Compliant Hand Research Articles

Bayesian Optimization for Robust Robotic Grasping Using a Sensorized Compliant Hand

Bayesian Optimization for Robust Robotic Grasping Using a Sensorized Compliant Hand

Development and validation of a WHO ICF compliant hand and upper limb assessment tool for children: The Reach Out questionnaire

BackgroundCurrent tools for evaluating hand and upper limb function in children do not represent all domains of the World Health Organization International Classification of Disability, Functioning and Health (ICF) framework and may not capture an accurate progression or regression of function over time. PurposeBased on this framework, we have developed an assessment tool (Reach Out) to evaluate function in children aged from 2 to 16 years following consultation with an advisory panel of specialists. Study designPrimary clinical study. MethodsConstruct validity along with test-retest reliability, inter-rater reliability and sensitivity to change have all been analyzed to validate the Reach Out assessment tool. ResultsThe assessment tool has been validated in a total of 231 patients. Significant construct validity of 0.64 (P < .00001, 95% confidence interval = 0.56-0.71, n = 231) for both age groups and diagnostic groups was observed. The Reach Out questionnaire was internally consistent with a Cronbach’s Alpha of > 0.8 for most domains in most age groups. Test re-retest scores showed that the questionnaire was reliable with most domains of the questionnaire achieving high scores of reliability (P ≤ .03). We also received positive feedback from participants and parents. ConclusionsThe use of this new tool will help identify both progression and regression of function, allowing a more tailored and holistic approach to treatment in children with conditions affecting the hand and upper limb through the incorporation of International Classification of Disability, Functioning and Health domains. This tool is quicker to complete and can be applied to a wide range of ages and diagnostic groups compared to previous assessment tools.

Automated Forearm Prosthesis Controlling Using Fiber Bragg Grating Sensor

This paper describes the automation of a forearm prosthesis using the signal collected by a Fiber Bragg Grating (FBG) sensor. The FBG sensor is applied to one subject's forearm to measure the deformation as a result of the index and middle fingers when moved individually. It is possible to control a one joint model prosthesis allied to a compliant hand mechanism through signal analyses. Each finger movement has its features, such as its amplitude, which opens the possibility of using those to control different parts of the prosthesis, joint rotation by the middle finger, and compliant hand movement by the index finger. This paper presents results regarding prosthesis assembling, Hypertext Transfer Protocol (HTTP) communication latency between prosthesis and computer and tests with pre-acquired and processed FBG signal data. The prosthesis wrist rotation movement is related to the middle finger signal, and its compliant mechanism actuation is due to index finger signal. The communication between prosthesis and the computer had a mean latency of 140 ms and a standard deviation of 18 ms. The results demonstrate the potential for using the sensor system and automated prosthesis in other applications involving real-time forearm sensing, multi-finger signal analysis, and prosthetic movement.

Attitudes towards using artificial intelligence to determine real-time hand hygiene compliance in the food sector

Foodhandler hand hygiene is critical to ensure food safety for consumers. Observational studies of foodhandler hand hygiene practices have been conducted in the food sector, although industry values such data the method is time-consuming/expensive. Artificial Intelligence (AI) may provide a solution, it has the potential to distinguish compliant and non-compliant hand hygiene attempts. To inform the development of such technology, this study conducted in-depth interviews ( n = 12) with representatives from food manufacturing and food service businesses, to explore their perceptions of using AI technology to obtain real-time hand hygiene compliance data. A thematic analysis approach determined that both sectors discussed the importance of hand hygiene and were supportive of the proposed concept. Discussions indicated perceived benefits to include constant and longitudinal monitoring, utilizing the technology to inform training, and for assessing training effectiveness. It was discussed that real-time compliance data could be utilised to reward, recognise, and promote compliant behaviour, which in turn may enhance the food safety culture of businesses. Development of the proposed technology, informed by these findings, could single-handedly revolutionise hand hygiene compliance – safeguarding food businesses and consumers. • AI technology has the potential to identify compliant hand hygiene attempts. • The food sector was supportive of using AI to obtain real-time hand hygiene data. • AI technology could inform training needs and assess the impact of training. • Identifying non-compliant individuals would support disciplinary action. • Data could reward and promote compliant behaviour to enhance food safety culture.

