A Fast Grasp Planning Algorithm for Humanoid Robot Hands

SUMMARYIn the human body there are many joints whose functions are very similar to revolute joints. To avoid the complexity of these joints, they are usually substituted by revolute joints in many humanoid robots. Revolute joints have purely rotational motion along their fixed axis, while real joints in the human body have Instantaneous Rotational Axis (IRA) due to their configuration. Substitution of this kind of human joints with revolute (hinge) joints in robots changes the kinematics of joints. Knowing the exact characteristics of the moving axis of rotation in human joints is a prerequisite for the kinematic study of a joint. Here the main geometrical difference between these kinds of joints in humans and their simplified (hinge-like) models in robots is described. Then, as a case study, the mechanism of the three joints of the index finger are compared with their hinge-like model using a multi-body code to understand when revolute joints can be substituted for anthropometric joints in hand exoskeletons and robotic hands. Furthermore, the position of IRA and its distance from the center of the condyle of the joint are presented. The concept and the results can be extended for other fingers and all similar joints, and can be used in humanoid robots, hand exoskeletons and robotic hands.

Utilizing robotic hands for manipulating objects and assembly requires one to deal with problems like immobility, grasp planning, and regrasp planning. This chapter integrates some essential subjects on robotic grasping: the first section presents a concise taxonomy of robotic grippers and hands. Then the basic concepts of grasping are provided, including immobility, form-closure, and force-closure, 2D and 3D grasping, and Coulomb friction. Next, the principles of grasp planning, measures of grasping quality, pre-grasp, stable grasps, and regrasp planning are presented. The chapter presents comparisons for robotic grippers, a new classification of measures of grasp quality, and a new categorization of regrasp planning approaches.

Many people are expecting for robots to support home work. However, in order to actually do such work, it is necessary for the robot to acquire the complex functions of human hands. Therefore, we developed a humanoid type hand that can be used for humanoid robot and prosthetic hand, and verified various actions of daily life to prove its function. As a result, this robot hand could grab eggs and vegetables, pour water into the cup, grasp the plastic wrap and cover the dishes.

This paper presents a new approach to the computation of stable grasps of polygonal objects. The authors consider the case of a hand equipped with three hard fingers and assume point contact with friction. They prove a sufficient condition for force-closure grasps that leads to a system of linear constraints in the position of the fingers along the polygonal edges. All regions satisfying these constraints are found by a new projection algorithm based on linear parameter elimination accelerated by simplex techniques. Maximal object segments where fingers can be positioned independently are found by linear optimization within the grasp regions. The approach has been implemented and examples are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

The purpose of this paper is to quickly and stably achieve grasping objects with a 3D robot arm controlled by electrooculography (EOG) signals. A EOG signal is a biological signal generated when the eyeballs move, leading to gaze estimation. In conventional research, gaze estimation has been used to control a 3D robot arm for welfare purposes. However, it is known that the EOG signal loses some of the eye movement information when it travels through the skin, resulting in errors in EOG gaze estimation. Thus, EOG gaze estimation is difficult to point out the object accurately, and the object may not be appropriately grasped. Therefore, developing a methodology to compensate, for the lost information and increase spatial accuracy is important. This paper aims to realize highly accurate object grasping with a robot arm by combining EMG gaze estimation and the object recognition of camera image processing. The system consists of a robot arm, top and side cameras, a display showing the camera images, and an EOG measurement analyzer. The user manipulates the robot arm through the camera images, which can be switched, and the EOG gaze estimation can specify the object. In the beginning, the user gazes at the screen’s center position and then moves their eyes to gaze at the object to be grasped. After that, the proposed system recognizes the object in the camera image via image processing and grasps it using the object centroid. The object selection is based on the object centroid closest to the estimated gaze position within a certain distance (threshold), thus enabling highly accurate object grasping. The observed size of the object on the screen can differ depending on the camera installation and the screen display state. Therefore, it is crucial to set the distance threshold from the object centroid for object selection. The first experiment is conducted to clarify the distance error of the EOG gaze estimation in the proposed system configuration. As a result, it is confirmed that the range of the distance error is 1.8–3.0 cm. The second experiment is conducted to evaluate the performance of the object grasping by setting two thresholds from the first experimental results: the medium distance error value of 2 cm and the maximum distance error value of 3 cm. As a result, it is found that the grasping speed of the 3 cm threshold is 27% faster than that of the 2 cm threshold due to more stable object selection.

