Search

Electromyography (EMG) signals have been used in designing muscle-machine interfaces (MuMIs) for various applications, ranging from entertainment (EMG controlled games) to human assistance and human augmentation (EMG controlled prostheses and exoskeletons). For this, classical machine learning methods such as Random Forest (RF) models have been used to decode EMG signals. However, these methods depend on several stages of signal pre-processing and extraction of hand-crafted features so as to obtain the desired output. In this work, we propose EMG based frameworks for the decoding of object motions in the execution of dexterous, in-hand manipulation tasks using raw EMG signals input and two novel deep learning (DL) techniques called Temporal Multi-Channel Transformers and Vision Transformers. The results obtained are compared, in terms of accuracy and speed of decoding the motion, with RF-based models and Convolutional Neural Networks as a benchmark. The models are trained for 11 subjects in a motion-object specific and motion-object generic way, using the 10-fold cross-validation procedure. This study shows that the performance of MuMIs can be improved by employing DL-based models with raw myoelectric activations instead of developing DL or classic machine learning models with hand-crafted features. [ABSTRACT FROM AUTHOR]

Over the last decade underactuated, adaptive robot grippers and hands have received an increased interest from the robotics research community. This class of robotic end-effectors can be used in many different fields and scenarios with a very promising application being the development of prosthetic devices. Their suitability for the development of such devices is attributed to the utilization of underactuation that provides increased functionality and dexterity with reduced weight, cost, and control complexity. The most critical components of underactuated, adaptive hands that allow them to perform a broad set of grasp poses are appropriate differential mechanisms that facilitate the actuation of multiple degrees of freedom using a single motor. In this work, we focus on the design, analysis, and experimental validation of a four output geared differential, a series elastic differential, and a whiffletree differential that can incorporate a series of manual and automated locking mechanisms. The locking mechanisms have been developed so as to enhance the control of the differential outputs, allowing for efficient grasp selection with a minimal set of actuators. The differential mechanisms are applied to prosthetic hands, comparing them and describing the benefits and the disadvantages of each. [ABSTRACT FROM AUTHOR]

Adaptive robot hands are typically created by introducing structural compliance either in their joints (e.g., implementation of flexures joints) or in their finger-pads. In this paper, we present a series of alternative uses of structural compliance for the development of simple, adaptive, compliant and/or under-actuated robot grippers and hands that can efficiently and robustly execute a variety of grasping and dexterous, in-hand manipulation tasks. The proposed designs utilize only one actuator per finger to control multiple degrees of freedom and they retain the superior grasping capabilities of the adaptive grasping mechanisms even under significant object pose or other environmental uncertainties. More specifically, in this work, we introduce, discuss, and evaluate: (a) a design of pre-shaped, compliant robot fingers that adapts/conforms to the object geometry, (b) a hyper-adaptive finger-pad design that maximizes the area of the contact patches between the hand and the object, maximizing also grasp stability, and (c) a design that executes compliance adjustable manipulation tasks that can be predetermined by tuning the in-series compliance of the tendon routing system and by appropriately selecting the imposed tendon loads. The grippers are experimentally tested and their efficiency is validated using three different types of tests: (i) grasping tests that involve different everyday objects, (ii) grasp quality tests that estimate the contact area between the grippers and the objects grasped, and (iii) dexterous, in-hand manipulation experiments to evaluate the manipulation capabilities of the Compliance Adjustable Manipulation (CAM) hand. The devices employ mechanical adaptability to facilitate and simplify the efficient execution of robust grasping and dexterous, in-hand manipulation tasks. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) based interfaces are the most common solutions for the control of robotic, orthotic, prosthetic, assistive, and rehabilitation devices, translating myoelectric activations into meaningful actions. Over the last years, a lot of emphasis has been put into the EMG based decoding of human intention, but very few studies have been carried out focusing on the continuous decoding of human motion. In this work, we present a learning scheme for the EMG based decoding of object motions in dexterous, in-hand manipulation tasks. We also study the contribution of different muscles while performing these tasks and the effect of the gender and hand size in the overall decoding accuracy. To do that, we use EMG signals derived from 16 muscle sites (8 on the hand and 8 on the forearm) from 11 different subjects and an optical motion capture system that records the object motion. The object motion decoding is formulated as a regression problem using the Random Forests methodology. Regarding feature selection, we use the following time-domain features: root mean square, waveform length and zero crossings. A 10-fold cross validation procedure is used for model assessment purposes and the feature variable importance values are calculated for each feature. This study shows that subject specific, hand specific, and object specific decoding models offer better decoding accuracy that the generic models. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the formulation of a hybrid methodology that combines analytical models, constrained optimization schemes, and machine learning techniques to simplify the execution of dexterous, in-hand manipulation tasks with adaptive robot hands. More precisely, the constrained optimization scheme is used to describe the kinematics of adaptive hands during the grasping and manipulation processes, unsupervised learning (clustering) is used to group together similar manipulation strategies, dimensionality reduction is used to either extract a set of representative motion primitives (for the identified groups of manipulation strategies) or to solve the manipulation problem in a low-d space and finally an automated experimental setup is used for unsupervised, automated collection of large data sets. We also assess the capabilities of the derived manipulation models and primitives for both model and everyday life objects, and we analyze the resulting manipulation ranges of motion (e.g., object perturbations achieved during the dexterous, in-hand manipulation). We show that the proposed methods facilitate the execution of fingertip-based, within-hand manipulation tasks while requiring minimal sensory information and control effort, and we demonstrate this experimentally on a range of adaptive hands. Finally, we introduce DexRep, an online repository for dexterous manipulation models that facilitate the execution of complex tasks with adaptive robot hands. Note to Practitioners—Robot grasping and dexterous, in-hand manipulations are typically executed with fully actuated robot hands that rely on analytical methods, computation of the hand object system Jacobians, and extensive numerical simulations for deriving optimal strategies. However, these hands require sophisticated sensing elements, complicated control laws, and are not robust to external disturbances or perception uncertainties. Recently, a new class of adaptive hands was proposed which uses structural compliance and underactuation (less motors than the available degrees of freedom) to offer increased robustness and simplicity. In this paper, we propose hybrid methodologies that blend analytical models with constrained optimization schemes and learning techniques to simplify the execution of dexterous, in-hand manipulation tasks with adaptive robot hands. [ABSTRACT FROM AUTHOR]

