An overview of 3D object grasp synthesis algorithms

In this paper, a modular underactuated multi-fingered robot hand is proposed. The robot hand can be freely configured with different number and configuration of modular fingers according to the work needs. Driving motion is achieved by the rigid structure of the screw and the connecting rod. A finger-connecting mechanism is designed on the palm of the robot hand to meet the needs of modular finger’s installation, drive, rotation, and sensor connections. The fingertips are made of hollow rubber to enhance the stability of grasping. Details about the design of the robot hand and analysis of the robot kinematics and grasping process are described. Last, a prototype is developed, and a grab test is carried out. Experimental results demonstrate that the structure of proposed modular robot hand is reasonable, which enables the adaptability and flexibility of the modular robot hand to meet the requirements of various grasping modes in practice.

The design of multi-fingered robotic hands can follow a kinematic synthesis approach, in which a trajectory or set of points and higher derivatives are defined for each fingertip. The output of the dimensional synthesis is a set of joint axes, effectively defining the basic kinematic structure of the hand. In the case of spatial motion, there seems to be a big gap between the results of the dimensional synthesis and a real and effective detailed design of the robotic hand, this being one of the reasons why synthesis is not regularly used in the design of robotic hands. This work aims to reduce the gap from kinematic synthesis to detailed, computer-aided design of robotic hands. In order to do so, the output of the dimensional synthesis is first used as the input of a link-based optimization process, aim to bring to reasonable values requirements such as link lengths, internal friction forces and obstacle avoidance, including self-intersection. The optimized results are automatically imported to a popular solid modeling software, creating reference geometry for parts, and joint axes and anchor points for the final hand assembly. At the same time, a database of hand parts is presented to the user to select and adapt in order to create a first realistic assembly of the robotic hand. The output of the process is a first detailed design of the robotic hand, which can be a good starting point for the designer to implement transmission and actuation in further stages.

A four-fingered metamorphic robotic hand with a reconfigurable palm is presented in this paper with the application in deboning operation of meat industry. This robotic hand has a reconfigurable palm that generates changeable topology and augments dexterity and versatility for the hand. Mechanical structure and design of the robotic hand are presented and based on mechanism decomposition, kinematics of the metamorphic hand is investigated with closed-form solutions leading to the workspace characterization of the robotic hand. Based on the kinematics of the four-fingered metamorphic hand, utilizing product-of-exponentials formula, grasp map and grasp constraint of the hand are then formulated revealing the grasp robustness and manipulability performed by the metamorphic hand. A prototype of the four-fingered metamorphic hand is consequently fabricated and integrated with low level control and sensor systems leading to a scenario of applying the hand in the field of meat industry for deboning operation.

The application of dexterous robotic hands out of research laboratories has been limited by the intrinsic complexity that these devices present. This is directly reflected as an economically unreasonable cost and a low overall reliability. Within the research reported in this thesis it is shown how the problem of complexity in the design of robotic hands can be tackled, taking advantage of modern technologies (i.e. rapid prototyping), leading to innovative concepts for the design of the mechanical structure, the actuation and sensory systems. The solutions adopted drastically reduce the prototyping and production costs and increase the reliability, reducing the number of parts required and averaging their single reliability factors. In order to get guidelines for the design process, the problem of robotic grasp and manipulation by a dual arm/hand system has been reviewed. In this way, the requirements that should be fulfilled at hardware level to guarantee successful execution of the task has been highlighted. The contribution of this research from the manipulation planning side focuses on the redundancy resolution that arise in the execution of the task in a dexterous arm/hand system. In literature the problem of coordination of arm and hand during manipulation of an object has been widely analyzed in theory but often experimentally demonstrated in simplified robotic setup. Our aim is to cover the lack in the study of this topic and experimentally evaluate it in a complex system as a anthropomorphic arm hand system.

The significant progress in robotics worldwide, brings further advancements in the design of the mechanical components, miniaturization of sensors and control hardware and more sophisticated control algorithms that come together with more available processing power. The state of the art humanoid robots are usually equipped with dexterous hands. This paper presents the design of the FTN robot hand for humanoid robot MARKO, with the emphasis on the fuzzy logic controller to control the Brushed DC motors used to actuate the underactuated fingers of the hand. The design of the robotic hand is highly anthropomorphic and biologically inspired by the human hands. The hand is passively adaptive to the shape of an object, due to a tendon-driven mechanism and torsional spring in each finger joint. Each of the five fingers has three DOFs (Degrees Of Freedom), except the thumb which has an additional DOF, for the rotation in its base. The fingers are tendon-driven, actuated with five DC motors, embedded in the palm. The proposed fuzzy controller is used to control the position of each finger. The results of the controller are compared with traditional PID control algorithms tuned with Ziegler – Nichols tuning method. The algorithms are first developed in a simulation environment and later are implemented on a real-time ARM Cortex M4 controller.

