Search

In-hand manipulation with Cartesian-force-control-based pushing primitives is introduced to achieve the precise placement of an object in a desired position at a manufacturing site. In the bin picking process, achieving the desired grasping posture is challenging due to limitations in the sensing and control of the robotic arm, interference from clustered objects, and unintended collisions, which hinder achieving the planned pose. Even under such conditions, in cases that require precise operations, such as manufacturing processes, maintaining a desired placement posture is crucial for the precise placement of objects into the machine slot. In this paper, a pushing primitive incorporating force feedback control is applied to ensure that the gripper is consistently positioned at the edge of the grasped object regardless of the initial grasping position by utilizing the surrounding environment of the processing machine. Modeling the exact contact friction between the gripper and the grasped object is challenging; therefore, instead of relying on a motion planning approach, we addressed the problem using a control method that leverages feedback from the external force information of the robot manipulator. Additional sensors such as external cameras or tactile sensors in the gripper are not required. The pushing primitive is executed by applying a force greater than the frictional force between the gripper and the grasped object, leveraging the surrounding environment. Experimental verification confirmed that the proposed method achieves precise placement into the machine slot, regardless of initial grasping positions. It also proved to be effective on an actual testbed. [ABSTRACT FROM AUTHOR]

This paper introduces the TacFR-Gripper, a novel reconfigurable soft robotic gripper inspired by the Fin-Ray effect and equipped with tactile skin. The gripper incorporates a four-bar mechanism for accurate finger bending and a reconfigurable design to change the relative positions between the fingers and palm, enabling precise and adaptable object grasping. This 5-Degree-of-Freedom (DOF) soft gripper can facilitate dexterous manipulation of objects with diverse shapes and stiffness and is beneficial to the safe and efficient grasping of delicate objects. An array of Force Sensitive Resistor (FSR) sensors is embedded within each robotic fingertip to serve as the tactile skin, enabling the robot to perceive contact information during manipulation. Moreover, we implemented a threshold-based tactile perception approach to enable reliable grasping without accidental slip or excessive force. To verify the effectiveness of the TacFR-Gripper, we provide detailed workspace analysis to evaluate its grasping performance and conducted three experiments, including (i) assessing the grasp success rate across various everyday objects through different finger configurations, (ii) verifying the effectiveness of tactile skin with different control strategies in grasping, and (iii) evaluating the in-hand manipulation capabilities through object pose control. The experimental results indicate that the TacFR-Gripper can grasp a wide range of complex-shaped objects with a high success rate and deliver dexterous in-hand manipulation. Additionally, the integration of tactile skin is demonstrated to enhance grasp stability by incorporating tactile feedback during manipulations. [ABSTRACT FROM AUTHOR]

Human dexterity is an invaluable capability for precise manipulation of objects in complex tasks. The capability of robots to similarly grasp and perform in-hand manipulation of objects is critical for their use in the ever changing human environment, and for their ability to replace manpower. In recent decades, significant effort has been put in order to enable in-hand manipulation capabilities to robotic systems. Initial robotic manipulators followed carefully programmed paths, while later attempts provided a solution based on analytical modeling of motion and contact. However, these have failed to provide practical solutions due to inability to cope with complex environments and uncertainties. Therefore, the effort has shifted to learning-based approaches where data is collected from the real world or through a simulation, during repeated attempts to complete various tasks. The vast majority of learning approaches focused on learning data-based models that describe the system to some extent or Reinforcement Learning (RL). RL, in particular, has seen growing interest due to the remarkable ability to generate solutions to problems with minimal human guidance. In this survey paper, we track the developments of learning approaches for in-hand manipulations and, explore the challenges and opportunities. This survey is designed both as an introduction for novices in the field with a glossary of terms as well as a guide of novel advances for advanced practitioners. [ABSTRACT FROM AUTHOR]

We present a method for enabling Reinforcement Learning of motor control policies for complex skills such as dexterous manipulation. We posit that a key difficulty for training such policies is the difficulty of exploring the problem state space, as the accessible and useful regions of this space form a complex structure along manifolds of the original high-dimensional state space. This work presents a method to enable and support exploration with Sampling-based Planning. We use a generally applicable non-holonomic Rapidly-exploring Random Trees algorithm and present multiple methods to use the resulting structure to bootstrap model-free Reinforcement Learning. Our method is effective at learning various challenging dexterous motor control skills of higher difficulty than previously shown. In particular, we achieve dexterous in-hand manipulation of complex objects while simultaneously securing the object without the use of passive support surfaces. These policies also transfer effectively to real robots. A number of example videos can also be found on the project website: [ABSTRACT FROM AUTHOR]