Haptic-Based and $SE(3)$-Aware Object Insertion Using Compliant Hands

Object insertion is primarily studied using rigid robotic hands. However, these may have difficulties overcoming spatial uncertainties originating from an uncertain initial grasp. Compliant hands, on the other hand, can cope with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$SE(3)$</tex-math></inline-formula> uncertainties and adapt to the environment upon contact. Nevertheless, contact forces may contribute additional uncertainties and lead to failure if not controlled properly. In this letter, we take inspiration from human insertion and study how <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">haptic glances</i> with compliant hands during contact can provide valuable information regarding object state. Using a force/torque sensor, we show that a haptic glance based on excitation of finger perturbations can provide accurate contact localization and indication of a successful insertion. With such insight, we propose an online learning scheme for general precision control of contact-rich object insertion. A deep residual Reinforcement Learning (RL) policy leverages the contact dynamics of the compliant hand to cope with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$SE(3)$</tex-math></inline-formula> uncertainties. Several experiments of precision insertion tasks with various objects and grasp uncertainties exhibit high success rate and validate the effectiveness of the approach.

Learning Haptic-Based Object Pose Estimation for In-Hand Manipulation Control With Underactuated Robotic Hands.

Unlike traditional robotic hands, underactuated compliant hands are challenging to model due to inherent uncertainties. Consequently, pose estimation of a grasped object is usually performed based on visual perception. However, visual perception of the hand and object can be limited in occluded or partly-occluded environments. In this paper, we aim to explore the use of haptics, i.e., kinesthetic and tactile sensing, for pose estimation and in-hand manipulation with underactuated hands. Such haptic approach would mitigate occluded environments where line-of-sight is not always available. We put an emphasis on identifying the feature state representation of the system that does not include vision and can be obtained with simple and low-cost hardware. For tactile sensing, therefore, we propose a low-cost and flexible sensor that is mostly 3D printed along with the finger-tip and can provide implicit contact information. Taking a two-finger underactuated hand as a test-case, we analyze the contribution of kinesthetic and tactile features along with various regression models to the accuracy of the predictions. Furthermore, we propose a Model Predictive Control (MPC) approach which utilizes the pose estimation to manipulate objects to desired positions solely based on haptics. We have conducted a series of experiments that validate the ability to estimate poses of various objects with different geometry, stiffness and texture, and show manipulation to goals in the workspace with relatively high accuracy.

Grasp compliance achieved with a planar hand composed of multiple 3-joint fingers

AbstractIn this paper, the realization of any specified planar Cartesian compliance for an object grasped by a compliant hand is addressed. The hands considered have 2 or more fingers for which each has 3 modulated elastic joints and predetermined link lengths. Geometric construction-based compliance synthesis procedures are developed. Using these procedures, a large set of compliant behaviors can be realized by a single hand simply by adjusting the configuration of each finger and by adjusting the joint stiffness (using variable stiffness actuation) of each finger joint.

Planar compliance realized with a hand composed of multiple 2-joint fingers

In this paper, a geometric construction based means of realizing any specified planar compliance for an object held by a compliant hand is developed. It is shown that the elastic behavior of an object held by a multi-serial parallel mechanism (a multi-finger compliant hand) is more simply and equivalently modeled by a fully-parallel dual elastic mechanism. Synthesis procedures are developed for the realization of an arbitrary compliance with compliant hands using geometric constraints on the fully-parallel elastic dual. Kinematic topologies addressed are those associated with hands having 2 or 3 fingers for which each finger has 2 joints.

