Search

Humans regularly use all inner surfaces of the hand during manipulation, whereas traditional formulations for robots tend to use only the tips of their fingers, limiting overall dexterity. In this paper, we explore the use of the whole hand during spatial robotic dexterous within-hand manipulation. We present a novel four-fingered robotic hand called the Model B, which is designed and controlled using a straight-forward potential energy-based motion model that is based on the hand configuration and applied actuator torques. In this way the handobject system is driven to a new desired configuration, often through sliding and rolling between the object and hand, and with the fingers "caging" the object to prevent ejection. This paper presents the first ever application of the energy model in three dimensions, which was used to compare the theoretical manipulability of popular robotic hands, which then inspired the design of the Model B. We experimentally validate the hand's performance with extensive benchtop experimentation with test objects and real world objects, as well as on a robotic arm, and demonstrate complex spatial caging manipulation on a variety of objects in all six object dimensions (three translation and three rotation) using all inner surfaces of the fingers and the palm. [ABSTRACT FROM AUTHOR]

Learning accurate representations of robot models remains a challenging problem, and is typically approached though large, system-specific feature sets. This method inherently introduces practical shortcomings, as interpretability and transferability of the learned model typically decreases as more features are introduced into the learning framework in order to handle increasing task complexity. In this article, we examine the problem of developing transferable learned models for dexterous manipulation that are able to accurately predict the behavior of physically distinct systems without retraining. We introduce the notion of learning from visually-extracted grasp mechanics-based features, which are formulated by combining geometrically-inspired, analytical representations of the gripper into the feature set to more holistically represent the state of varied systems performing manipulation. We characterize the added utility of using such features through simulation and incorporate them into a classifier to predict specific phenomena, or modes of manipulation, that occur during prehensile within-hand movement. Four modes of manipulation—normal (rolling contact), drop, stuck, and sliding—are defined, collected physically, and trained via a self-supervised learning approach. The classifier is first trained on a single sensorless underactuated hand variant for all four modes. We, then, investigate the transferability of the learned classifier on five different planar gripper variants—analyzing applicability of this approach with both online and offline evaluation. [ABSTRACT FROM AUTHOR]

The process of modeling a series of hand-object parameters is crucial for precise and controllable robotic in-hand manipulation because it enables the mapping from the hand's actuation input to the object's motion to be obtained. Without assuming that most of these model parameters are known a priori or can be easily estimated by sensors, we focus on equipping robots with the ability to actively self-identify necessary model parameters using minimal sensing. Here, we derive algorithms, on the basis of the concept of virtual linkage-based representations (VLRs), to self-identify the underlying mechanics of hand-object systems via exploratory manipulation actions and probabilistic reasoning and, in turn, show that the self-identified VLR can enable the control of precise in-hand manipulation. To validate our framework, we instantiated the proposed system on a Yale Model O hand without joint encoders or tactile sensors. The passive adaptability of the underactuated hand greatly facilitates the self-identification process, because they naturally secure stable hand-object interactions during random exploration. Relying solely on an in-hand camera, our system can effectively self-identify the VLRs, even when some fingers are replaced with novel designs. In addition, we show in-hand manipulation applications of handwriting, marble maze playing, and cup stacking to demonstrate the effectiveness of the VLR in precise in-hand manipulation control. [ABSTRACT FROM AUTHOR]

Humans use all surfaces of the hand for contact-rich manipulation. Robot hands, in contrast, typically use only the fingertips, which can limit dexterity. In this work, we leveraged a potential energy–based whole-hand manipulation model, which does not depend on contact wrench modeling like traditional approaches, to design a robotic manipulator. Inspired by robotic caging grasps and the high levels of dexterity observed in human manipulation, a metric was developed and used in conjunction with the manipulation model to design a two-fingered dexterous hand, the Model W. This was accomplished by simulating all planar finger topologies composed of open kinematic chains of up to three serial revolute and prismatic joints, forming symmetric two-fingered hands, and evaluating their performance according to the metric. We present the best design, an unconventional robot hand capable of performing continuous object reorientation, as well as repeatedly alternating between power and pinch grasps—two contact-rich skills that have often eluded robotic hands—and we experimentally characterize the hand's manipulation capability. This hand realizes manipulation motions reminiscent of thumb–index finger manipulative movement in humans, and its topology provides the foundation for a general-purpose dexterous robot hand. [ABSTRACT FROM AUTHOR]