This paper addresses the problem of computing frictional 4-fingered force-closure grasps of three-dimensional objects. The proposed approach searches for force-closure grasps from a collection of sampled points on the object's surface. Unlike most other works, the approach is not limited to the objects with a certain class of shapes. It can be applied to an object in any shape since only the object's surface points and corresponding surface normal at the points are needed. The efficiency of the approach arises from a heuristic for search space pruning which is based on ability to efficiently locate regions in three dimensional space where friction cones intersect and a randomized test for checking force-closure condition. The proposed approach is implemented and preliminary results are presented.

Due to the artificial muscle advantage properties of light weight, low energy consumption and high power to weight ratio, an underactuated humanoid hand was designed with ionic polymer metal composite (IPMC) actuating distal joint unit and shape memory alloy (SMA) actuating unit. The SMA actuating unit could complete compliant enveloping grasping task for daily life goods. The IPMC actuating distal joint unit could complete grasping task for fragile and light weight goods. The SMA actuating unit was fabricated by multi-piece SMA wires in series to increase output displacement and this series part in parallel to increase output force. This SMA actuator possessed both large output displacement and large output force, solving the mutual restrain problem between output displacement and output force of SMA actuator. Finally, the humanoid hand had completed the bottle, the card and other daily life goods grasping task in experiment, which gave a potent demonstration to the grasping effectiveness.

Achieving in-hand manipulation of a grasped object is challenging in robotic communities. This article proposes a planar intrinsic in-hand manipulation approach based on isometric transformation. We demonstrate that the isometric transformation (excluding reflections) can be reduced to rotations with two fixed centers, if more than two rotations around two different centers are performed. Furthermore, this article applies this theory to reposition and reorient a grasped object by performing three or more primitive rotations sequentially. We further analyze the feasible manipulation space, where the desired position and orientation of a grasped object can be attained. The theoretical results have been verified through simulations and experiments. In addition, we performed several real-world tasks using a novel robotic hand with two rotational degrees of freedom at each finger, demonstrating that the proposed in-hand manipulation method can reposition and reorient different grasped objects in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{SE}(2)$</tex-math></inline-formula> .

Camera Holding Robotic Devices in Urology

This paper presents a user study evaluating teleoperated grasping performance and perceived workload of the human operator in a shared autonomy setup when working with different assistance modes and hand kinematics. The hands of a humanoid robot are operated using two approaches: direct mapping of human finger motions (telemanipulation), and “open/close” commands in combination with online grasp planning (shared autonomy). Human finger movements are measured with a data glove in both approaches. Grasp planning for the shared autonomy mode is based on the online calculation of reachable independent contact regions. In this approach, two visual assistance modes were tested: one indicating graspability in a binary manner (possible vs. impossible) and another one showing the potential contact regions for the fingertips. To analyze the influence of the hand kinematics on grasping performance and workload, two hands with different thumb positions are compared. The study shows that shared autonomy significantly decreases the task completion time and increases the grasp robustness compared to the direct mapping approach. The effect is more evident for a hand with optimized kinematics. The results reveal that choosing the appropriate control and assistance mode has a significant influence in telepresence performance.

Dexterous Dynamic Optimal Grasping of a Circular Object subject to Gravity with Soft-fingertips