To match the richness and complexity of the sensory and motor functionalities of a human hand with a robust and economically reasonable robotic device remains one of the hardest challenges in the field. Previous work has explored the possibility to exploit insight from neuroscientific results on postural correlation patterns (synergies) taming the sensorimotor complexity of hands. The postural synergy model has been recently extended to account for grasp force control through a model of “soft synergies” which incorporate hand compliance. In this paper we propose a first translation of such principles in the design of a robot hand. It so turns out that the implementation of the soft synergy model in an effective design is not obvious. The solution proposed in this paper rests on ideas coming from under-actuated hand design. We give a synthesis method to realize a desired set of soft synergies through the principled design of adaptive under-actuated mechanisms, which we call the method of adaptive synergies. This approach leads to the design and implementation of a prototype modular hand capable of accommodating an arbitrary number of synergies. The effectiveness of the design is shown in grasping simulations and experiments.

In this paper development, implementation and experimental validation of a grasp synthesis algorithm for an anthropomorphic robotic arm-hand system in a low dimensional posture subspace is proposed. The algorithm has been developed on the basis of the analysis of human hand postural synergies. Drawing inspiration from neuroscientific studies, a database of grasps has been created through the observation and the analysis of the human finger posture during reaching and grasping tasks of several objects. The optimal hand configuration and wrist pose have been determined by applying an optimization procedure grounded on a stochastic method. The grasp synthesis algorithm has been validated in simulation and on a real arm-hand robotic platform consisting of the KUKA LWR 4+ robot arm and the DLR-HIT Hand II. The experimental results have validated the hypothesis made during algorithm implementation and have shown that the armhand robotic platform is able to perform the hand preshaping configurations predicted by the grasp synthesis algorithm.

ABSTRACTTo bridge the gap between users' expectations and technological solutions, a better understanding of human body experience and sensory-motor skills is mandatory. This could pave the way towards a novel generation of robotic hands, which can be successfully employed in everyday life e.g. in prosthetics and assistive robotics. Available robotic hands are still far from matching the requirements of the corresponding experimental and real-world applications, e.g. fast motions might be achieved at the expense of accuracy. Knowledge of the users' sensory-motor skills can guide technical developments, e.g. prosthetic design processes. This paper presents design solutions developed in a Delphi study. Explorative questionnaires are prepared to acquire and elaborate expert opinions to improve the design of previously developed robotic anthropomorphic hands. By gathering and fusing expert opinions, novel robotic hand and wrist concepts specifically optimized regarding body experience and sensory-motor skill research are developed. In three rounds, experts with experience in robotic hand design and/or control analyze, develop, and rank solutions for mechanisms, actuators, and control , which result in overall design concepts. The technical concepts and implications resulting from the study are discussed considering psychological and biomechanical aspects.

Robotics technology, especially in the robotic hand development, is very important to perform various tasks that are considered too risky or fatal to be performed by a human being. This technology is also important to assist human being physiological rehabilitation. There are numerous designs of robotic hand, but the five-fingered robotic hand design is the most dexterous robotic hand design due to its similar appearance with a human hand. In general, the fingers' motions are driven or actuated by geared motors or other types of emerging technologies and controlled by microcontrollers or computers that received instructions from sensors or user inputs. However, the motions are yet to be driven or actuated by solenoids and controlled by using pressure sensor comparator method due to the solenoid technology limited applications and the controller novelty approach. Nevertheless, solenoids are known for their fast reaction time and strong holding force that are useful to perform high speed motions and strong grasping actions. The controller novelty approach is also expected to provide good motions' accuracy and response. Therefore, the synergy of this idea can introduce a new master-slave robotic hand design called SPCT (Solenoid-Pressure-Comparator-Technology) Robotic Hand. For this particular paper, the focus will be on the slave component design and solenoid actuation system. It can be seen that the design has potential for further developments.

In this paper we present a novel method of designing multi-fingered robotic hands using tasks composed of both finite and infinitesimal motion. The method is based on representing the robotic hands as a kinematic chain with a tree topology. We represent finite motion using Clifford algebra and infinitesimal motion using Lie algebra to perform finite dimensional kinematic synthesis of the multi-fingered mechanism. This allows tasks to be defined not only by displacements, but also by the velocity and acceleration at different positions for the design of robotic hands. The additional information enables an increased local approximation of the task at critical positions, as well as contact and curvature specifications. An example task is provided using an experimental motion capture system and we present the design of a robotic hand for the task using a hybrid Genetic Algorithm/Levenberg-Marquadt solver.