Switched systems are common in artificial control systems. Here, we suggest that the brain adopts a switched feedforward control of grip forces during manipulation of objects. We measured how participants modulated grip force when interacting with soft and rigid virtual objects when stiffness varied continuously between trials. We identified a sudden phase transition between two forms of feedforward control that differed in the timing of the synchronization between the anticipated load force and the applied grip force. The switch occurred several trials after a threshold stiffness level in the range 100--200 N/m. These results suggest that in the control of grip force, the brain acts as a switching control system. This opens new research questions as to the nature of the discrete state variables that drive the switching. [ABSTRACT FROM AUTHOR]

Classical robotic approaches to tactile object identification often involve rigid mechanical grippers, dense sensor arrays, and exploratory procedures (EPs). Though EPs are a natural method for humans to acquire object information, evidence also exists for meaningful tactile property inference from brief, non-exploratory motions (a ‘haptic glance’). In this work, we implement tactile object identification and feature extraction techniques on data acquired during a single, unplanned grasp with a simple, underactuated robot hand equipped with inexpensive barometric pressure sensors. Our methodology utilizes two cooperating schemes based on an advanced machine learning technique (random forests) and parametric methods that estimate object properties. The available data is limited to actuator positions (one per two link finger) and force sensors values (eight per finger). The schemes are able to work both independently and collaboratively, depending on the task scenario. When collaborating, the results of each method contribute to the other, improving the overall result in a synergistic fashion. Unlike prior work, the proposed approach does not require object exploration, re-grasping, grasp-release, or force modulation and works for arbitrary object start positions and orientations. Due to these factors, the technique may be integrated into practical robotic grasping scenarios without adding time or manipulation overheads. [ABSTRACT FROM PUBLISHER]

A learning scheme based on random forests is used to discriminate between different reach to grasp movements in 3-D space, based on the myoelectric activity of human muscles of the upper-arm and the forearm. Task specificity for motion decoding is introduced in two different levels: Subspace to move toward and object to be grasped. The discrimination between the different reach to grasp strategies is accomplished with machine learning techniques for classification. The classification decision is then used in order to trigger an EMG-based task-specific motion decoding model. Task specific models manage to outperform “general” models providing better estimation accuracy. Thus, the proposed scheme takes advantage of a framework incorporating both a classifier and a regressor that cooperate advantageously in order to split the task space. The proposed learning scheme can be easily used to a series of EMG-based interfaces that must operate in real time, providing data-driven capabilities for multiclass problems, that occur in everyday life complex environments. [ABSTRACT FROM PUBLISHER]

