assess that the fusion of data coming from low-cost devices and estimations provided by neural networks can fulfill the reliability and appropriateness requirements for using these technologies to improve overall safety in production vehicles. Because of the increasing of computing power, the reduction of consumption and electric devices size, along with the high variety of communication technologies and networking protocols using Internet have yield to Internet of Things (IoT) development. In order to address this issue, this study has two main goals: 1) Determine the appropriateness and performance of neural networks embedded in low-cost sensors kits to estimate roll angle required to evaluate rollover risk situations. 2) Compare the low-cost control unit devices (Intel Edison and Raspberry Pi 3 Model B), to provide the roll angle estimation with this artificial neural network-based approach. To fulfil these objectives an experimental environment has been set up composed of a van with two set of low-cost kits, one including a Raspberry Pi 3 Model B, low cost Inertial Measurement Unit (BNO055 - 37€) and GPS (Mtk3339 - 53€) and the other having an Intel Edison System on Chip linked to a SparkFun 9 Degrees of Freedom module. This experimental environment will be tested in different maneuvers for comparison purposes. Neural networks embedded in low-cost sensor kits provide roll angle estimations very approximated to real values. Even more, Intel Edison and Raspberry Pi 3 Model B have enough computing capabilities to successfully run roll angle estimation based on neural networks to determine rollover risks situation fulfilling real-time operation restrictions stated for this problem.

scholarly journals Feasibility Study of Advanced Neural Networks Applied to sEMG-Based Force Estimation

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3226 ◽  
Author(s):  
Lingfeng Xu ◽  
Xiang Chen ◽  
Shuai Cao ◽  
Xu Zhang ◽  
Xun Chen
Keyword(s):  
Neural Networks ◽  
Muscle Force ◽  
Short Term Memory ◽  
Elbow Flexion ◽  
High Accuracy ◽  
Force Estimation ◽  
Short Term ◽  
Long Short Term Memory ◽  
Lstm Network ◽  
Time Subject

To find out the feasibility of different neural networks in sEMG-based force estimation, in this paper, three types of networks, namely convolutional neural network (CNN), long short-term memory (LSTM) network and their combination (C-LSTM) were applied to predict muscle force generated in static isometric elbow flexion across three different circumstances (multi-subject, subject-dependent and subject-independent). Eight healthy men were recruited for the experiments, and the results demonstrated that all the three models were applicable for force estimation, and LSTM and C-LSTM achieved better performances. Even under subject-independent situation, they maintained mean RMSE% of as low as 9.07 ± 1.29 and 8.67 ± 1.14. CNN turned out to be a worse choice, yielding a mean RMSE% of 12.13 ± 1.98. To our knowledge, this work was the first to employ CNN, LSTM and C-LSTM in sEMG-based force estimation, and the results not only prove the strength of the proposed networks, but also pointed out a potential way of achieving high accuracy in real-time, subject-independent force estimation.

Mechanisms for Force Adjustments to Unpredictable Frictional Changes at Individual Digits During Two-Fingered Manipulation

1998 ◽  
Vol 80 (4) ◽  
pp. 1989-2002 ◽  
Author(s):  
Ingvars Birznieks ◽  
Magnus K. O. Burstedt ◽  
Benoni B. Edin ◽  
Roland S. Johansson
Keyword(s):  
Contact Surface ◽  
Normal Force ◽  
Tangential Force ◽  
Sensory Information ◽  
Load Force ◽  
Normal Forces ◽  
Tangential Forces ◽  
Contact Surfaces ◽  
The Right ◽  
Fingertip Forces

Birznieks, Ingvars, Magnus K. O. Burstedt, Benoni B. Edin, and Roland S. Johansson. Mechanisms for force adjustments to unpredictable frictional changes at individual digits during two-fingered manipulation. J. Neurophysiol. 80: 1989–2002, 1998. Previous studies on adaptation of fingertip forces to local friction at individual digit–object interfaces largely focused on static phases of manipulative tasks in which humans could rely on anticipatory control based on the friction in previous trials. Here we instead analyze mechanisms underlying this adaptation after unpredictable changes in local friction between consecutive trials. With the tips of the right index and middle fingers or the right and left index fingers, subjects restrained a manipulandum whose horizontal contact surfaces were located side by side. At unpredictable moments a tangential force was applied to the contact surfaces in the distal direction at 16 N/s to a plateau at 4 N. The subjects were free to use any combination of normal and tangential forces at the two fingers, but the sum of the tangential forces had to counterbalance the imposed load. The contact surface of the right index finger was fine-grained sandpaper, whereas that of the cooperating finger was changed between sandpaper and the more slippery rayon. The load increase automatically triggered normal force responses at both fingers. When a finger contacted rayon, subjects allowed slips to occur at this finger during the load force increase instead of elevating the normal force. These slips accounted for a partitioning of the load force between the digits that resulted in an adequate adjustment of the normal:tangential force ratios to the local friction at each digit. This mechanism required a fine control of the normal forces. Although the normal force at the more slippery surface had to be comparatively low to allow slippage, the normal forces applied by the nonslipping digit at the same time had to be high enough to prevent loss of the manipulandum. The frictional changes influenced the normal forces applied before the load ramp as well as the size of the triggered normal force responses similarly at both fingers, that is, with rayon at one contact surface the normal forces increased at both fingers. Thus to independently adapt fingertip forces to the local friction the normal forces were controlled at an interdigital level by using sensory information from both engaged digits. Furthermore, subjects used both short- and long-term anticipatory mechanisms in a manner consistent with the notion that the central nervous system (CNS) entertains internal models of relevant object and task properties during manipulation.

Sign in / Sign up

Export Citation Format

Share Document