Clinical measurement. Many daily living tasks require in-hand manipulation (IHM). There is a gap in standardized assessment tools for measuring IHM. The Corbett Targeted Coin Test (CTCT) was designed to allow measurement of that fine motor skill. 1) To evaluate the interrater, test-retest reliability, and validity of the CTCT, and 2) to establish adult norms for the CTCT. Reliability and Validity – 30 participants (25 females, age range 21–45) were assessed with the Nine-Hole Peg test and CTCT consecutively by three researchers, then re-evaluated one week later on the CTCT; Reliability was determined using intraclass correlation (ICC 2,k) between tests and across testers; Criterion-related validity was determined by comparing scores from nine-hole test and CTCT across testers using ICC 2,k. Normative – 190 participants (147 females, age range 20–80) were assessed with the CTCT; mean and standard deviation for participants' scores were calculated by age groups and gender. Test-retest reliability: poor for the right hand (ICCs = −0.29 to 0.45), and poor-moderate for the left hand (ICCs = 0.17–0.56). Inter-rater reliability ranged from moderate to excellent (ICCs = 0.60–0.80). The agreement between CTCT scores and Nine-Hole Peg test was poor for the right (ICC = 0.02; 95% CI: [−0.06, 0.14]) and left hands (ICC = 0.06; 95% CI: [−0.08, 0.28]). CTCT normative data: 41–50 age group demonstrated the highest performance while the 71–80 age group demonstrated the lowest performance. Scores between genders were similar. The poor test-retest reliability of CTCT was probably due to practice effect, while interrater reliability indicated that the test can be administered by different testers without compromising the results. The poor validity between tools proves their different constructs. Use of the CTCT may add another dimension to assessment of dexterity and fine motor skills, specifically, in-hand manipulation, but needs further research on test-retest reliability. • Dexterity assessment. • In-hand manipulation. • Hand function. • Fine motor assessment. [ABSTRACT FROM AUTHOR]

Origami‐inspired mechanisms have found significant applications in end effector design. So far, the exploration of thick‐panel origami has been relatively limited, but it is worth noting that the incorporation of rigid thick panels can introduce unique mechanical properties, showcasing great potential in addressing manipulation challenges. Our previous work has developed a gripper from thick‐panel waterbomb origami, which can pick up a variety of daily objects. Based on the same prototype, this article extends the gripper's function from grasping to in‐hand manipulation, which is attributed to the kinematic bifurcations and compliance of thick‐panel origami. A kinematic study is carried out to investigate the gripper's bifurcated motion modes. The hinge compliance is also taken into account to enhance the gripper's motion dexterity. Theoretical analysis and experiments are conducted to demonstrate both features, thereby paving the foundation for achieving dexterous motions with a simplified control strategy. Aided by a differential mechanism, the gripper can effectively interact with objects with the actuation inputs from only two motors. Objects including balls, cuboids, and cones are explored for in‐hand manipulation under different motion modes, showing varied trajectories. With the integration of tactile sensors at the fingertips, we have also revealed the gripper's potential for classification tasks. [ABSTRACT FROM AUTHOR]

Human dexterity is an invaluable capability for precise manipulation of objects in complex tasks. The capability of robots to similarly grasp and perform in-hand manipulation of objects is critical for their use in the ever changing human environment, and for their ability to replace manpower. In recent decades, significant effort has been put in order to enable in-hand manipulation capabilities to robotic systems. Initial robotic manipulators followed carefully programmed paths, while later attempts provided a solution based on analytical modeling of motion and contact. However, these have failed to provide practical solutions due to inability to cope with complex environments and uncertainties. Therefore, the effort has shifted to learning-based approaches where data is collected from the real world or through a simulation, during repeated attempts to complete various tasks. The vast majority of learning approaches focused on learning data-based models that describe the system to some extent or Reinforcement Learning (RL). RL, in particular, has seen growing interest due to the remarkable ability to generate solutions to problems with minimal human guidance. In this survey paper, we track the developments of learning approaches for in-hand manipulations and, explore the challenges and opportunities. This survey is designed both as an introduction for novices in the field with a glossary of terms as well as a guide of novel advances for advanced practitioners.

Prisma Hand II is an under-actuated prosthetic hand developed at the University of Naples, Federico II to study in-hand manipulations during grasping activities. 3 motors equipped on the robotic hand drive 19 joints using elastic tendons. The operations of the hand are achieved by combining tactile hand sensing with under-actuation capabilities. The hand has the potential to be employed in both industrial and prosthetic applications due to its dexterous motion capabilities. However, currently there are no commercially available tactile sensors with compatible dimensions suitable for the prosthetic hand. Hence, in this work, we develop a novel tactile sensor designed based on an opto-electronic technology for the Prisma Hand II. The optimised dimensions of the proposed sensor made it possible to be integrated with the fingertips of the prosthetic hand. The output voltage obtained from the novel tactile sensor is used to determine optimum grasping forces and torques during in-hand manipulation tasks employing Neural Networks (NNs). The grasping force values obtained using a Convolutional Neural Network (CNN) and an Artificial Neural Network (ANN) are compared based on Mean Square Error (MSE) values to find out a better training network for the tasks. The tactile sensing capabilities of the proposed novel sensing method are presented and compared in simulation studies and experimental validations using various hand manipulation tasks. The developed tactile sensor is found to be showcasing a better performance compared to previous version of the sensor used in the hand.