The emerging discussion about the sustainability potential of distributed production is the starting point for this paper. The focus is on the “design global, manufacture local” model. This model builds on the conjunction of the digital commons of knowledge and design with desktop and benchtop manufacturing technologies (from three-dimensional printers and laser cutters to low-tech tools and crafts). Two case studies are presented to illustrate three interlocked practices of this model for degrowth. It is argued that a “design global, manufacture local” model, as exemplified by these case studies, seems to arise in a significantly different political economy from that of the conventional industrial model of mass production. “Design global, manufacture local” may be seen as a platform to bridge digital and knowledge commons with existing physical infrastructures and degrowth communities, in order to achieve distributed modes of collaborative production. [ABSTRACT FROM AUTHOR]

The increasing use of smart technical devices in our everyday lives has necessitated the use of muscle-machine interfaces (MuMI) that are intuitive and that can facilitate immersive interactions with these devices. The most common method to develop MuMIs is using Electromyography (EMG) based signals. However, due to several drawbacks of EMG-based interfaces, alternative methods to develop MuMI are being explored. In our previous work, we presented a new MuMI called Lightmyography (LMG), which achieved outstanding results compared to a classic EMG-based interface in a five-gesture classification task. In this study, we extend our previous work experimentally validating the efficiency of the LMG armband in classifying thirty-two different gestures from six participants using a deep learning technique called Temporal Multi-Channel Vision Transformers (TMC-ViT). The efficiency of the proposed model was assessed using accuracy. Moreover, two different undersampling techniques are compared. The proposed thirty-two-gesture classifiers achieve accuracies as high as 92%. Finally, we employ the LMG interface in the real-time control of a robotic hand using ten different gestures, successfully reproducing several grasp types from taxonomy grasps presented in the literature.

The need for more practical, robust, and affordable prosthetic hands for amputees has led to significant advancements in their functionality. However, the challenge of designing prostheses that balance dexterity, functionality, and affordability still persists. The lack of prosthetic designs that can efficiently address the needs of amputees for both heavy manual labor and social interactions, while also being lightweight and dexterous, is still evident. This paper presents a design for an anthropomorphic, adaptive, lightweight, body-powered prosthetic hand built for performing Activities of Daily Living using a selectively lockable differential mechanism. The proposed differential mechanism allows the users to flex and lock the prosthesis' fingers in a wide range of poses and grasps. The performance of the body-powered prosthesis is experimentally validated with three different types of experiments: i) object grasping, ii) total grasping strength, and iii) individual finger force exertion. The resultant prosthetic hand is lightweight and comfortable to wear and is adequately capable of grasping a wide range of objects, including items commonly used in cleaning and cooking applications where waterproofness is essential.

Evaluating the dexterity of human and robotic hands through appropriate benchmarks, scores, and metrics is of paramount importance for determining how skillful humans are and for designing and developing new bioinspired or even biomimetic end-effectors (e.g., robotic grippers and hands). Dexterity tests have been used in industrial and medical settings to assess how dexterous the hands of workers and surgeons are as well as in robotic rehabilitation settings to determine the improvement or deterioration of the hand function after a stroke or a surgery. In robotics, having a comprehensive dexterity test can allow us to evaluate and compare grippers and hands irrespectively of their design characteristics. However, there is a lack of well defined metrics, benchmarks, and tests that quantify robot dexterity. Previous work has focused on a number of widely accepted functional tests that are used for the evaluation of manual dexterity and human hand function improvement post injury. Each of these tests focuses on a different set of specific tasks and objects. Deriving from these tests, this work proposes a new modular, affordable, accessible, open-source dexterity test for both humans and robots. This test evaluates the grasping and manipulation capabilities by combining the features and best practices of the aforementioned tests, as well as new task categories specifically designed to evaluate dexterous manipulation capabilities. The dexterity test and the accompanying benchmarks allow us to determine the overall hand function recovery and dexterity of robotic end-effectors with ease. More precisely, a dexterity score that ranges from 0 (simplistic, non-dexterous system) to 1 (human-like system) is calculated using the weighted sum of the accuracy and task execution speed subscores. It should also be noted that the dexterity of a robotic system can be evaluated assessing the efficiency of either the robotic hardware, or the robotic perception system, or both. The test and the benchmarks proposed in the study have been validated using extensive human and robot trials. The human trials have been used to determine the baseline scores for the evaluation system. The results show that the time required to complete the tasks reduces significantly with trials indicating a clear learning curve in mastering the dexterous manipulation capabilities associated with the imposed tasks. Finally, the time required to complete the tasks with restricted tactile feedback is significantly higher indicating its importance., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Elangovan, Chang, Gao and Liarokapis.)