Precision manipulation, or moving small objects held in the fingertips, is likely the most heavily utilized class of dexterous within-hand manipulation and adds greatly to the capabilities of the human hand. This article focuses on studying the effects of varying the number of digits used on the resulting manipulation abilities, in terms of translational workspaces and rotational ranges, by manipulating two circular objects, 50 mm and 80 mm in diameter. In general, as the number of digits in contact with the object increases, the results show a significant reduction in precision manipulation workspace range for four of the six translation and rotation directions and no significant change in the other two, suggesting that for these particular metrics, more fingers result in a reduction in performance. Furthermore, while two digits results in the largest workspaces for five of the six translation and rotation axes, the lack of ability to control rotation in the distal-proximal direction suggests that three digits may be more desirable for overall precision manipulation dexterity. [ABSTRACT FROM AUTHOR]

This article is the second in a two-part series analyzing human arm and hand motion during a wide range of unstructured tasks. In this work, we track the hand of healthy individuals as they perform a variety of activities of daily living (ADLs) in three ways decoupled from hand orientation: end-point locations of the hand trajectory, whole path trajectories of the hand, and straight-line paths generated using start and end points of the hand. These data are examined by a clustering procedure to reduce the wide range of hand use to a smaller representative set. Hand orientations are subsequently analyzed for the end-point location clustering results and subsets of orientations are identified in three reference frames: global, torso, and forearm. Data driven methods that are used include dynamic time warping (DTW), DTW barycenter averaging (DBA), and agglomerative hierarchical clustering with Ward’s linkage. Analysis of the end-point locations, path trajectory, and straight-line path trajectory identified 5, 5, and 7 ADL task categories, respectively, while hand orientation analysis identified up to 4 subsets of orientations for each task location, discretized and classified to the facets of a rhombicuboctahedron. Together these provide insight into our hand usage in daily life and inform an implementation in prosthetic or robotic devices using sequential control. [ABSTRACT FROM AUTHOR]

This paper is the first in a two-part series analyzing human arm and hand motion during a wide range of unstructured tasks. The wide variety of motions performed by the human arm during daily tasks makes it desirable to find representative subsets to reduce the dimensionality of these movements for a variety of applications, including the design and control of robotic and prosthetic devices. This paper presents a novel method and the results of an extensive human subjects study to obtain representative arm joint angle trajectories that span naturalistic motions during Activities of Daily Living (ADLs). In particular, we seek to identify sets of useful motion trajectories of the upper limb that are functions of a single variable, allowing, for instance, an entire prosthetic or robotic arm to be controlled with a single input from a user, along with a means to select between motions for different tasks. Data driven approaches are used to discover clusters and representative motion averages for the wrist 3 degree of freedom (DOF), elbow-wrist 4 DOF, and full-arm 7 DOF motions. The proposed method makes use of well-known techniques such as dynamic time warping (DTW) to obtain a divergence measure between motion segments, Ward’s distance criterion to build hierarchical trees, and functional principal component analysis (fPCA) to evaluate cluster variability. The emerging clusters associate various recorded motions into primarily hand start and end location for the full-arm system, motion direction for the wrist-only system, and an intermediate between the two qualities for the elbow-wrist system. [ABSTRACT FROM AUTHOR]

