1,720,988 research outputs found
Dexterity Augmentation of Robotic Hands: A Study on the Kinetic Domain
No full textPostural hand synergies, or eigenpostures, are joint angle covariation patterns observed in common grasping tasks. A typical definition associates the geometry of synergy vectors and their hierarchy (relative statistical weight) with the principal component analysis of an experimental covariance matrix. In a reduced complexity representation, the accuracy of hand posture reconstruction is incrementally improved as the number of synergies is increased according to the hierarchy. In this work, we explore whether and how hierarchy and incrementality extend from posture description to grasp force distribution. To do so, we study the problem of optimizing grasps w.r.t. hand/object relative pose and force application, using hand models with an increasing number of synergies, ordered according to a widely used postural basis. The optimization is performed numerically, on a data set of simulated grasps of four objects with a 19-DoF anthropomorphic hand. Results show that the hand/object relative poses that minimize (possibly locally) the grasp optimality index remain roughly the same as more synergies are considered. This suggests that an incremental learning algorithm could be conceived, leveraging on the solution of lower dimensionality problems to progressively address more complex cases as more synergies are added. Second, we investigate whether the adopted hierarchy of postural synergies is indeed the best also for force distribution. Results show that this is not the case
Enhancing Robot-Environment Physical Interaction via Optimal Impedance Profiles
Full text linkPhysical interaction of robots with their environment is a challenging problem because of the exchanged forces. Hybrid position/force control schemes often exhibit problems during the contact phase, whereas impedance control appears to be more simple and reliable, especially when impedance is shaped to be energetically passive. Even if recent technologies enable shaping the impedance of a robot, how best to plan impedance parameters for task execution remains an open question. In this paper we present an optimization-based approach to plan not only the robot motion but also its desired end-effector mechanical impedance. We show how our methodology is able to take into account the transition from free motion to a contact condition, typical of physical interaction tasks. Results are presented for planar and three-dimensional open-chain manipulator arms. The compositionality of mechanical impedance is exploited to deal with kinematic redundancy and multi-arm manipulation
Incrementality and Hierarchies in the Enrollment of Multiple Synergies for Grasp Planning
No full textPostural hand synergies or eigenpostures are joint angle covariation patterns observed in common grasping tasks. A typical definition associates the geometry of synergy vectors and their hierarchy (relative statistical weight) with the principal component analysis of an experimental covariance matrix. In a reduced complexity representation, the accuracy of hand posture reconstruction is incrementally improved as the number of synergies is increased according to the hierarchy. In this work, we explore whether and how hierarchy and incrementality extend from posture description to grasp force distribution. To do so, we study the problem of optimizing grasps w.r.t. hand/object relative pose and force application, using hand models with an increasing number of synergies, ordered according to a widely used postural basis. The optimization is performed numerically, on a data set of simulated grasps of four objects with a 19-DoF anthropomorphic hand. Results show that the hand/object relative poses that minimize (possibly locally) the grasp optimality index remain roughly the same as more synergies are considered. This suggests that an incremental learning algorithm could be conceived, leveraging on the solution of lower dimensionality problems to progressively address more complex cases as more synergies are added. Second, we investigate whether the adopted hierarchy of postural synergies is indeed the best also for force distribution. Results show that this is not the case
Toward brain-heart computer interfaces: A study on the classification of upper limb movements using multisystem directional estimates
Full text linkObjective. Brain-computer interfaces (BCIs) exploit computational features from brain signals to perform a given task. Despite recent neurophysiology and clinical findings indicating the crucial role of functional interplay between brain and cardiovascular dynamics in locomotion, heartbeat information remains to be included in common BCI systems. In this study, we exploit the multidimensional features of directional and functional interplay between electroencephalographic and heartbeat spectra to classify upper limb movements into three classes. Approach. We gathered data from 26 healthy volunteers that performed 90 movements; the data were processed using a recently proposed framework for brain-heart interplay (BHI) assessment based on synthetic physiological data generation. Extracted BHI features were employed to classify, through sequential forward selection scheme and k-nearest neighbors algorithm, among resting state and three classes of movements according to the kind of interaction with objects. Main results. The results demonstrated that the proposed brain-heart computer interface (BHCI) system could distinguish between rest and movement classes automatically with an average 90% of accuracy. Significance. Further, this study provides neurophysiology insights indicating the crucial role of functional interplay originating at the cortical level onto the heart in the upper limb neural control. The inclusion of functional BHI insights might substantially improve the neuroscientific knowledge about motor control, and this may lead to advanced BHCI systems performances
Learning With Few Examples the Semantic Description of Novel Human-Inspired Grasp Strategies From RGB Data
Full text linkData-driven approaches and human inspiration are