The human hand is an amazing tool, demonstrated by its incredible motor capability and remarkable sense of touch. To enable robots to work in a human-centric environment, it is desirable to endow robotic hands with human-like capabilities for grasping and object manipulation. However, due to its inherent complexity and inevitable model uncertainty, robotic grasping and manipulation remains a challenge. This thesis focuses on grasp adaptation in the face of model and sensing uncertainties: Given an object whose properties are not known with certainty (e.g., shape, weight and external perturbation), and a multifingered robotic hand, we aim at determining where to put the fingers and how the fingers should adaptively interact with the object using tactile sensing, in order to achieve either a stable grasp or a desired dynamic behaviour. A central idea in this thesis is the object-centric dynamics: namely, that we express all control constraints into an object-centric representation. This simplifies computa- tion and makes the control versatile to the type of hands. This is an essential feature that distinguishes our work from other robust grasping work in the literature, where generating a static stable grasp for a given hand is usually the primary goal. In this thesis, grasp adaptation is a dynamic process that flexibly adapts the grasp to fit some purpose from the objectâ s perspective, in the presence of a variety of uncertainties and/or perturbations. When building a grasp adaptation for a given situation, there are two key problems that must be addressed: 1) the problem of choosing an initial grasp that is suitable for future adaptation, and more importantly 2) the problem of design- ing an adaptation strategy that can react adequately to achieve desired behaviour of the grasped object. To address challenge 1 (planning a grasp under shape uncertainty), we propose an approach to parameterizing the uncertainty in object shape using Gaussian Processes (GPs) and incorporate it as a constraint into contact-level grasp planning. To realize the planned contacts using different hands interchangeably, we further develop a prob- abilistic model to predict the feasible hand configurations, including hand pose and finger joints, given the desired contact points only. The model is built using the con- cept of Virtual Frame(VF), and it is independent from the choice of hand frame and object frame. The performance of the proposed approach is validated on two differ- ent robotic hands, an industrial gripper (4 DOF Barrett hand) and a humanoid hand (16 DOF Allegro hand) to manipulate objects of daily use with complex geometry and various texture (a spray bottle, a tea caddy, a jug and a bunny toy). In the second part of this thesis, we propose an approach to the design of adapta- tion strategy to ensure grasp stability in the presence of physical uncertainties of objects(object weight, friction at contacts and external perturbation). Based on an object-level impedance controller, we first design a grasp stability estimator in the object frame using the grasp experience and tactile sensing. Once a grasp is predicted to be unstable during online execution, the grasp adaptation strategy is triggered to improve the grasp stability, by either changing the stiffness at finger level or relocating the position of one fingertip to a better area.

Assistive robot solutions are mostly designed as robot helpers with robotic arms and aim to assist disabled and elderly people with carrying out basic activities of daily life such as reaching household objects, i.e. cups, feeding with spoon, opening a drawer/fridge doors, etc., However, commercial assistive robotic arms with joystick control require extensive and tiring hand motor skill training that limits robot’s practical usage by patients with disabilities. The main objective of this work is to present the methodology for designing an intelligent human-machine interface for a commercial joystick controlled assistive robotic arm realizing shared autonomy and supervisory control modes. Preliminary results on a RGB-D based object detection and position estimation system development using publicly available YOLOv3 and CenterNet deep learning models implementation of an autonomous object grasping mode by the Kinova Jaco robotic arm are described in detail and experimentally demonstrated.

The human hand is a very complex mechanism which dealing with the external environment with a high range of degree of freedoms to allowing it to do a big variety of movements. Humanoid robotic hands are robotic hands that resemble human hands, especially with respect to their shape and their kinematic abilities. Recently, soft actuators are drawing attention in robotics field due to their high flexibility, lightness, ease of fabrication and its low cost. In this paper, we present a novel soft humanoid pneumatic hand which consists of nine soft bending actuators assembled together in one hand which can be matching the mobility of the human hand as closely as possible and verify this ability by using the hand sign language configurations. Direct 3D printing technique has been presented in the fabrication process of the soft pneumatic hand as a new technique by using a TPU 3D printer filament. Soft actuators characterization such as the bending performance is presented by using the advantage of ABAQUS/CAE software and experimental tests. All control actions were achieved by using Arduino Mega board supported with MATLAB SIMULINK model working with graphical user interface computer application (GUI).

This study presents the development of a novel omnidirectional soft bending sensor tailored for humanoid dexterous hands to facilitate posture perception in delicate manipulation tasks. Drawing inspiration from the human hand's intricate design and proprioceptive capabilities, this study aims to enhance the dexterity of robotic hands, particularly in multi-degree-of-freedom (DoF) motion and posture perception. To this end, we designed a humanoid dexterous hand featuring 18 active DoFs, with five rigid-flexible structured fingers for improved joint mobility. Each finger is equipped with our innovative omnidirectional bending sensor, utilizing segmented polymethylmethacrylate (PMMA) optical fibers, a trichromatic LED, and a chromatic detector to detect the pitch and yaw angles of the metacarpophalangeal joints. The sensor demonstrated excellent measurement performance, stability, and repeatability in challenging tasks such as using scissors, operating a computer mouse, and playing the piano. This technology addresses the challenges associated with multi-DoF motion and omnidirectional posture perception in robotic hands, thereby enhancing their capabilities in delicate manipulation tasks and paving the way for further advancements in humanoid dexterous hand development.