We consider the problem of in-hand dexterous manipulation with a focus on unknown or uncertain hand–object parameters, such as hand configuration, object pose within hand, and contact positions. In particular, in this work we formulate a generic framework for hand–object configuration estimation using underactuated hands as an example. Owing to the passive reconfigurability and the lack of encoders in the hand's joints, it is challenging to estimate, plan, and actively control underactuated manipulation. By modeling the grasp constraints, we present a particle filter-based framework to estimate the hand configuration. Specifically, given an arbitrary grasp, we start by sampling a set of hand configuration hypotheses and then randomly manipulate the object within the hand. While observing the object's movements as evidence using an external camera, which is not necessarily calibrated with the hand frame, our estimator calculates the likelihood of each hypothesis to iteratively estimate the hand configuration. Once converged, the estimator is used to track the hand configuration in real time for future manipulations. Thereafter, we develop an algorithm to precisely plan and control the underactuated manipulation to move the grasped object to desired poses. In contrast to most other dexterous manipulation approaches, our framework does not require any tactile sensing or joint encoders, and can directly operate on any novel objects, without requiring a model of the object a priori. We implemented our framework on both the Yale Model O hand and the Yale T42 hand. The results show that the estimation is accurate for different objects, and that the framework can be easily adapted across different underactuated hand models. In the end, we evaluated our planning and control algorithm with handwriting tasks, and demonstrated the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

Interactions with an object during within-hand manipulation (WIHM) constitutes an assortment of gripping, sliding, and pivoting actions. In addition to manipulation benefits, the re-orientation and motion of the objects within-the-hand also provides a rich array of additional haptic information via the interactions to the sensory organs of the hand. In this article, we utilize variable friction (VF) robotic fingers to execute a rolling WIHM on a variety of objects, while recording ‘proprioceptive’ actuator data, which is then used for object classification (i.e., without tactile sensors). Rather than hand-picking a select group of features for this task, our approach begins with 66 general features, which are computed from actuator position and load profiles for each object-rolling manipulation, based on gradient changes. An Extra Trees classifier performs object classification while also ranking each feature's importance. Using only the six most-important ‘Key Features’ from the general set, a classification accuracy of 86% was achieved for distinguishing the six geometric objects included in our data set. Comparatively, when all 66 features are used, the accuracy is 89.8%. [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]

Human in-hand dexterity can be highly fluid and unstructured, with multiple phalanxes breaking and re-establishing contact during any given task. In contrast, prevailing research in robotic manipulation has focused on highly structured well-controlled motions, where contact points are carefully characterized. Maintaining grasp stability by satisfying traditional closure conditions during complex within-hand manipulation motions can be difficult, even with highly articulated end effectors. However, simple grippers can still achieve an effective range of in-hand manipulation tasks without strict closure conditions, as long as the object can be bounded locally relative to the hand frame. The end effector can be considered as a tool to limit the range of possible object poses. In particular, the energy of the hand-object system can be used to determine an attractor region toward which the hand drives the object. This can be combined with a sparse sampling of the configuration space to find a set of manipulation primitives that can reliably constrain the object inside the hand workspace even without feedback, a strategy proposed as whole-hand caging manipulation. In this paper, experimental results with a planar underactuated gripper are presented to validate this manipulation strategy, and it is shown that even though contacts are regularly broken and reformed, the object can be reliably manipulated within the hand workspace without ejection, and challenging movements such as sliding and gaiting can be reliably performed. [ABSTRACT FROM AUTHOR]

Perching helps small unmanned aerial vehicles (UAVs) extend their time of operation by saving battery power. However, most strategies for UAV perching require complex maneuvering and rely on specific structures, such as rough walls for attaching or tree branches for grasping. Many strategies to perching neglect the UAV's mission such that saving battery power interrupts the mission. We suggest enabling UAVs with the capability of making and stabilizing contacts with the environment, which will allow the UAV to consume less energy while retaining its altitude, in addition to the perching capability that has been proposed before. This new capability is termed "resting." For this, we propose a modularized and actuated landing gear framework that allows stabilizing the UAV on a wide range of different structures by perching and resting. Modularization allows our framework to adapt to specific structures for resting through rapid prototyping with additive manufacturing. Actuation allows switching between different modes of perching and resting during flight and additionally enables perching by grasping. Our results show that this framework can be used to perform UAV perching and resting on a set of common structures, such as street lights and edges or corners of buildings. We show that the design is effective in reducing power consumption, promotes increased pose stability, and preserves large vision ranges while perching or resting at heights. In addition, we discuss the potential applications facilitated by our design, as well as the potential issues to be addressed for deployment in practice. [ABSTRACT FROM AUTHOR]