In-hand manipulation with Cartesian-force-control-based pushing primitives is introduced to achieve the precise placement of an object in a desired position at a manufacturing site. In the bin picking process, achieving the desired grasping posture is challenging due to limitations in the sensing and control of the robotic arm, interference from clustered objects, and unintended collisions, which hinder achieving the planned pose. Even under such conditions, in cases that require precise operations, such as manufacturing processes, maintaining a desired placement posture is crucial for the precise placement of objects into the machine slot. In this paper, a pushing primitive incorporating force feedback control is applied to ensure that the gripper is consistently positioned at the edge of the grasped object regardless of the initial grasping position by utilizing the surrounding environment of the processing machine. Modeling the exact contact friction between the gripper and the grasped object is challenging; therefore, instead of relying on a motion planning approach, we addressed the problem using a control method that leverages feedback from the external force information of the robot manipulator. Additional sensors such as external cameras or tactile sensors in the gripper are not required. The pushing primitive is executed by applying a force greater than the frictional force between the gripper and the grasped object, leveraging the surrounding environment. Experimental verification confirmed that the proposed method achieves precise placement into the machine slot, regardless of initial grasping positions. It also proved to be effective on an actual testbed.

This paper introduces the TacFR-Gripper, a novel reconfigurable soft robotic gripper inspired by the Fin-Ray effect and equipped with tactile skin. The gripper incorporates a four-bar mechanism for accurate finger bending and a reconfigurable design to change the relative positions between the fingers and palm, enabling precise and adaptable object grasping. This 5-Degree-of-Freedom (DOF) soft gripper can facilitate dexterous manipulation of objects with diverse shapes and stiffness and is beneficial to the safe and efficient grasping of delicate objects. An array of Force Sensitive Resistor (FSR) sensors is embedded within each robotic fingertip to serve as the tactile skin, enabling the robot to perceive contact information during manipulation. Moreover, we implemented a threshold-based tactile perception approach to enable reliable grasping without accidental slip or excessive force. To verify the effectiveness of the TacFR-Gripper, we provide detailed workspace analysis to evaluate its grasping performance and conducted three experiments, including (i) assessing the grasp success rate across various everyday objects through different finger configurations, (ii) verifying the effectiveness of tactile skin with different control strategies in grasping, and (iii) evaluating the in-hand manipulation capabilities through object pose control. The experimental results indicate that the TacFR-Gripper can grasp a wide range of complex-shaped objects with a high success rate and deliver dexterous in-hand manipulation. Additionally, the integration of tactile skin is demonstrated to enhance grasp stability by incorporating tactile feedback during manipulations.

Origami‐inspired mechanisms have found significant applications in end effector design. So far, the exploration of thick‐panel origami has been relatively limited, but it is worth noting that the incorporation of rigid thick panels can introduce unique mechanical properties, showcasing great potential in addressing manipulation challenges. Our previous work has developed a gripper from thick‐panel waterbomb origami, which can pick up a variety of daily objects. Based on the same prototype, this article extends the gripper's function from grasping to in‐hand manipulation, which is attributed to the kinematic bifurcations and compliance of thick‐panel origami. A kinematic study is carried out to investigate the gripper's bifurcated motion modes. The hinge compliance is also taken into account to enhance the gripper's motion dexterity. Theoretical analysis and experiments are conducted to demonstrate both features, thereby paving the foundation for achieving dexterous motions with a simplified control strategy. Aided by a differential mechanism, the gripper can effectively interact with objects with the actuation inputs from only two motors. Objects including balls, cuboids, and cones are explored for in‐hand manipulation under different motion modes, showing varied trajectories. With the integration of tactile sensors at the fingertips, we have also revealed the gripper's potential for classification tasks.

In-hand manipulation to translate and rotate an object is a challenging problem for robotic hands. As one solution, robotic hand with belts around fingers ( $active~surfaces$ ) has been developed for continuous and seamless manipulation. However, in practice, the grasped object can only be rotated through a small range less than 90° except the objects with simple shapes like cubes and cylinders. This is because the fingers cannot follow the width required not to drop the object or the desired rotation cannot be produced depending on its shape, leading to dropping the object or unable to rotate it anymore. This paper presents a method to address these problems and rotate objects of various shape and sizes through a large range of motion. A stereo camera is attached to a two-fingered robotic hand with belts. The changes in the contact points between the surfaces of the belts and object are predicted. Based on the prediction, the belts are controlled to adjust the angular velocity of the object such that the fingers can follow the width required to grasp it and the appropriate rotation can be produced. The fingers are controlled to follow the predicted contact points and deflect the belts to both cancel the unwanted rotation and generate the desired rotation. Through experiments in which 32 objects of 16 shapes and 2 sizes, and other real-world objects were rotated to 1 revolution, the rotational ranges for various objects were larger than in the other studies, confirming the validity of the proposed method.

