In this paper, we report on the design, modeling, and experimental testing of a piezoelectric-driven microgripper making use of both an integrated gripping force sensor and an integrated tip ...displacement sensor. In the developed microgripper, a stack piezoelectric ceramic actuator is used to simultaneously obtain the tip displacement and the gripping force. A novel monolithic compliant mechanism is proposed to act as the microdisplacement transmission mechanism to obtain the large tip displacement and to provide the possibility of integrating both the gripping force sensor and the tip displacement sensor into the microgripper. The relationship between the gripping force, tip displacement, input force, and input displacement of the piezoelectric-driven microgripper and the dynamic model are established using the pseudorigid-body-model method. The characteristics of the developed microgripper are tested and the case of gripping an optical fiber is presented. The experimental results indicate that: 1) the theoretical model for the developed microgripper matched well with the measured results; 2) the integrated gripping force sensor and tip displacement sensor could accurately measure the gripping force and tip displacement; 3) the developed microgripper could achieve a displacement magnification of 16.0 × with respect to the stack piezoelectric ceramic actuator to realize the large tip displacement with high resolution but is also able to possess the parallel movement of its gripping jaws and the constant displacement magnification.
Grasp detection in cluttered scenes is a very challenging task for robots. Generating synthetic grasping data is a popular way to train and test grasp methods, as is Dex-Net; yet, these methods ...sample training grasps on 3-D synthetic object models, but evaluate at images or point clouds with different sample distributions, which reduces performance due to covariate shift and sparse grasp labels. To solve existing problems, we propose a novel on-policy grasp detection method for parallel grippers, which can train and test on the approximate distribution with dense pixel-level grasp labels generated on RGB-D images. An Orthographic-Depth Grasp Generation (ODG-Generation) method is proposed to generate an orthographic depth image through a new imaging model of projecting points in orthographic; then this method generates multiple candidate grasps for each pixel and obtains robust positive grasps through flatness detection, force-closure metric and collision detection. Then, a comprehensive Pixel-Level Grasp Pose Dataset (PLGP-Dataset) is constructed, which is the first pixel-level grasp dataset, with the on-policy distribution. Lastly, we build a grasp detection network with a novel data augmentation process for imbalance training. Experiments show that our on-policy method can partially overcome the gap between simulation and reality, and achieves the best performance.
Efficiently grasping and releasing objects using robotic grippers is an essential step in robotic assembly. This paper presents a low-cost four-finger adaptive gripper capable of performing stable ...and reliable grasping operations on irregular-shaped flat objects. Unlike other grasping systems in the fixture-to-fixture robotic assembly, the assembly process using the proposed gripper does not rely on any vision systems or six-axis force/torque sensors. Specifically, assuming that the relative position <inline-formula><tex-math notation="LaTeX">\bm {\Lambda }</tex-math></inline-formula> between the two fixtures is known, such assembly tasks can be accomplished simply by performing a predefined motion of a robot arm only related to <inline-formula><tex-math notation="LaTeX">\bm {\Lambda }</tex-math></inline-formula>. This is mainly because the developed gripper not only adapts to the shape and size of the grasped object, but also keeps its position and posture relative to the gripper unchanged throughout the grasping process. A novel underactuated grasping mechanism consisting of an X-shaped differential mechanism and two seesaw ones is proposed to perform adaptive and stable fingertip grasps with more contact points. The kinematics and statics of the gripper-object system are derived for the analysis and design of the gripper. The proposed gripper is fabricated, and a grasping system is built using a commercial robot arm (UR5) to verify its capability for adaptive grasps and assembly of difficult-to-handle flat objects. Experimental results show that it is effective to grasp objects with uncertain shape/size and position, control the grasping force, and accomplish the fixture-to-fixture assembly, etc.
There are precision issues with traditional rigid-body grippers due to their nature in presence of joints’ backlash and friction. This paper presents a macroscale compliant gripper to eliminate these ...issues for the applications in handing delicate/brittle materials such as powder granular or manipulating sub-millimetre objects such as optical fibre and micro-lens. The compliant gripper is obtained from a 2-PRRP (P: prismatic; R: revolute) kinematic mechanism, and uses distributed-compliance joints for avoiding stress-concentration and enabling large range of motion. A very compact design is achieved by using a position space principle. The compliant gripper is modelled, fabricated, followed by comprehensive testing for characterising relationships between the input displacement/force and output displacement and between the input displacement and displacement amplification ratio, and for analysing hysteresis during loading and unloading. The experimental results are compared with finite element analysis (FEA) model and linear analytical model. The testing results have suggested good performance characteristics of this compliant gripper such as a nearly linear relationship between the input and output, a nearly constant amplification ratio for closing the jaw, and negligible hysteresis error.