The human wrist contributes greatly to the mobility of the arm/hand system, empowering dexterity and manipulation capabilities. However, both robotic and prosthetic research communities tend to favor the study and development of end-effectors/terminal devices (hands, grippers, etc.) over wrists. Wrists can improve manipulation capabilities, as they can orient the end-effector of a system without imparting significant translational motion. In this paper, we review the current state of the art of wrist devices, ranging from passive wrist prostheses to actuated robotic wrist devices. We focus on the mechanical design and kinematic arrangements of said devices and provide specifications when available. [ABSTRACT FROM AUTHOR]

Ospreys are renowned for their fishing abilities, which have largely been attributed to their specialized talon morphology and semi-zygodactyly-the ability to rotate the fourth toe to accompany the first toe in opposition of toes II and III. Anecdotal observations indicate that zygodactyly in Ospreys is associated with prey capture, although to our knowledge this has not been rigorously tested. As a first pass toward understanding the functional significance of semi-zygodactyly in Ospreys, we scoured the internet for images of Osprey feet in a variety of circumstances. From these we cross-tabulated the number of times each of three toe configurations (anisodactylous, zygodactylous, and an intermediate condition between these) was associated with different grasping scenarios (e.g., grasping prey or perched), contact conditions (e.g., fish, other objects, or substrate), object sizes (relative to foot size), and grasping behaviors (e.g., using one or both feet). Our analysis confirms an association between zygodactyly and grasping behavior; the odds that an osprey exhibited zygodactyly while grasping objects in flight were 5.7 times greater than whilst perched. Furthermore, the odds of zygodactyly during single-foot grasps were 4.1 times greater when pictured grasping fish compared to other objects. These results suggest a functional association between predatory behavior and zygodactyly and has implications for the selective role of predatory performance in the evolution of zygodactyly more generally. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In this paper, we present the design of a shape-memory-alloy (SMA)-based compliant linear actuator [active cell (AC)] and the use of these in designing and modeling articulated meshes, which form the mechanical subsystem of a class of proposed modular active-cell robots (MACROs). The ACs are capable of undergoing ∼25% strain and groups of cells are connected via passively compliant nodes to produce articulated mesh networks. The deformation of compliant meshes of ACs is modeled by scale-invariant parametric equations derived from the physics of SMA deformations and a reduced-order model of the cells. Parameters of the implemented system were used to develop a simulation platform that predicts the mechanical deformation of the networked robot given electrical inputs at arbitrary nodes of the network. We provide results of several experimental trials used to validate and establish the accuracy of this deformation model. The error in predicting deformations in small meshes is shown to be under 10% over both time-varying inputs and at steady states. [ABSTRACT FROM PUBLISHER]

In this paper, we present an image and model dataset of the real-life objects from the Yale-CMU-Berkeley Object Set, which is specifically designed for benchmarking in manipulation research. For each object, the dataset presents 600 high-resolution RGB images, 600 RGB-D images and five sets of textured three-dimensional geometric models. Segmentation masks and calibration information for each image are also provided. These data are acquired using the BigBIRD Object Scanning Rig and Google Scanners. Together with the dataset, Python scripts and a Robot Operating System node are provided to download the data, generate point clouds and create Unified Robot Description Files. The dataset is also supported by our website, www.ycbbenchmarks.org, which serves as a portal for publishing and discussing test results along with proposing task protocols and benchmarks. [ABSTRACT FROM AUTHOR]