We develop a conditional generative model to represent dexterous grasp postures of a robotic hand and use it to generate in-hand regrasp trajectories. Our model learns to encode the robotic grasp postures into a low-dimensional space, called Synergy Space, while taking into account additional information about the object such as its size and its shape category. We then generate regrasp trajectories through linear interpolation in this low-dimensional space. The result is that the hand configuration moves from one grasp type to another while keeping the object stable in the hand. We show that our model achieves higher success rate on in-hand regrasping compared to previous methods used for synergy extraction, by taking advantage of the grasp size conditional variable. [ABSTRACT FROM AUTHOR]

One of the hallmarks of a dexterous robotic hand is the ability to perform in-hand manipulation (i.e., without re-grasping). In the field of robotic hand design, however, there are competing interests between dexterity, simplicity, and reconfigurability. It can be difficult to achieve all of these objectives simultaneously. This paper presents the design of a simple underactuated grasper which uses a gimbal and parallelogram mechanism to achieve in-hand manipulation while maintaining grasp. The new grasper also integrates elements which make it reconfigurable or metamorphic, and is readily adapted for different types of robotic fingers. The design is validated with a physical prototype, and its performance related to in-hand manipulation is evaluated using multibody simulations, showing improved range of reorientation of grasped objects compared to a more standard fixed-palm underactuated finger design. [ABSTRACT FROM AUTHOR]

Achieving both compliant grasping and robust in-hand manipulation for a robotic hand is a challenging task, especially for fragile or irregularly shaped objects. Active surface grippers usually rely on non-stretchable belts and compliant finger mechanisms for adaptive manipulation and grasping, requiring complex tensioning mechanisms that increase mechanical complexity. This paper presents a novel design of an active elastic band-based gripper, that can achieve translation and rotation of grasped objects with passive adaptive wrapping and active conveyor motion. The design utilizes pre-tensioned elastic bands that function simultaneously as an adaptive grasping mechanism and an active surface, conforming to the shape of the object shape and providing evenly distributed gripping forces. The principles of grasping and manipulation, as well as the fabrication process of the gripper are presented in this work, and the kinematics and workspace of the gripper with cylindrical objects are analyzed. Based on experiments, the contact stiffness model of the elastic band finger with cylindrical objects was established. To evaluate the performance of the gripper, we carried out experiments on manipulation objects with different shapes and sizes, such as boiled eggs, and fruits. Experimental results illustrated the adaptable grasping and stable in-hand manipulation ability of the gripper. [Display omitted] • A robotic gripper using elastic active surfaces to adaptively wrap and manipulate various objects is designed in this paper. • This gripper design with dual active elastic surfaces exhibits enhanced adaptability for diverse object operation. • Experiments show that the elastic band adaptive wrapping enables the design to manipulate objects with high dexterity. [ABSTRACT FROM AUTHOR]

In this paper, we seek performing dynamic in-hand object manipulation with two-segmented soft fingers in 2-D plane. Thereby, after the dynamic behavior of the soft fingers was defined, we evaluate the influence of external tip force on the finger. It is shown that the tip position error, under the effect of tip force, can be represented by uncertainties in kinematic parameters of the finger. As a result, we design a sliding-adaptive controller with compensation of kinematic uncertainties to fulfill our expectation that is controlling the tip position of the finger in vertical plane while interacting with the environment. Finally, inspired by the way that human fingers manipulate an object, a cooperative control system for manipulation is proposed which incorporates the states and tip positions of the fingers in its feedback signal. Combination of this controller with the adaptive control system yields more promising results than does the PID controller. In order to evaluate performance of the proposed controller, Simulation results for manipulation of a cubic rigid object are demonstrated. [ABSTRACT FROM AUTHOR]

Aim: Accurate assessment of in-hand manipulation is imperative when treating children with fine motor delays. A clinically suitable instrument for in-hand manipulation is required to inform the paediatric developmental and rehabilitation context. Critical evaluation of the available instrument is required to make an informed decision and direct future research. The aim of the study was to assess the available literature with a view to writing a scoping review on in-hand manipulation assessment instruments for children. Methods: The Arskey and O'Malley six-stage scoping review was applied. Fifteen databases were sourced for articles published between 1 January 1990 and 31 December 2020. After identifying 33 eligible articles that met the inclusion criteria, the data obtained from the articles were charted. Results: Eleven in-hand manipulation assessment instruments were identified and summarised according to (i) the constructs of in-hand manipulation included; (ii) clinical utility aspects of applicability and practicality and (iii) psychometric properties. Conclusion: At the time of the review, none of the instruments had comprehensively completed the instrument development process to the point of standardisation with evaluated psychometric properties. Further research is recommended for the development of a gold standard in-hand manipulation assessment instrument. [ABSTRACT FROM AUTHOR]