Purpose
This paper aims to present a soft closed-chain modular gripper for robotic pick-and-place applications. The proposed biomimetic gripper design is inspired by the Fin Ray effect, derived from ...fish fins physiology. It is composed of three axisymmetric fingers, actuated with a single actuator. Each finger has a modular under-actuated closed-chain structure. The finger structure is compliant in contact normal direction, with stiff crossbeams reorienting to help the finger structure conform around objects.
Design/methodology/approach
Starting with the design and development of the proposed gripper, a consequent mathematical representation consisting of closed-chain forward and inverse kinematics is detailed. The proposed mathematical framework is validated through the finite element modeling simulations. Additionally, a set of experiments was conducted to compare the simulated and prototype finger trajectories, as well as to assess qualitative grasping ability.
Findings
Key Findings are the presented mathematical model for closed-loop chain mechanisms, as well as design and optimization guidelines to develop controlled closed-chain grippers.
Research limitations/implications
The proposed methodology and mathematical model could be taken as a fundamental modular base block to explore similar distributed degrees of freedom (DOF) closed-chain manipulators and grippers. The enhanced kinematic model contributes to optimized dynamics and control of soft closed-chain grasping mechanisms.
Practical implications
The approach is aimed to improve the development of soft grippers that are required to grasp complex objects found in human–robot cooperation and collaborative robot (cobot) applications.
Originality/value
The proposed closed-chain mathematical framework is based on distributed DOFs instead of the conventional lumped joint approach. This is to better optimize and understand the kinematics of soft robotic mechanisms.
In this letter, we describe a novel capillary force gripper with two nozzles for the manipulation of complex-shaped micro-objects. These nozzles rapidly form constant-volume droplets and have two ...primary functions: fast water refilling by capillary action and fast droplet formation by the on-off control of a diaphragm pump. Capillary force is a dominant microscopic force acting on objects of all shapes owing to the fluidity of water. Therefore, it is suitable for the capture and release of heterogeneous and complex-shaped micro-objects. In the experiments, we picked and placed 1-mm cubes, triangular prisms, and helical micro springs. The positioning errors ±SD for each shape were 54 ± 36 μm, 85 ± 32 μm, and 162 ± 74 μm, respectively. These prisms and springs are difficult to control using conventional air nozzles, which have a typical positioning accuracy of approximately ± 40 μm for rectangular prismatic objects. In addition, by setting the distance between the nozzles to an appropriate value, we reduced the deviation of the attitude angle around the vertical axis to ±2.6° using self-alignment phenomena for the 1-mm cubes. The proposed method is feasible for manipulating complex-shaped and fragile micro-objects in the micro-electro-mechanical systems field.
Given the heterogeneous nature of cultures, tumors, and tissues, the ability to capture, contain, and analyze single cells is important for genomics, proteomics, diagnostics, therapeutics, and ...surgery. Moreover, for surgical applications in small conduits in the body such as in the cardiovascular system, there is a need for tiny tools that approach the size of the single red blood cells that traverse the blood vessels and capillaries. We describe the fabrication of arrayed or untethered single cell grippers composed of biocompatible and bioresorbable silicon monoxide and silicon dioxide. The energy required to actuate these grippers is derived from the release of residual stress in 3–27 nm thick films, did not require any wires, tethers, or batteries, and resulted in folding angles over 100° with folding radii as small as 765 nm. We developed and applied a finite element model to predict these folding angles. Finally, we demonstrated the capture of live mouse fibroblast cells in an array of grippers and individual red blood cells in untethered grippers which could be released from the substrate to illustrate the potential utility for in vivo operations.
In this paper, a two-way self-adaptive gripper that has adaptability to external disturbance loads during linear opening/closing pinch actions and adaptability to encompass a variety of shapes during ...grasping using a single actuator is proposed, unlike the previous self-adaptive robotic grippers capable of only shape adaptation. Therefore, both linear motion adaptability and shape adaptability during parallel grasping situations are enabled by the proposed design of the gripper. Adaptation to the linear pinch motion is provided through the use of a differential gear, the two outputs of which drive the two tips of the gripper. If facing uneven external loads, the differential gear adaptively alters the speeds of the two outputs, resulting in different closing speeds of the two gripper tips. Despite asymmetric closing, very stable grasping can be guaranteed for such a situation. The differential gear can even complete the grasping by intentionally or unintentionally fixing one of the gripper tips. The proposed design is also capable of shape adaptation in the encompassing grasping mode by adopting a parallel-linkage gripper mechanism, consisting of an exoskeleton and 6 internal joints with a spring element. The finger exoskeleton facilitates pinch and spread actions, while the encompassing action is carried out by adjusting the internal linkage. Based on the kinematic analysis and modeling of the proposed gripper, a prototype of the two-way adaptive gripper hardware was developed. Several experiments were performed to verify the feasibility and validity of the proposed gripper system. The actuator using the proposed differential gear was shown to be able to grasp objects in jammed conditions. In addition, the gripper was able to perform grasping actions, such as pinch, spread, and encompassing grasp.