Shape-changing interfaces are a category of device capable of altering their form in order to facilitate communication of information. In this work, we present a shape-changing device that has been designed for navigation assistance. ‘The Animotus’ (previously, ‘The Haptic Sandwich’ ), resembles a cube with an articulated upper half that is able to rotate and extend (translate) relative to the bottom half, which is fixed in the user's grasp. This rotation and extension, generally felt via the user's fingers, is used to represent heading and proximity to navigational targets. The device is intended to provide an alternative to screen or audio based interfaces for visually impaired, hearing impaired, deafblind, and sighted pedestrians. The motivation and design of the haptic device is presented, followed by the results of a navigation experiment that aimed to determine the role of each device DOF, in terms of facilitating guidance. An additional device, ‘The Haptic Taco’, which modulated its volume in response to target proximity (negating directional feedback), was also compared. Results indicate that while the heading (rotational) DOF benefited motion efficiency, the proximity (translational) DOF benefited velocity. Combination of the two DOF improved overall performance. The volumetric Taco performed comparably to the Animotus’ extension DOF. [ABSTRACT FROM PUBLISHER]

Fingertip-based within-hand manipulation, also called precision manipulation, refers to the repositioning of a grasped object within the workspace of a multifingered robot hand without breaking or changing the contact type between each fingertip and the object. Given a robot hand architecture and a set of assumed contact models, this paper presents a method to perform a gross motion analysis of its precision manipulation capabilities, regardless of the particularities of the object being manipulated. In particular, the technique allows the composition of the displacement manifold of the grasped object relative to the palm of the robot hand to be determined as well as the displacements that can be controlled—useful for high-level design and classification of hand function. The effects of a fingertip contacting a body in this analysis are modeled as kinematic chains composed of passive and resistant revolute joints; what permits the introduction of a general framework for the definition and classification of nonfrictional and frictional contact types. Examples of the application of the proposed method in several architectures of multifingered hands with different contact assumptions are discussed; they illustrate how inappropriate contact conditions may lead to uncontrollable displacements of the grasped object. [ABSTRACT FROM PUBLISHER]

Performing dexterous manipulation of unknown objects with robot grippers without using high-fidelity contact sensors, active/sliding surfaces, or a priori workspace exploration is still an open problem in robot manipulation and a necessity for many robotics applications. In this paper we present a two-fingered gripper topology that enables an enhanced predefined in-hand manipulation primitive controlled without knowing the size, shape, or other particulars of the grasped object. The in-hand manipulation behavior, namely, the planar manipulation of the grasped body, is predefined thanks to a simple hybrid low-level control scheme and has an increased range of motion due to the introduction of an elastic pivot joint between the two fingers. Experimental results with a prototype clearly show the advantages and benefits of the proposed concept. Given the generality of the topology and in-hand manipulation principle, researchers and designers working on multiple areas of robotics can benefit from the findings. [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]

This paper applies dimensional synthesis to explore the geometric design of dexterous three-fingered robotic hands for maximizing precision manipulation workspace, in which the hand stably moves an object with respect to the palm of the hand, with contacts only on the fingertips. We focus primarily on the tripod grasp, which is the most commonly used grasp for precision manipulation. We systematically explore the space of design parameters, with two main objectives: maximize the workspace of a fully actuated hand and explore how under-actuation modifies it. We use a mathematical framework that models the hand-plus-object system and examine how the workspace varies with changes in nine hand and object parameters such as link length and finger arrangement on the palm.Results show that to achieve the largest workspaces the palm radius should be approximately half of a finger length larger than the target object radius, that the distal link of the two-link fingers should be around 1–1.2 times the length of the proximal link, and that fingers should be arranged symmetrically about the palm with object contacts also symmetric. Furthermore, a proper parameter design for an under-actuated hand can achieve up to 50% of the workspace of a fully actuated hand. When compared to the system parameters of existing popular hand designs, larger palms and longer distal links are needed to maximize the manipulation workspace of the studied design. [ABSTRACT FROM AUTHOR]