Grasping learning, optimization, and knowledge transfer in the robotics field

Service robotics is a fast-developing sector, requiring embedded intelligence into robotic platforms to interact with the humans and the surrounding environment. One of the main challenges in the field is robust and versatile manipulation in everyday life activities. An appealing opportunity is to exploit compliant end-effectors to address the manipulation of deformable objects. However, the intrinsic compliance of such grippers results in increased difficulties in grasping control. Within the described context, this work addresses the problem of optimizing the grasping of deformable objects making use of a compliant, under-actuated, sensorless robotic hand. The main aim of the paper is, therefore, finding the best position and joint configuration for the mentioned robotic hand to grasp an unforeseen deformable object based on collected RGB image and partial point cloud. Due to the complex grasping dynamics, learning-from-simulations approaches (e.g., Reinforcement Learning) are not effective in the faced context. Thus, trial-and-error-based methodologies have to be exploited. In order to save resources, a samples-efficient approach has to be employed. Indeed, a Bayesian approach to address the optimization of the grasping strategy is proposed, enhancing it with transfer learning capabilities to exploit the acquired knowledge to grasp (partially) new objects. A PAL Robotics TIAGo (a mobile manipulator with a 7-degrees-of-freedom arm and an anthropomorphic underactuated compliant hand) has been used as a test platform, executing a pouring task while manipulating plastic (i.e., deformable) bottles. The sampling efficiency of the data-driven learning is shown, compared to an evenly spaced grid sampling of the input space. In addition, the generalization capability of the optimized model is tested (exploiting transfer learning) on a set of plastic bottles and other liquid containers, achieving a success rate of the 88%.

A Biorealistic Computational Model Unfolds Human-Like Compliant Properties for Control of Hand Prosthesis.

Objective: Human neuromuscular reflex control provides a biological model for a compliant hand prosthesis. Here we present a computational approach to understanding the emerging human-like compliance, force and position control, and stiffness adaptation in a prosthetic hand with a replica of human neuromuscular reflex. Methods: A virtual twin of prosthetic hand was constructed in the MuJoCo environment with a tendon-driven anthropomorphic hand structure. Biorealistic mathematic models of muscle, spindle, spiking-neurons and monosynaptic reflex were implemented in neuromorphic chips to drive the virtual hand for real-time control. Results: Simulation showed that the virtual hand acquired human-like ability to control fingertip position, force and stiffness for grasp, as well as the capacity to interact with soft objects by adaptively adjusting hand stiffness. Conclusion: The biorealistic neuromorphic reflex model restores human-like neuromuscular properties for hand prosthesis to interact with soft objects.

Modeling and Evaluation of a Novel Hybrid-Driven Compliant Hand Exoskeleton Based on Human-Machine Coupling Model

This paper presents the modeling design method for a novel hybrid-driven compliant hand exoskeleton based on the human-machine coupling model for the patients who have requirements on training and assisting. Firstly, the human-machine coupling model is established based on the kinematics characteristics of human fingers and the Bernoulli beam formula. On this basis, the variable stiffness flexible hinge (VSFH) is used to drive the finger extension and the cable-driven mechanism is used to implement the movement of the finger flexion. Here, a hand orthosis is designed in the proposed hand exoskeleton to act as the base and maintain the function position of the hand for patients with hand dysfunction. Then, a final design prototype is fabricated to evaluate the proposed modeling method. In the end, a series of experiments based on the prototype is proceeded to evaluate its capabilities on stretching force for extension, bio-imitability, finger flexion capability, and fingertip force. The results show that the prototype has a significant improvement in all aspects of the ability mentioned above, and has good bionics. The proposed design method can be utilized to implement the rapid design of the hybrid-driven compliant hand exoskeleton with the changed requirements. The novel modeling method can be easily applied in personalized design in rehabilitation engineering.

Design of Soft Grippers with Modular Actuated Embedded Constraints

Underactuated, modular and compliant hands and grippers are interesting solutions in grasping and manipulation tasks due to their robustness, versatility, and adaptability to uncertainties. However, this type of robotic hand does not usually have enough dexterity in grasping. The implementation of some specific features that can be represented as “embedded constraints” allows to reduce uncertainty and to exploit the role of the environment during the grasp. An example that has these characteristics is the Soft ScoopGripper a gripper that has a rigid flat surface in addition to a pair of modular fingers. In this paper, we propose an upgraded version of the Soft ScoopGripper, developed starting from the limits shown by the starting device. The new design exploits a modular structure to increase the adaptability to the shape of the objects that have to be grasped. In the proposed device the embedded constraint is no rigid neither unactuated and is composed of an alternation of rigid and soft modules, which increase versatility. Moreover, the use of soft material such as thermoplastic polyurethane (TPU) reduces the risk of damage to the object being grasped. In the paper, the main design choices have been exploited and a finite element method (FEM) analysis through static simulation supports a characterization of the proposed solution. A complete prototype and some preliminary tests have been presented.

