1,720,987 research outputs found
Combining Unsupervised Muscle Co-Contraction Estimation with Bio-Feedback Allows Augmented Kinesthetic Teaching
Full text linkNowadays, an increasingly diversification of products and production lines would largely benefit from intuitive and multimodal robot teaching strategies. The present article proposes an augmented kinesthetic teaching system, which is based on surface electromyographic (sEMG) measurements from the operator forearm. Specifically, sEMG signals are used for minimal-training unsupervised estimation of forearm's muscles co-contraction level. In this way, also exploiting a vibrotactile bio-feedback, we evaluate the ability of operators in stiffening their hand-during kinesthetic teaching-in order to modulate the estimated level of muscle co-contraction to (i) match target levels and (ii) command the opening/closing of a gripper, i.e. in exploiting their sEMG signals for effective augmented robot kinesthetic teaching tasks. Experiments were carried out involving ten subjects in two different kind of experimental sessions, in order to test both co-contraction modulation abilities, and actual usage of the co-contraction for programming robot functionalities during kinesthetic teaching. The obtained results provide positive outcomes on the intuitiveness and effectiveness of the proposed system and approach, paving the way to a new generation of advanced teaching by demonstration interfaces
Combined joint-cartesian mapping for simultaneous shape and precision teleoperation of anthropomorphic robotic hands
Full text linkThere are many applications involving robotic hands in which teleoperation-based approaches are preferred to autonomous solutions. The main reason is that cognitive skills of human operators are desirable in some task scenarios, in order to overcome limitations of robotic hands abilities in dealing with unstructured environments and/or unpredetermined requirements. In particular, in this work we focus on the use of anthropomorphic grasping devices and, specifically, on their teleoperation based on movements of the human operator's hand (the master hand.) Indeed, the mapping of human hand configurations to an anthropomorphic robotic hand (the slave device) is still an open problem, because of the presence of dissimilar kinematics between master and slave that produce shape and/or Cartesian errors - as addressed within our study. In this work, we propose a novel algorithm that combines joint and Cartesian mappings in order to enhance the preservation of both finger shapes and fingertip positions during the teleoperation of the robotic hand. In particular, a transition between the joint and Cartesian mappings is realized on the basis of the distance between the fingertip of the master hands' thumb and the opposite fingers, in which the mapping of the thumb fingertip is specifically addressed. The result of the testing of the algorithm with a ROS-based simulator of a commercially available robotic hand is reported, showing the effectiveness of the proposed mapping
Design and evaluation of a factorization-based grasp myoelectric control founded on synergies
No full textIn this article we present a factorization-based myoelectric proportional control that uses surface skin electromyographic (sEMG) measurements to estimate the hand closure level of a user for telemanipulation purposes. The sEMG-based proportional control design is presented and the results of an experimental session are reported. In particular, involving one healthy subject, four different factorization algorithms are tested (Factor Analysis, Fast Independent Component Analysis, Non-negative Matrix Factorization and Principal Component Analysis) and quantitative evaluated along four different daily session using four different error metrics (Root-Mean-Square Error, Normalized Root-Mean-Square Error, cross-correlation coefficient and Dynamic Time Warping measurement). The metrics are computed comparing the sEMG-based estimation of the hand closure level with a ground-truth signal obtained through a motion tracking system. The results report for better performances of the Non-negative Matrix Factorization algorithm, that can be used for controlling robotic hands in a real telemanipulation scenario. Therefore, the proposed myoelectric proportional control was finally tested in a simple validation grasping scenario using a real robotic hand, reporting for user's simplicity and intuitiveness in regulating the grasp closure in accordance with different objects
Exploiting In-Hand Knowledge in Hybrid Joint-Cartesian Mapping for Anthropomorphic Robotic Hands