The development of algorithms capable of automatically generating optimal grasp involves first of all the necessity to define the notion of optimal grasp in relation to the target task. To address this problem, the scientific community offers many quality criteria in the literature and continues to propose new ones for grasp synthesis purpose. This paper aims at proposing a synthesis and a fine analysis of the quality criteria useful to evaluate a grasp in a context of adaptive grasping, as well as in the perspective of in-hand manipulation. These criteria are divided in two categories, the first one has 11 criteria and focuses exclusively on the location of contact points while the second one has 5 criteria and takes into account the kinematics of the robotic hand as well. Evaluation of the criteria is proposed with a common evaluation framework based on reference objects and reference manipulation tasks. The evaluation and illustration of the resulting grasps with the different criteria allow to appreciate the physical meaning of each of these criteria with this common evaluation framework. In order to reduce the number of criteria to be used in the context of a grasping synthesis process, a correlation study is carried out. The results show that several criteria in the literature are strongly correlated. Four criteria are finally chosen. Thus, to demonstrate the relevance of the selected criteria, a grasp synthesis process is used for in-hand manipulation purpose. An evolutionary approach is used to solve this multi-criteria optimization problem. The approach is validated in the OpenRAVE simulation environment and then demonstrated with the new RoBioSS hand: a fully actuated dexterous robotic hand with four fingers and sixteen degrees of freedom. Experimental results illustrate the relevance of the choice of these criteria to produce robust grasps leading to stable in-hand manipulations with large amplitudes. [ABSTRACT FROM AUTHOR]

We introduce a reconfigurable underactuated robot hand able to perform systematic prehensile in-hand manipulations regardless of object size or shape. The hand utilizes a two-degree-of-freedom five-bar linkage as the palm of the gripper, with three three-phalanx underactuated fingers, jointly controlled by a single actuator, connected to the mobile revolute joints of the palm. Three actuators are used in the robot hand system in total, one for controlling the force exerted on objects by the fingers through an underactuated tendon system, and two for changing the configuration of the palm and, thus, the positioning of the fingers. This novel layout allows decoupling grasping and manipulation, facilitating the planning and execution of in-hand manipulation operations. The reconfigurable palm provides the hand with a large grasping versatility, and allows easy computation of a map between task space and joint space for manipulation based on distance-based linkage kinematics. The motion of objects of different sizes and shapes from one pose to another is then straightforward and systematic, provided the objects are kept grasped. This is guaranteed independently and passively by the underactuated fingers using a custom tendon routing method, which allows no tendon length variation when the relative finger base positions change with palm reconfigurations. We analyze the theoretical grasping workspace and grasping and manipulation capability of the hand, present algorithms for computing the manipulation map and in-hand manipulation planning, and evaluate all these experimentally. Numerical and empirical results of several manipulation trajectories with objects of different size and shape clearly demonstrate the viability of the proposed concept. [ABSTRACT FROM AUTHOR]

Deep Reinforcement Learning techniques demonstrate advances in the domain of robotics. One of the limiting factors is a large number of interaction samples usually required for training in simulated and real-world environments. In this work, we demonstrate for a set of simulated dexterous in-hand object manipulation tasks that tactile information can substantially increase sample efficiency for training (by up to more than threefold). We also observe an improvement in performance (up to 46%) after adding tactile information. To examine the role of tactile-sensor parameters in these improvements, we included experiments with varied sensor-measurement accuracy (ground truth continuous values, noisy continuous values, Boolean values), and varied spatial resolution of the tactile sensors (927 sensors, 92 sensors, and 16 pooled sensor areas in the hand). To facilitate further studies and comparisons, we make these touch-sensor extensions available as a part of the OpenAI Gym Shadow-Dexterous-Hand robotics environments.

Introduction: Assessment of in-hand manipulation is fundamental to guide treatment for children with fine motor delays. Limited literature is available on how South African occupational therapists assess in-hand manipulation. This study aimed to describe which current in-hand manipulation assessment methods are used and what the preferences of occupational therapists in all areas of paediatric practices are regarding a suitable instrument. Methods: Quantitative cross-sectional study design with a non-probability, purposive sampling method was used. Participants completed an EvaSys survey system online questionnaire. Results: Two-hundred-and-ninety-two (n=292) occupational therapists registered with the HPCSA participated. Limited familiarity (n=50; 17.1%) with the formal assessment instruments described in literature was reported. The informal assessment methods most commonly used were subjective observation of tasks (n=287; 98.3%) of scholastic tasks (n=261; 89.4%) and play tasks (n=255; 87.3%) for children between the ages of five to six years (n=273; 93.5%). Preferences supported a descriptive instrument accompanied by a user manual that is administered under 15 minutes, in multiple languages, and with attention to the quality of movements and compensatory techniques used by the child. Conclusion: Results showed that the current and preferred assessment methods used by occupational therapists might provide guidance for the future development of a contextual, relevant in-hand manipulation instrument for paediatric practices in South Africa. [ABSTRACT FROM AUTHOR]

Performing a successful robotic grasping to uncertain objects in unstructured environments is challenging. This study presents a new compliant soft robotic gripper for objects handling and cap manipulation through the coordination of three soft fingers and in-hand manipulation. The experiments are conducted to validate that the soft robotic gripper can successfully realize simultaneous grasping and capping manipulations with only one flexible shaft actuation for every single soft finger. Note to Practitioners—Uncertain object manipulation tasks pose significant challenges to a robotic gripper while grasping and capping unknown objects without damaging them. The existing rigid grippers have experienced flexible manipulation through multiple degrees of freedom (DoFs) by complex mechanical structures, and the soft gripper can realize stiffness-compliant manipulation differently. The proposed novel robotic in-hand manipulation can execute grasping and cap manipulation by a single flexible shaft to simultaneously achieve bending and rotational movements. The relationship between stretching force and finger’s curvature can enable a custom design for user-specific applications. [ABSTRACT FROM AUTHOR]