Grasping With the SoftPad, a Soft Sensorized Surface for Exploiting Environmental Constraints With Rigid Grippers

A common trend in robotic manipulation is to build compliant hands that can exploit environmental constraints to perform robust grasps. However, in large-scale industrial applications, end-effectors are mostly rigid. How can we exploit environmental constraints using rigid industrial grippers? We propose to add compliance to the environment, thanks to a soft modular pneumatic surface: the SoftPad. Pressure sensors connected to its modules allow to estimate the object pose and center of mass and to detect the contact between the gripper and the SoftPad during a grasping task. A new grasp strategy that exploits such information for top-grasping objects, without using cameras or force sensors, is presented. It has been tested with objects having a wide range of sizes, shapes, and weights. The SoftPad design can easily be adapted to the set of objects that are used in a certain application.

A Variable-Structure Robot Hand That Uses the Environment to Achieve General Purpose Grasps

Modern robotic grippers are either specialized and simple, complex and general purpose, or soft and compliant hands. The first provide high reliability but are limited in the range of objects they grasp. Compliant or soft grippers can grasp wide ranges of objects, but are not yet reliable enough for real-world applications. This letter presents a novel variable-structure general purpose robotic hand. The planar-acting hand has a minimalistic structure that can adapt itself against the environment to fit a wide range of objects. The single motor, multi-finger hand utilizes a novel principle of re-arranging its structure prior to grasping. This is achieved by pressing the hand against the environment and performing a series of adjustment moves, to best suit the hand for the object to be grasped. The design and method of operation of the hand is explained. Then, a technique for determining the set of adjustments needed to re-arrange the hand according to the desired grasp is sketched. Real-world experiments are performed with the hand, showing its ability to re-arrange itself and grasp previously unseen objects. Source code for the simulations and experiments is supplemented to the paper, as well as a video clip of the variable-structure hand in action.

CORA hand: a 3D printed robotic hand designed for robustness and compliance

This work presents design and experimental evaluation of CORA (COmpliant Robotic hAnd), a robotic hand designed for easy manufacturing and maintenance, and for robustness and compliance in real operational environments. It takes advantage of recent soft-polymer printable filaments to obtain intrinsic compliance during grasping and accidental contacts. All parts are designed and optimized for manufacturing with conventional fused deposition modeling 3D printers, in order to allow simple fabrication and replacement of parts. In this paper design of the CORA hand is presented, focusing on specific design solutions adopted for improving robustness of the final 3D printed parts and for obtaining compliance in interaction with the environment. A prototype of the CORA hand was built and experimentally tested in terms of grasping capabilities, measuring contact forces and the distributed grasping pressure. Compliance introduced by soft polymer links was evaluated with finite element method simulation and experimental bending tests. A collision test evidenced robustness of the finger mechanism and transmission to pronounced passive deformations, induced by lateral contacts possibly occurring in common manipulation tasks.

Influence of the object stiffness on the grasp stability with compliant hand based on energetic approach

Abstract This article presents a stability analysis of object grasping with a compliant multi-fingered robot hand considering the influence of the flexibility of the grasped object on this stability. In this stability analysis we aimed to compute the maximum disturbance that can be withstood by a compliant hand-object system before being destabilized. Here, the case of objects with a compliant behavior that can be synthesized in a stiffness matrix is addressed. The specific example of beam objects and cylindrical grasps is investigated, a computation of the local stiffness matrix of the beam object is proposed using Euler-Bernoulli theory for beam deflection and the influence of the Young modulus of the beam on the stability is evaluated.

Tunable Contact Conditions and Grasp Hydrodynamics Using Gentle Fingertip Suction

Gentle suction flow at the fingertips of a compliant hand can enhance object acquisition and increase the robustness of pinch grasps under water. The approach adds a low-pressure pump and flexible tubes that terminate at the distal phalanges. The light flow rate does not create a powerful suction force, nor does it stir up significant sediment. The method works on porous and rough objects in addition to smooth objects as it does not require forming a seal. It changes contact conditions—normal force and coefficient of friction—and enlarges the acquisition region when grasping free objects under water. A simple hydrodynamic model matches empirical force measurements adequately for incorporation in a dynamic simulation to explore the effects of flow rate and object mass. Simulations and experiments show that effects of fingertip suction flow are most pronounced for acquiring objects on the order of 1 kg or less and when pinching large objects. Gentle suction flow is an effective, versatile, and convenient addition for robots that must grasp and manipulate objects under water.