Over the last decade, there has been an increased interest in developing aerial robotic platforms that exhibit grasping and perching capabilities not only within the research community but also in companies across different industry sectors. Aerial robots range from standard multicopter vehicles/drones, to autonomous helicopters, and fixed-wing or hybrid devices. Such devices rely on a range of different solutions for achieving grasping and perching. These solutions can be classified as: 1) simple gripper systems, 2) arm-gripper systems, 3) tethered gripping mechanisms, 4) reconfigurable robot frames, 5) adhesion solutions, and 6) embedment solutions. Grasping and perching are two crucial capabilities that allow aerial robots to interact with the environment and execute a plethora of complex tasks, facilitating new applications that range from autonomous package delivery and search and rescue to autonomous inspection of dangerous or remote environments. In this review paper, we present the state-of-the-art in aerial grasping and perching mechanisms and we provide a comprehensive comparison of their characteristics. Furthermore, we analyze these mechanisms by comparing the advantages and disadvantages of the proposed technologies and we summarize the significant achievements in these two research topics. Finally, we conclude the review by suggesting a series of potential future research directions that we believe that are promising., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Meng, Buzzatto, Liu and Liarokapis.)

Currently, ~ 1.5 million American deaf-blind individuals depend on the availability of interpreting services to communicate in their primary conversational language, tactile American Sign Language (ASL). In an effort to give the deaf-blind community access to a device that facilitates independent communication using tactile ASL, we developed TATUM (Tactile ASL Translational User Mechanism). TATUM employs 15 degrees of actuation in a hand-wrist system that is capable of signing the 26-letter ASL alphabet. Leveraging Interpres, an independent cloud-based service, all servo sequences that render desired fingerspelled letters and ASL words are stored in a web application programming interface (API). A validation study including both deaf and deaf-blind participants confirmed that the TATUM hand mimics a human hand both in size and feel. The current design of TATUM attained an average recognition rate of 94.7% in visual validation, indicative of the potential to support deaf and deaf-blind individuals in communicating via visual and tactile ASL.

Recognising and classifying human hand gestures is important for effective communication between humans and machines in applications such as human-robot interaction, human to robot skill transfer, and control of prosthetic devices. Although there are already many interfaces that enable decoding of the intention and action of humans, they are either bulky or they rely on techniques that need careful positioning of the sensors, causing inconvenience when the system needs to be used in real-life scenarios and environments. Moreover, electromyography (EMG), which is the most commonly used technique, captures EMG signals that have a nonlinear relationship with the human intention and motion. In this work, we present lightmyography (LMG) a new muscle machine interfacing method for decoding human intention and motion. Lightmyography utilizes light propagation through elastic media and the change of light luminosity to detect silicone deformation. Lightmyography is similar to forcemyography in the sense that they both record muscular contractions through skin displacements. In order to experimentally validate the efficiency of the proposed method, we designed an interface consisting of five LMG sensors to perform gesture classification experiments. Using this device, we were able to accurately detect a series of different hand postures and gestures. We also compared LMG data with processed EMG data.

With an increasing number of robotic and prosthetic devices, there is a need for intuitive Muscle-Machine Interfaces (MuMIs) that allow the user to have an embodied interaction with the devices they are controlling. Such MuMIs can be developed using machine learning based methods that utilize myoelectric activations from the muscles of the user to decode their intention. However, the choice of the learning method is subjective and depends on the features extracted from the raw Electromyography signals as well as on the intended application. In this work, we compare the performance of five machine learning methods and eight time-domain feature extraction techniques in discriminating between different gestures executed by the user of an EMG based MuMI. From the results, it can be seen that the Willison Amplitude performs consistently better for all the machine learning methods compared in this study, while the Zero Crossings achieves the worst results for the Decision Trees and the Random Forests and the Variance offers the worst performance for all the other learning methods. The Random Forests method is shown to achieve the best results in terms of achieved accuracies (has the lowest variance between subjects). In order to experimentally validate the efficiency of the Random Forest classifier and the Willison Amplitude technique, a series of gestures were decoded in a real-time manner from the myoelectric activations of the operator and they were used to control a robot hand.