Full text linkReplication of human hand motions on anthropomorphic robotic hands is typically treated in literature as the combination of two sub-problems: the measurement of human hand motions, and the mapping of such motions on the robotic hand. In this letter we focus on the second one. Different approaches have been proposed to deal with this problem, but none of them preserves both master finger shapes and fingertip positions on the robotic hand, i.e. ensuring predictability and natural motion for the teleoperator. In this article, we propose a novel hybrid approach that combines both joint and Cartesian mappings in a single solution. In particular, we exploit the a priori, in-hand information related to the areas of the workspace in which thumb and finger fingertips can get in contact. This allows to define, for each finger, a zone of transition from joint to Cartesian mapping. As a consequence, both hand shape during volar grasps and correctness of the fingertip positions for precision grasps are preserved, despite the master-slave kinematic dissimilarities. The proposed hybrid mapping is presented and experimentally evaluated both in simulation and with a real slave anthropomorphic robotic hand
Feedback-aided data acquisition improves myoelectric control of a prosthetic hand
No full textObjective. Pattern-recognition-based myocontrol can be unreliable, which may limit its use in the clinical practice and everyday activities. One cause for this is the poor generalization of the underlying machine learning models to untrained conditions. Acquiring the training data and building the model more interactively can reduce this problem. For example, the user could be encouraged to target the model's instabilities during the data acquisition supported by automatic feedback guidance. Interactivity is an emerging trend in myocontrol of upper-limb electric prostheses: the user should be actively involved throughout the training and usage of the device.
Approach. In this study, 18 non-disabled participants tested two novel feedback-aided acquisition protocols against a standard one that did not provide any guidance. All the protocols acquired data dynamically in multiple arm positions to counteract the limb position effect. During feedback-aided acquisition, an acoustic signal urged the participant to hover with the arm in specific regions of her peri-personal space, de facto acquiring more data where needed. The three protocols were compared on everyday manipulation tasks performed with a prosthetic hand. Main results. Our results showed that feedback-aided data acquisition outperformed the acquisition routine without guidance, both objectively and subjectively. Significance. This indicates that the interaction with the user during the data acquisition is fundamental to improve myocontrol
Automated instability detection for interactive myocontrol of prosthetic hands
Full text linkMyocontrol is control of a prosthetic device using data obtained from (residual) muscle activity. In most myocontrol prosthetic systems, such biological data also denote the subject’s intent: reliably interpreting what the user wants to do, exactly and only when she wants, is paramount to avoid instability, which can potentially lead to accidents, humiliation and trauma. Indeed, instability manifests itself as a failure of the myocontrol in interpreting the subject’s intent, and the automated detection of such failures can be a specific step to improve myocontrol of prostheses—e.g., enabling the possibility of self-adaptation of the system via on-demand model updates for incremental learning, i.e., the interactive myocontrol paradigm. In this work we engaged six expert myocontrol users (five able-bodied subjects and one trans-radial amputee) in a simple, clear grasp-carry-release task, in which the subject’s intent was reasonably determined by the task itself. We then manually ascertained when the intent would not coincide with the behavior of the prosthetic device, i.e., we labeled the failures of the myocontrol system. Lastly, we trained and tested a classifier to automatically detect such failures. Our results show that a standard classifier is able to detect myocontrol failures with a mean balanced error rate of 18.86% over all subjects. If confirmed in the large, this approach could pave the way to self-detection and correction of myocontrol errors, a tighter man-machine co-adaptation, and in the end the improvement of the reliability of myocontrol
Mapping Finger Motions on Anthropomorphic Robotic Hands: Two Realizations of a Hybrid Joint-Cartesian Approach Based on Spatial In-Hand Information