fundamental to endow robotic manipulators with advanced autonomous grasping capabilities. However, to capitalize upon these
two pillars, several aspects need to be considered, which include the
number of human examples used for training; the need for having
in advance all the required information for classification (hardly
feasible in unstructured environments); the trade-off between the
task performance and the processing cost. In this letter, we propose
a RGB-based pipeline that can identify the object to be grasped
and guide the actual execution of the grasping primitive selected
through a combination of Convolutional and Gated Graph Neural
Networks. We consider a set of human-inspired grasp strategies,
which are afforded by the geometrical properties of the objects
and identified from a human grasping taxonomy, and propose to
learn new grasping skills with only a few examples. We test our
framework with a manipulator endowed with an under-actuated
soft robotic hand. Even though we use only 2D information to
reduce the footprint of the network, we achieve 90% of successful
identifications of the most appropriate human-inspired grasping
strategy over ten different classes, of which three were few-shot
learned, outperforming an ideal model trained with all the classes,
in sample-scarce conditions
Modeling Human Motor Skills to Enhance Robots’ Physical Interaction
Full text linkThe need for users’ safety and technology acceptability has incredibly increased with the deployment of co-bots physically interacting with humans in industrial settings, and for people assistance. A well-studied approach to meet these requirements is to ensure human-like robot motions and interactions. In this manuscript, we present a research approach that moves from the understanding of human movements and derives usefull guidelines for the planning of arm movements and the learning of skills for physical interaction of robots with the surrounding environment
A user-centered approach to artificial sensory substitution for blind People assistance"egalitarian" approach for special users
No full textArtificial sensory substitution plays a crucial role in different domains, including prosthetics, rehabilitation and assistive technologies. The sense of touch has historically represented the ideal candidate to convey information on the external environment, both contact-related and visual, when the natural action-perception loop is broken or not available. This is particularly true for blind people assistance, in which touch elicitation has been used to make content perceivable (e.g. Braille text or graphical reproduction), or to deliver informative cues for navigation. However, despite the significant technological advancements for what concerns both devices for touch-mediated access to alphanumeric stimuli, and technology- enabled haptic navigation supports, the majority of the pro- posed solutions has met with scarce acceptance in end users community. Main reason for this, in our opinion, is the poor involvement of the blind people in the design process. In this work, we report on a user-centric approach that we successfully applied for haptics- enabled systems for blind people assistance, whose engineering and validation have received significant inputs from the visually-impaired people. We also present an application of our approach to the design of a single-cell refreshable Braille device and to the development of a wearable haptic system for indoor navigation. After a summary of our previous results, we critically discuss next avenues and propose novel solutions for touch-mediated delivery of information for navigation, whose implementation has been totally driven by the feedback collected from real end-users
Kineto-dynamic modeling of human upper limb for robotic manipulators and assistive applications
Full text linkThe sensory-motor architecture of human upper limb and hand is characterized by a complex inter-relation of multiple elements, such as ligaments, muscles, and joints. Nonetheless, humans are able to generate coordinated and meaningful motor actions to interact-and eventually explore-the external environment. Such a complexity reduction is usually studied within the framework of synergistic control, whose focus has been mostly limited on human grasping and manipulation. Little attention has been devoted to the spatio-temporal characterization of human upper limb kinematic strategies and how the purposeful exploitation of the environmental constraints shapes human execution of manipulative actions. In this chapter, we report results on the evidence of a synergistic control of human upper limb and during manipulation with the environment. We propose functional analysis to characterize main spatio-temporal coordinated patterns of arm joints. Furthermore, we study how the environment influences human grasping synergies. The effect of cutaneous impairment is also evaluated. Applications to the design and control of robotic and assistive devices are finally discussed
Estimation of Whole-Body Muscular Activation from an Optimal Set of Scarce Electromyographic Recordings
Full text linkMonitoring workers' status is crucial to prevent work-related musculoskeletal disorders and to enable a safe human-robot interaction. This is typically achieved relying on muscle activation recordings, commonly performed via wearable electromyographic EMG sensors. However, to properly acquire whole-body muscular status, a large number of sensors is needed. This represents a limitation for a real deployment of wearable acquisition systems, due to cost and wearability constraints. To overcome this problem, we propose a solution to provide a reliable muscles estimation from a limited number of EMG recordings. Our method exploits the covariation patterns between muscles activation to complement the recordings coming from a reduced set of optimally placed sensors, minimizing the estimation uncertainty. Using a dataset of EMG data recorded from 10 subjects, we demonstrate that it is possible to reconstruct the temporal evolution of 10 whole-body muscles with a maximum normalized estimation error of 13%, using only 7 EMG sensors
- …