This paper proposes an underactuated grippers mechanism that grasps and pulls in different types of objects. These two movements are generated by only a single actuator while two independent actuators are used in conventional grippers. To demonstrate this principle, we have developed two kinds of gripper by different driving systems: one is driven by a DC motor with planetary gear reducers and another is driven by pneumatic actuators with branch tubes as a differential. Each pulling-in mechanism in the former one and the latter one is achieved by a belt-driven finger surface and a linear slider with an air cylinder, respectively. The motor-driven gripper with planetary gear reducers can pull-up the object after grasping. However, the object tends to fall when placing because it opens the finger before pushing out the object during the reversed movement. In addition, the closing speed and the picking-up speed of the fingers are slow due to the high reduction gear. To solve these drawbacks, a new pneumatic gripper by combining three valves, a speed control valve, a relief valve, and non-return valves, is proposed. The proposed pneumatic gripper is superior in the sense that it can perform pulling-up after grasping the object and opening the fingers after pushing-out the object. In the present paper, a design methodology of the different underactuated grippers that can not only grasp but also pull up objects is discussed. Then, to examine the performance of the grippers, experiments were conducted using various objects with different rigidity, shapes, size, and mass, which may be potentially available in real applications.

In-hand manipulation and grasp adjustment with dexterous robotic hands is a complex problem that not only requires highly coordinated finger movements but also deals with interaction variability. The control problem becomes even more complex when introducing tactile information into the feedback loop. Traditional approaches do not consider tactile feedback and attempt to solve the problem either by relying on complex models that are not always readily available or by constraining the problem in order to make it more tractable. In this paper, we propose a hierarchical control approach where a higher level policy is learned through reinforcement learning, while low level controllers ensure grip stability throughout the manipulation action. The low level controllers are independent grip stabilization controllers based on tactile feedback. The independent controllers allow reinforcement learning approaches to explore the manipulation tasks state-action space in a more structured manner. We show that this structure allows learning the unconstrained task with RL methods that cannot learn it in a non-hierarchical setting. The low level controllers also provide an abstraction to the tactile sensors input, allowing transfer to real robot platforms. We show preliminary results of the transfer of policies trained in simulation to the real robot hand.

This paper presents an autonomous robotic assembly system for Soma cube blocks, which, after observing the individual blocks and their assembled shape, quickly plans and executes the assembly motion sequence that picks up each block and incrementally build the target shape. A multi stage planner is used to find the suitable assembly solutions, assembly sequences and grip sequences considering various constraints, and re-grasping is used when the block target pose is not directly realizable or the block pose is ambiguous. The suggested system is implemented for a commercial UR5e robotic arm and a novel two degrees of freedom (DOF) gripper capable of in-hand manipulation, which further speeds up the manipulation speed. It was experimentally validated through a public competitive demonstration, where the suggested system completed all assembly tasks reliably with outstanding performance. [ABSTRACT FROM AUTHOR]

Tactile sensing is a key sensor modality for robots interacting with their surroundings. These sensors provide a rich and diverse set of data signals that contain detailed information collected from contacts between the robot and its environment. The data are however not limited to individual contacts and can be used to extract a wide range of information about the objects in the environment as well as the actions of the robot during the interactions. In this article, we provide an overview of tactile information and its applications in robotics. We present a hierarchy consisting of raw, contact, object, and action levels to structure the tactile information, with higher-level information often building upon lower-level information. We discuss different types of information that can be extracted at each level of the hierarchy. The article also includes an overview of different types of robot applications and the types of tactile information that they employ. Finally we end the article with a discussion for future tactile applications which are still beyond the current capabilities of robots. [ABSTRACT FROM AUTHOR]

Introduction: Screen‐time has become a regular occupation for young children at home and school, with little evidence of its impact on children's developmental skills. This study explored the association between children's screen‐time, fine motor, in‐hand manipulation (IHM), visual‐motor integration (VMI), sensory processing (SP) and parent‐reported play skills. Method: The fine motor, IHM, VMI, SP and play skills of a sample of 25 Australian children without disabilities (M age = 6.2 years, SD = 1.03; 64% girls) were assessed using the Bruininks–Oseretsky Test of Motor Proficiency—Second Edition, Test of In‐Hand Manipulation—Revised, Berry Buktenica Developmental Test of Visual‐Motor Integration Sixth Edition, Sensory Processing Measure—Home Form and Pretend Play Enjoyment Developmental Checklist (PPEDC). Parents completed a week‐long log of their child's screen‐time. Spearman's rho correlations and linear regressions with bootstrapping were used for data analysis. Results: Statistically significant moderate level negative correlations were found between Total Screen‐Time (TST) and VMI skills (r = −.67, p <.01); Interactive Screen‐Time and IHM abilities (r = −.46, p <.05) and TST and bilateral coordination skills (r = −.42, p <.05). There were significant negative correlations between SP ability and both TST (r = −.53, p <.01) and Watching Screen‐Time (r = −.66, p <.01). When the PPEDC Object Substitution variable was entered into a regression model as a co‐variate of hand function, it appeared to lessen the impact of TST as an independent predictor variable of children's VMI and bilateral coordination skills (p <.23 and p <.61). Conclusion: Playing with toys and using object substitution in play (e.g. a child uses an object for something else other than its intended use when playing with it) potentially appear to be a moderating factor of the impact of children's screen‐time on their bilateral coordination and VMI skills. Clinicians can encourage children's active and dynamic involvement in games and play pursuits to counteract the potential impact of increased use of devices that involve screen‐time. [ABSTRACT FROM AUTHOR]