This paper proposes a combined planning and optimization method that enables a dual-arm robot to lift up and flip heavy plates using crane pulley blocks. The problem is motivated by the low payload ...of modern collaborative robots. Instead of directly manipulating heavy plates that collaborative robots cannot afford, the paper develops a planner for collaborative robots to operate crane pulley blocks. The planner assumes a target plate is pre-attached to the crane hook. It optimizes dual-arm action sequences and plans the robot's dual-arm motion that pulls the rope of the crane pulley blocks to lift up the plate. The crane pulley blocks reduce the payload that each robotic arm needs to bear. When the plate is lifted up to a satisfying pose, the planner plans a sliding-pushing motion for one of the robot arms to tumble over the plate while considering force and moment constraints. The article presents the technical details of the planner and several experiments and analysis carried out using a dual-arm robot made by two Universal Robots UR3 arms. The influence of various parameters and optimization goals are investigated and compared in depth. The results show that the proposed planner is flexible and efficient. This paper is motivated by a cleaning process in a factory that produces sewage press machines. The pressboard of sewage press machines could be as heavy as 1000 kg. Human workers need to flip and clean both sides of the board before installing them to the main axis of a sewage machine. Their solution is using a gantry crane. They attach the board to the crane hook using bearing belts, activate the crane to lift up the board. When the board is raised to a satisfying pose, the workers turn the board over by pushing it. Motivated by human workers' actions, we developed the planner presented in this paper. We assumed crane pulley blocks in the experiments and analysis, but in practice, they may be replaced with electronic ones to improve effort and efficiency. Using the electronic ones will be a sub-problem since there is no need for pulling ropes. The proposed method is expected to help a company's technicians better judge if they need a heavy payload manipulator or keep their current crane equipment while employing several intelligent collaborative robots to operate them. As a result, it may help to accelerate the upgrade of manufacturing sites while reducing reforming budgets. Note to Practitioners-This paper is motivated by a cleaning process in a factory that produces sewage press machines. The pressboard of sewage press machines could be as heavy as 1000 kg. Human workers need to flip and clean both sides of the board before installing them to the main axis of a sewage machine. Their solution is using a gantry crane. They attach the board to the crane hook using bearing belts, activate the crane to lift up the board. When the board is raised to a satisfying pose, the workers turn the board over by pushing it. Motivated by human workers' actions, we developed the planner presented in this paper. We assumed crane pulley blocks in the experiments and analysis, but in practice, they may be replaced with electronic ones to improve effort and efficiency. Using the electronic ones will be a sub-problem since there is no need for pulling ropes. The proposed method is expected to help a company's technicians better judge if they need a heavy payload manipulator or keep their current crane equipment while employing several intelligent collaborative robots to operate them. As a result, it may help to accelerate the upgrade of manufacturing sites while reducing reforming budgets.
To achieve high-accuracy grasping of unknown objects, we present novel multilevel convolutional neural networks (CNNs) for robotic grasping with a parallel gripper or multifingered dexterous hand. ...The multilevel CNNs include four levels with different structures and functions. The first level is constructed to get the approximate position of the grasped object. The second level aims to obtain the preselected grasping rectangles. The third level is constructed to re-evaluate the preselected grasping rectangles and obtain substantially detailed features with quite a large network, so as to assess each preselected grasping rectangle exactly. By using a selection algorithm, the optimal grasping rectangle can be determined and unknown object grasping can be achieved with a parallel gripper. The purpose of the fourth level is to obtain the finger position distribution to complete the accurate grasping of unknown objects with a multifingered dexterous hand. The test results indicate that, compared to state-of-the-art methods, the proposed multilevel CNNs can greatly increase the precision of the grasping rectangle. Grasping experiments were implemented on a Youbot arm with five degrees of freedom and a Shadow four-fingered dexterous hand. The results show that the multilevel CNNs can determine the optimal grasping rectangle and finger position distribution, thereby achieving high-accuracy grasping of various unknown objects, even under several complex environmental conditions.
Note to Practitioners-Robot grasping of objects lags far behind human experiences and poses a significant challenge in the robotics area. To solve it, we present new multilevel convolutional neural networks (CNNs) to process red green blue-depth (RGB-D) images and realize optimal grasping detection of unknown objects. Moreover, we provide details of the network structure, network training, and network testing. The testing results obtained from the open grasping data set show that the multilevel CNNs can significantly increase the accuracy of the grasping rectangle compared to state-of-the-art methods. Experiments were implemented on different robotic platforms, including a five-degrees-of-freedom Youbot arm with a parallel gripper and a UR5 robot arm with a Shadow multifingered dexterous hand. The results validate that the multilevel CNNs offer excellent generalization and robustness for handling different sizes and shapes of unknown objects, as well as background disturbances, which are key problems in robotic manipulation.