Robust Precision Manipulation With Simple Process Models Using Visual Servoing Techniques With Disturbance Rejection

This paper presents a high-performance vision-based precision manipulation technique that does not rely on an object, contact, or gripper model, which are challenging and often times impractical to acquire. Instead, we utilize a simple process model that roughly maps object velocities to actuator velocities, and we maintain system efficiency and robustness via advanced vision-based control techniques with disturbance rejection mechanisms. For obtaining simple models, we derive a set of actuator coordination rules for achieving common task space motions. The performance degradation due to modeling inaccuracies is then minimized via the model predictive control framework and a correction matrix method. Our experimental results show that the proposed strategy results in high-performance precision manipulation with minimal modeling effort. Note to Practitioners —Compliant, soft robotic grippers make it easier to grasp objects with various shapes and sizes; these grippers adapt to the shape of the object, which provides robustness to positioning errors and often removes the necessity to precisely plan the contact locations. These advantages make compliant grippers ideal to use in industrial settings as well as in service robotics, where the variety of object shapes and sizes are immense. On the other hand, for the tasks that require precise object manipulation (e.g., for a peg-in-hole problem), these hands are more challenging to control than their rigid counterparts: it is harder to obtain their precise models, and they often do not have enough proprioceptive sensors to calculate the full pose of the system. In this paper, we propose solutions to utilize vision feedback for positioning an object using compliant hands. These solutions do not rely on precise models of the gripper or the full knowledge of the gripper state. We adopt various control techniques to provide precise positioning in steady state as well as to maintain efficiency in the transient.

The Closure Signature: A Functional Approach to Model Underactuated Compliant Robotic Hands

Underactuated and compliant hands, frequently referred to as soft hands, have been recently proposed to overcome common issues of multifingered robotic hands. Although several prototypes have been developed, there is still a lack of systematic ways to model and control these devices to get grasps exploiting their intrinsic features. Classical tools can hardly be applied when contact surfaces are deformable and hand kinematics is not uniquely defined due to underactuation. In this letter, we propose a method to model underactuated compliant hands. The model captures how the hand closes analyzing the motion of suitable reference points defined on the hand. In particular, we present a procedure to compute the preferred grasping direction of a given hand, namely, the closure signature (CS), and then we use this information to plan power grasps. The feasibility of the proposed method has been validated by performing experiments with a soft hand fixed to a robotic arm. The use of the CS proved to increase the performance of the grasp planner. The proposed method can easily be extended to other underactuated compliant hands.

Comparative Peg-in-Hole Testing of a Force-Based Manipulation Controlled Robotic Hand.

Force-based manipulation control strategies are evolving as a primary mechanism in robotics for performing the fine manipulation tasks typical within manufacturing assembly. The ability to systematically compare robotic system performance and quantify true advancement in fine manipulation is of utmost importance. Accordingly, the objectives of this paper are threefold: 1) creation of a peg-in-hole test method with associated performance metrics and a systematic data analysis strategy for performance benchmarking, 2) first demonstration of a recently developed manipulation controller piloting a robotic hand and its paired task-level logic for completing the peg-in-hole test, and 3) exemplifying the performance benchmarking technique by comparing two approaches for robotic insertions-the previously mentioned compliant hand, stiff arm system, and a stiff gripper, compliant arm system. Analyses reveal that the unconventional hand system can perform at and sometimes above the level of the gripper system in the developed peg-in-hole scenario. Moreover, the hand's active control of the peg's full Cartesian pose reduces positional error sensitivity and minimizes exerted insertion forces, highlighting the strategy's potential for fine manipulation tasks. Results indicate that robotic arms equipped with highly articulated and sensorized robotic hands can provide a truly realizable solution path for performing peg-in-hole tasks.