This paper discusses the design and implementation of a high-speed electromechanical robotic gripper for grasping and manipulation of objects. The novelty of the developed robot end-effector lies in the ability to perform rapid and precision in-hand manipulation of various parts. Unlike existing solutions, the end-effector is capable to grasp, reorient and release objects, enabling high productivity in sophisticated industrial feeding and packaging operations. The motivation for the gripper design is inspired by the industrial needs of handling products with complex geometric characteristics, while a use case originating from the consumer goods industry was used for assessing the gripper's performance in an industrial relevant environment. © 2020 The Authors, Published by Elsevier B.V. Peer review under the responsibility of the scientific committee of CIRP [ABSTRACT FROM AUTHOR]

In this article, we present the mechanics and algorithms to compute the set of feasible motions of an object pushed in a plane. This set is known as the motion cone and was previously described for non-prehensile manipulation tasks in the horizontal plane. We generalize its construction to a broader set of planar tasks, such as those where external forces including gravity influence the dynamics of pushing, or prehensile tasks, where there are complex frictional interactions between the gripper, object, and pusher. We show that the motion cone is defined by a set of low-curvature surfaces and approximate it by a polyhedral cone. We verify its validity with thousands of pushing experiments recorded with a motion tracking system. Motion cones abstract the algebra involved in the dynamics of frictional pushing and can be used for simulation, planning, and control. In this article, we demonstrate their use for the dynamic propagation step in a sampling-based planning algorithm. By constraining the planner to explore only through the interior of motion cones, we obtain manipulation strategies that are robust against bounded uncertainties in the frictional parameters of the system. Our planner generates in-hand manipulation trajectories that involve sequences of continuous pushes, from different sides of the object when necessary, with 5–1,000 times speed improvements to equivalent algorithms. [ABSTRACT FROM AUTHOR]

In past research, in-hand object manipulation for various sized and shaped objects has been achieved. However, the network had to be trained for each different motion. Training data takes time to acquire and increases the hardware load, thereby increasing the cost for training data. Four-fingered in-hand manipulation is especially difficult as a high number of joints need to be controlled in synchrony. This paper presents a method that reduces the required training data for in-hand manipulation with the idea of pretraining and mutual finger motions. The Allegro Hand is used with soft fingertips and integrated 6-axis F/T sensors to evaluate the proposed method. To make the network more versatile, the training data included objects of various sizes and shapes. When pretraining the network, one shot learning suffices to learn a new task; mutual finger motions can be exploited to use three-fingered pretraining data for four-fingered manipulation. Both data-sharing and weight-sharing were used and show similar results. Crucially, pretraining data from fingers with the same kinematic chain has to be used, showing the importance of morphology specific learning. Moreover, objects with untrained sizes and shapes could be manipulated. [ABSTRACT FROM AUTHOR]

• A novel 3- P RS-finger-based parallel dexterous hand (PDH) is proposed. • The PDH can perform 6-DOF in-hand manipulation with bidirectional pinching. • The PDH have the possibility to achieve a good force transmission capability. • The PDH can complete the accurate control of in-hand manipulation. Considering the defects of the traditional dexterous hand in precise in-hand manipulation and bidirectional pinching capability, this paper proposes a 3- P RS-finger-based parallel dexterous hand (PDH). The PDH structure is composed of three 3- P RS parallel fingers. First, a pinching shape analysis is conducted to demonstrate the PDH's bidirectional pinching capability. Then, by analyzing the workspace of the PDH pinching nine objects, the influence on the in-hand manipulation workspace of different objects is determined. The PDH can perform symmetrical in-hand manipulation to address the issue that almost all humanoid dexterous hands pinch objects in a single direction. The force transmission capability of the PDH is compared with that of the 3R serial dexterous hand (SDH) under the same trajectory. The results indicate that the PDH have the possibility to possess a good pinching force performance through the specific trajectory planning. Bidirectional pinching experiments are conducted, and the experimental results demonstrate that the PDH can realize the accurate in-hand manipulation under almost frictionless conditions. The proposed PDH provides a feasible design for the theoretical development and practical application of dexterous hands. [ABSTRACT FROM AUTHOR]

This paper presents an autonomous robotic assembly system for Soma cube blocks, which, after observing the individual blocks and their assembled shape, quickly plans and executes the assembly motion sequence that picks up each block and incrementally build the target shape. A multi stage planner is used to find the suitable assembly solutions, assembly sequences and grip sequences considering various constraints, and re-grasping is used when the block target pose is not directly realizable or the block pose is ambiguous. The suggested system is implemented for a commercial UR5e robotic arm and a novel two degrees of freedom (DOF) gripper capable of in-hand manipulation, which further speeds up the manipulation speed. It was experimentally validated through a public competitive demonstration, where the suggested system completed all assembly tasks reliably with outstanding performance.