This paper establishes an architecture for design of prosthetic and robotic hands. By exploiting the information obtained from CyberGlove <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">®</sup> and surface EMG data for muscle activity, we propose a new method for design of prosthetic and robotic hands.

Multi-finger Robotic hands (MFRH) are desired similar to human hands in order to perform stable grasping and fine manipulation of different objects. Their industrial applications including material handling fulfills the requirement of unique end-effector tool empowering specific reach, payloads, and flexibility. The design and control of dexterous and prosthetic robotic hands is of important concern these days. The performance of these hands depends on their mechanical design, prosthetics etc. The mechanical range of movement must be properly controlled and monitored to get the best performance of the robotic hand. In order to obtain the desired outcome from these robotic hands, various design parameters are discussed. The control issues of the multi-finger hand-arm system in order to interact with the human environment are also discussed. The objective of this paper is to evaluate multi-finger robotic hands capable of grasping a large variety of products. An overview of the relations between the designing features for the robotic hand, its anthropomorphism and dexterity is reported. Also, the best known robotic hands developed so far are reviewed emphasizing on their ergonomics and mechanical features. Based on these parameters, a newly designed four fingered tendon actuated robotic hand is discussed along with its mechanical structure.

There are numerous robotic hand designs but the five-fingered robotic hand design is the most dexterous robotic hand design due to its similar appearance and motions with the human hands. The five-fingered robotic hands are commonly controlled or governed through a master-slave system that can be accomplished by using simple preset motions or other complicated and advanced technologies. However, a five-fingered robotics hand can also be controlled by a novel approach known as pressure sensors comparator technique. This technique compares the values from the pressure sensors that are strategically located at the glove (master) and robotic hand (slave). If the values differ, the actuators will generate motions accordingly. The initial finding based on the master and slave prototypes showed that applying this technique is very challenging due to the humans' physiological diversity. Nevertheless, a solution was proposed for further studies and future developments by introducing an offset.

After introductory considerations on the main functional and design differences between anthropomorphic hands conceived as robotic end effectors or as prostheses, this chapter presents two topics related to advances in robotic hand design that seem transferable to prosthetic hands, in order to increase their functional capability yet coping with specific constraints like simplicity, lightweight, cost effectiveness, robustness, etc. The development of a bio-inspired robotic hand, called UB Hand IV, based on an endoskeletal articulated structure, actuated by tendons and covered by a soft dermal-epidermal layer is briefly illustrated, in order to show the potential of its design solutions to be transferred into prosthetic hands. The first part of the chapter presents alternative design approaches for articulated joints and finger structures based on purposely designed compliant hinges. The basic problem of compliant hinges adoption in robotic structures, that is the limitation of secondary compliance effects, is analyzed and considerations about comparative metrics are proposed. Two hinge morphologies which show promising features are critically compared and pros and cons the production of fully integral fingers with compliant joints are discussed. The second part reports on the development of thin soft covers for robotic (and prosthetic) hands capable of strictly mimicking the actual compliance of human finger pulps. A design method, called by the authors Differentiated Layer Design (DLD), is reviewed and its potential for application on both robotic and prosthetic devices is underlined. Conclusions summarize the main aspects that encourage the transfer of the described results from the world of robots to that of human portable devices.

The design and implementation of a suitable robotic hand for a toddler-sized humanoid robot is a challenging task. The main purpose of this work is to optimize the design of an anthropomorphic robotic hand and control it by using surface electromyographic (sEMG) signals. Isolation forest backward particle swarm optimization is used to optimize the robotic hand. The fitness function is defined by thumb opposability and the ability to grasp objects based on grasp taxonomy. Learning without forgetting (LWF) is adopted to train sEMG signal data sequentially, and the consequently learned model is used as an ensemble to control the optimized robotic hand. Webots is adopted to simulate the scenario of grasping objects to optimize the design of the hand. The optimized robotic hand is compared with two robotic hands, and the highest fitness values in the simulator and real world are obtained. Three different sEMG inputs, namely, raw data, bandpass, and discrete wavelet transformed bandpass, are compared in LWF, and the structure of neural networks is considered. The final LWF model is successfully applied to a real-world system to manipulate a robotic hand via hand gesture classification in real time.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-30658-2.