No full textIn literature, two sub-problems are typically identified for the replication of human finger motions on artificial hands: the measurement of the motions on the human side, and the mapping method of human hand movements on the robotic hand. In this study, we focus on the second sub-problem. During human to robot hand mapping, ensuring natural motions and predictability for the operator is a difficult task, since it requires to preserve the Cartesian position of the fingertips and the finger shapes given by the joint values. Several approaches have been presented to deal with this problem, which is still unresolved in general. In this work, we propose an approach for combining joint and Cartesian mapping in a single method. More specifically, we exploit the spatial information available in-hand, in particular, related to the thumb-fingers relative position. In this way, it is possible to perform both volar grasps (where the preservation of finger shapes is more important) and precision grips (where the preservation of fingertip positions is more important) during primary-to-target hand mappings, even if kinematic dissimilarities are present. We therefore report for two specific realizations of this approach: a distance-based hybrid mapping, in which the transition between joint and Cartesian mapping is driven by the approaching of the fingers to the current thumb fingertip position, and a workspace-based hybrid mapping, in which the joint-Cartesian transition is defined on the areas of the workspace in which thumb and finger fingertips can get in contact
Synergy-based control of anthropomorphic robotic hands with contact force sensors
No full textA study on the synergy-based control of an anthropomorphic hand is proposed in this paper. The robotic hand is equipped with three-axis optical force sensors placed on thumb, index, and middle fingertips in order to obtain a better grasping quality in terms of adaptability and contact forces with respect to the physical object properties. A fully-actuated hand is used in the experiments since this allows to select different postural synergies and explore how the hand behaves in case of decoupled finger motion. Therefore, the proposed method can be extended to two different application cases: purely synergy-based contact force control and synergy-based contact force control with decoupled fingers. While the first control strategy allows to simplify the grasping by selecting only the synergy weights in order to obtain the desired value of the mean contact forces among the fingers, the second allows both to control the contact force individually on each finger in order to better adapt the hand to the object and to preserve the simplicity in the grasp design provided by the synergy-based approach. Experimental tests have been performed in both the cases to show the performance of the proposed methods and to highlight the capability of the proposed control strategies to regulate the contact forces properly
A Vision-based Shared Autonomy Framework for Deformable Linear Objects Manipulation
Full text linkThe manipulation of Deformable Linear Objects (DLOs) is a critical process in which the introduction of automation and autonomous systems is still marginal. In this paper, a novel teleoperation framework is proposed in which an intuitive manipulation of DLOs is achieved by means of visual aid. The proposed system could be deployed for manipulating DLOs in hazardous scenarios or for simplifying robot teaching tasks by allowing a faster demonstration time. Experiments are performed involving several subjects and their feedback is collected by means of a survey. The results show that the proposed teleoperation framework simplifies DLOs manipulation and reduces the task completion time by 20% on average
Simulative and Experimental Evaluation of a Soft-DTW Neural Network for sEMG-Based Robotic Grasping
No full textIn this paper, we present a neural network architecture for minimally supervised regression of surface electromyographic (sEMG) signals into control commands to drive robotic grasping devices. The proposed architecture overcomes one of the limitations of state-of-the-art supervised regression approaches, which require an instant by instant labelling of the training dataset. This is achieved by deploying a differentiable version of the Dynamic Time Warping (DTW) similarity measure as loss function of a feed-forward neural network. The effectiveness of this approach was assessed both with simulation and experimental studies. We first used a model of the sEMG generation process to test the feasibility of the method. Then, we evaluated the proposed approach in a two-step experimental session involving a group of 10 subjects: an offline experiment was conducted to investigate neural network performance with desynchronized labelling, whereas an online experiment was carried out to control both a simulated and a real robotic hand. The obtained results demonstrate that the presented method allows minimally supervised regression of sEMG signals, reporting performances comparable with standard supervised approaches. In this relation, we show that the proposed soft-DTW neural network enables successful myocontrol of robotic hands even in presence of substantial temporal misalignments between sEMG trainset and related labelling, while supervised regression totally loses its capabilities. This means that the presented approach allows a greatly simplified training procedure that can pave the way to an innovative myocontrol framework characterized by highly simplified training procedures for the user without performance degradation
- …