Grip force control during robotic in-hand manipulation is usually modeled as a monolithic task, where complex controllers consider the placement of all fingers and the contact states between each finger and the gripped object in order to compute the necessary forces to be applied by each finger. Such approaches normally rely on object and contact models and do not generalize well to novel manipulation tasks. Here, we propose a modular grip stabilization method based on a proposition that explains how humans achieve grasp stability. In this biomimetic approach, independent tactile grip stabilization controllers ensure that slip does not occur locally at the engaged robot fingers. Local slip is predicted from the tactile signals of each fingertip sensor i.e., BioTac and BioTac SP by Syntouch. We show that stable grasps emerge without any form of central communication when such independent controllers are engaged in the control of multi-digit robotic hands. The resulting grasps are resistant to external perturbations while ensuring stable grips on a wide variety of objects.

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]

This paper discusses the design and implementation of a robotic gripper that uses compressed air to (a) orient the parts in the desired grasping position, (b) guide the parts inside a grasping mechanism and (c) feed the parts to a track conveyor with sufficient accuracy. The novelty of the approach lays in the ability to perform in-hand manipulation of the object by the gripper allowing to pick randomly placed objects that have a complex geometry. Unlike existing ‘pick and place’ operations which are mainly focused on flat objects that require minimal manipulation (rotation around vertical axis), the gripper can re-orient the parts itself, minimizing the robot’s motion. The major components of the gripper are 3D printed, allowing fast customization for different products. The manipulation and gripping mechanisms have been inspired by an application in the consumer goods industry involving the feeding of shaver handles to an assembly machine. The findings indicate that the proposed solution can be an alternative to part-dedicated, high-cost feeding equipment that is currently used. [ABSTRACT FROM AUTHOR]

Speed and flexibility are the primary concerns to whom a well designed industrial gripper should target. The first one leads to unquestionable pros in terms of production, while the second one to the ability of grasping and manipulating several payloads. However, these qualities are opposed to each other in terms of design requirements: speed requires a structure built of rigid bodies, flexibility would have to be favoured by the use of soft materials. As a common target, the human hand represents the most interesting inspiration source in this field, due to its natural dexterity and ability to perform in-hand manipulations. Thus, many bio-inspired or bio-mimicked grippers have been developed in the last decades with the final aim of replicating the terrific capabilities offered by the human hand. In such panorama, this paper presents the kinematic synthesis of a novel, modular, reconfigurable gripper, which is capable to manipulate a plurality of objects, being dexterous at the same time. Instead of using soft materials to achieve in-hand manipulation, the authors focused to use mechanisms to address the problem. The concept of manipulation is firstly evaluated in a multibody software environment, then a physical prototype was developed, and the necessary control laws were derived. Several experiments were conducted to test the effectiveness of the proposed structure. Results in terms of accuracy and repeatability are shown, and also the ability to address the three major tasks of grasp, in-hand manipulation and release with appropriate posture have been demonstrated. [ABSTRACT FROM AUTHOR]

Background/aim: A review of the literature related to in‐hand manipulation (IHM) revealed that there is no assessment which specifically measures this construct in the adult population. This study reports the face and content validity of an IHM assessment for adults with impaired hand function based on expert opinion. Methods: The definition of IHM skills, assessment tasks and scoring methods identified from literature was discussed in a focus group (n = 4) to establish face validity. An expert panel (n = 16) reviewed the content validity of the proposed assessment; evaluating the representativeness and relevance of encompassing the IHM skills in the proposed assessment tasks, the clarity and importance to daily life of the task and the clarity and applicability to clinical environment of the scoring method. The content validity was calculated using the content validity index for both the individual task and all tasks together (I‐CVI and S‐CVI). Feedback was incorporated to create the assessment. Results: The focus group members agreed to include 10 assessment tasks that covered all IHM skills. In the expert panel review, all tasks received an I‐CVI above 0.78 and S‐CVI above 0.80 in representativeness and relevance ratings, representing good content validity. With the comments from the expert panel, tasks were modified to improve the clarity and importance to daily life. A four‐point Likert scale was identified for assessing both the completion of the assessment tasks and the quality of IHM skills within the task performance. Conclusion: Face and content validity were established in this new IHM assessment. Further studies to examine psychometric properties and use within clinical practice are recommended. [ABSTRACT FROM AUTHOR]