Minas V. Liarokapis

Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems

Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.

Open-source, affordable, modular, light-weight, underactuated robot hands

In this paper we present a series of design directions for the development of affordable, modular, light-weight, intrinsically-compliant, underactuated robot hands, that can be easily reproduced using off-the-shelf materials. The proposed robot hands, efficiently grasp a series of everyday life objects and are considered to be general purpose, as they can be used for various applications. The efficiency of the proposed robot hands has been experimentally validated through a series of experimental paradigms, involving: grasping of multiple everyday life objects with different geometries, myoelectric (EMG) control of the robot hands in grasping tasks, preliminary results on a grasping capable quadrotor and autonomous grasp planning under object position and shape uncertainties.

Open-source, anthropomorphic, underactuated robot hands with a selectively lockable differential mechanism: Towards affordable prostheses

In this paper we present an open-source design for the development of low-complexity, anthropomorphic, underactuated robot hands with a selectively lockable differential mechanism. The differential mechanism used is a variation of the whiffletree (or seesaw) mechanism, which introduces a set of locking buttons that can block the motion of each finger. The proposed design is unique since with a single motor and the proposed differential mechanism the user is able to control each finger independently and switch between different grasping postures in an intuitive manner. Anthropomorphism of robot structure and motion is achieved by employing in the design process an index of anthropomorphism. The proposed robot hands can be easily fabricated using low-cost, off-the-shelf materials and rapid prototyping techniques. The efficacy of the proposed design is validated through different experimental paradigms involving grasping of everyday life objects and execution of daily life activities. The proposed hands can be used as affordable prostheses, helping amputees regain their lost dexterity.

Unplanned, model-free, single grasp object classification with underactuated hands and force sensors

In this paper we present a methodology for discriminating between different objects using only a single force closure grasp with an underactuated robot hand equipped with force sensors. The technique leverages the benefits of simple, adaptive robot grippers (which can grasp successfully without prior knowledge of the hand or the object model), with an advanced machine learning technique (Random Forests). Unlike prior work in literature, the proposed methodology does not require object exploration, release or re-grasping and works for arbitrary object positions and orientations within the reach of a grasp. A two-fingered compliant, underactuated robot hand is controlled in an open-loop fashion to grasp objects with various shapes, sizes and stiffness. The Random Forests classification technique is used in order to discriminate between different object classes. The feature space used consists only of the actuator positions and the force sensor measurements at two specific time instances of the grasping process. A feature variables importance calculation procedure facilitates the identification of the most crucial features, concluding to the minimum number of sensors required. The efficiency of the proposed method is validated with two experimental paradigms involving two sets of fabricated model objects with different shapes, sizes and stiffness and a set of everyday life objects.

Functional Anthropomorphism for human to robot motion mapping

In this paper we propose a generic methodology for human to robot motion mapping for the case of a robotic arm hand system, allowing anthropomorphism. For doing so we discriminate between Functional Anthropomorphism and Perceptional Anthropomorphism, focusing on the first to achieve anthropomorphic solutions of the inverse kinematics for a redundant robot arm. Regarding hand motion mapping, a “wrist” (end-effector) offset to compensate for differences between human and robot hand dimensions is applied and the fingertips mapping methodology is used. Two different mapping scenarios are also examined: mapping for teleoperation and mapping for autonomous operation. The proposed methodology can be applied to a variety of human robot interaction applications, that require a special focus on anthropomorphism.

Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors

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.

Robust model free control of robotic manipulators with prescribed transient and steady state performance

In this paper, we propose a robust model free control scheme of minimal complexity (it is a static scheme involving very few and simple calculations to output the control signal) for robotic manipulators, capable of achieving prescribed transient and steady state performance. No information regarding the robot dynamic model is employed in the design procedure. Moreover, the tracking performance of the developed scheme (i.e., convergence rate and steady state error) is a priori and explicitly imposed by a designer-specified performance function, and is fully decoupled by both the control gains selection and the robot dynamic model. In that respect, the selection of the control gains is only confined to adopting those values that lead to reasonable control effort. Finally, two experimental studies in the joint and the Cartesian workspace clarify the design procedure and verify its performance and robustness against external disturbances.

Task-specific grasp selection for underactuated hands

In this paper, we propose an optimization scheme for deriving task-specific force closure grasps for underactuated robot hands. Motivated by recent neuroscientific studies on the human grasping behavior, a novel grasp strategy is built upon past analysis regarding the task-specificity of human grasps, that also complies with the recent soft synergy model of underactuated hands. Our scheme determines an efficient force closure grasp (i.e., configuration and contact points/forces) with a posture compatible with the desired task, taking into consideration the mechanical and geometric limitations imposed by the design of the hand and the object shape. The efficiency of the algorithm is verified through simulated paradigms on a hypothetical underactuated hand with the kinematic model of the DLR/HIT II five fingered robot hand.

On the effect of human arm manipulability in 3D force tasks: Towards force-controlled exoskeletons

Coupling the human upper limbs with robotic devices is gaining increasing attention in the last decade, due to the emerging applications in orthotics, prosthetics and rehabilitation devices. In the cases of every-day life tasks, force exertion and generally interaction with the environment is absolutely critical. Therefore, the decoding of the users force exertion intention is important for the robust control of orthotic robots (e.g. arm exoskeletons). In this paper, the human arm manipulability is analyzed and its effect on the recruitment of the musculo-skeletal system is explored. It was found that the recruitment and activation of muscles is strongly affected by arm manipulability. Based on this finding, a decoding method is built in order to estimate force exerted in the three-dimensional (3D) task space from surface ElectroMyoGraphic (EMG) signals, recorded from muscles of the arm. The method is using the manipulability information for the given force task. Experimental results were verified in various arm configurations with two subjects.

Post-contact, in-hand object motion compensation for compliant and underactuated hands

The past decade has seen great progress in the development of adaptive, low-complexity, underactuated robot hands. An advantage of these hands is that they use under-constrained mechanisms and compliance, which facilitate grasping even under significant object pose uncertainties. However, for many minimal contact grasps such as precision fingertip grasps, these hands tend to move the object after a grasp is secured, to an equilibrium configuration determined by the elasticity of the mechanism and the contact forces exerted through the robot fingertips. In this paper, we present a methodology based on constrained optimization methods for deriving stable, minimal effort grasps for underactuated robot hands and compensating for post-contact, in-hand parasitic object motions. To do so, we compute the imposed object motions for different object shapes and sizes and we synthesize appropriate robot arm trajectories that eliminate them. The approach allows for the computation of these grasps and motions even for hands with complex, flexure-based, compliant members. The effectiveness of the proposed methods is validated using a redundant robot arm (Barrett WAM) and a two fingered, compliant, underactuated robot hand (Yale Open Hand model T42), for a series of simulated and experimental paradigms.