Robust Grasps Research Articles

Bioinspired Bidirectional Stiffening Soft Actuators Enable Versatile and Robust Grasping.

The bending stiffness modulation mechanism for soft grippers has gained considerable attention to improve grasping versatility, capacity, and stability. However, lateral stability is usually ignored or hard to achieve at the same time with good bending stiffness modulation performance. Therefore, this article presents a bioinspired bidirectional stiffening soft actuator (BISA), enabling compliant and stable performance. BISA combines the air tendon actuation (ATA) and a bone-like structure (BLS). The ATA is the main actuation of the BISA, and the bending stiffness can be modulated with a maximum stiffness of about 0.7 N/mm and a maximum magnification of three times when the bending angle is 45°. Inspired by the morphological structure of the phalanx, the lateral stiffness can be modulated by changing the pulling force of the BLS. The actuator with BLSs can improve the lateral stiffness by about 3.9 times compared to the one without BLSs. The maximum lateral stiffness can reach 0.46 N/mm. And the lateral stiffness can be modulated by decoupling about 1.3 times (e.g., from 0.35 to 0.46 N/mm when the bending angle is 45°). The test results show that the influence of the rigid structures on bending is small with about 1.5 mm maximum position errors of the distal point of the actuator in different pulling forces. The advantages brought by the proposed method enable versatile four-finger grasping. The performance of this gripper is characterized and demonstrated on multiscale, multiweight, and multimodal grasping tasks.

Robust Grasping of a Variable Stiffness Soft Gripper in High-Speed Motion Based on Reinforcement Learning.

Industrial robots are widely deployed to perform pick-and-place tasks at high speeds to minimize manufacturing time and boost productivity. When dealing with delicate or fragile goods, soft robotic grippers are better end effectors than rigid grippers due to their softness and safe interaction. However, high-speed motion causes the soft robotic gripper to vibrate, leading to damage of the objects or failed grasping. Soft grippers with variable stiffness are considered to be effective in suppressing vibrations by adding damping devices, but it is quite challenging to compromise between stiffness and compliance. In this article, a controller based on deep reinforcement learning is proposed to control the stiffness of the soft robotic gripper, which can accurately suppress the vibration with only a minor influence on its compliance and softness. The proposed controller is a real-time vibration control strategy, which estimates the output of the controller based on the current operating environment. To demonstrate the effectiveness of the proposed controller, experiments were done with a UR5 robotic arm. For different situations, experimental results show that the proposed controller responds quickly and reduces the amplitude of the oscillation substantially.

Design and Development of a New Bioinspired Hybrid Robotic Gripper for Multi-Mode Robust Grasping

Design and Development of a New Bioinspired Hybrid Robotic Gripper for Multi-Mode Robust Grasping

Adaptive Fingers Coordination for Robust Grasp and In-Hand Manipulation Under Disturbances and Unknown Dynamics

Adaptive Fingers Coordination for Robust Grasp and In-Hand Manipulation Under Disturbances and Unknown Dynamics

Stiffness-Tunable Soft Bellows Actuators by Cross-Fiber Jamming Effect for Robust Grasping

Soft actuators typically exhibit low stiffness and low load-bearing properties due to the intrinsic limitations of soft materials. Stiffness modulation is an effective means to improve the performance of soft actuators. However, most stiffness-tunable mechanisms are nonstretchable, and have difficulty in independently adjusting the tensile stiffness of soft elongation actuators. Here, a universal cross-fiber jamming mechanism with both elongation and bending stiffness-tunable capability is proposed for soft bellows actuators. It is composed of two semicircular symmetrical fiber bundles in an up-and-down crossed arrangement, and can follow the tensile state of the soft bellows actuator through the passive staggered motion of the layered fiber bundles. Furthermore, a soft gripper with wide grasping range and sufficient grasping stability is also developed by applying soft bellows actuators with cross-fiber jamming mechanisms. Experiments are conducted to show the related performance of the proposed cross-fiber jamming mechanism. The results show that it has fast antiimpact damping response, strong shaping ability and adjustable stiffness. Such efficient performance will promote the ability of grasping robots, and is expected to be used in daily life and industry.

Category-Association Based Similarity Matching for Novel Object Pick-and-Place Task

Robotic pick-and-place has been researched for a long time to cope with uncertainty of novel objects and changeable environments. Past works mainly focus on learning-based methods to achieve high precision. However, they have difficulty being generalized for the limitation of specified training models. To break through this drawback of learning-based approaches, we introduce a new perspective of similarity matching between novel objects and a known database based on category-association to achieve pick-and-place tasks with high accuracy and stabilization. We calculate the category name similarity using word embedding to quantify the semantic similarity between the categories of known models and the target real-world objects. With a similar model identified by a similarity prediction function, we preplan a series of robust grasps and imitate them to plan new grasps on the real-world target object. We also propose a distance-based method to infer the in-hand posture of objects and adjust small rotations to achieve stable placements under uncertainty. Through a real-world robotic pick-and-place experiment with a dozen of in-category and out-of-category novel objects, our method achieved an average success rate of 90.6% and 75.9% respectively, validating the capacity of generalization to diverse objects.

Learning Suction Graspability Considering Grasp Quality and Robot Reachability for Bin-Picking.

Deep learning has been widely used for inferring robust grasps. Although human-labeled RGB-D datasets were initially used to learn grasp configurations, preparation of this kind of large dataset is expensive. To address this problem, images were generated by a physical simulator, and a physically inspired model (e.g., a contact model between a suction vacuum cup and object) was used as a grasp quality evaluation metric to annotate the synthesized images. However, this kind of contact model is complicated and requires parameter identification by experiments to ensure real world performance. In addition, previous studies have not considered manipulator reachability such as when a grasp configuration with high grasp quality is unable to reach the target due to collisions or the physical limitations of the robot. In this study, we propose an intuitive geometric analytic-based grasp quality evaluation metric. We further incorporate a reachability evaluation metric. We annotate the pixel-wise grasp quality and reachability by the proposed evaluation metric on synthesized images in a simulator to train an auto-encoder–decoder called suction graspability U-Net++ (SG-U-Net++). Experiment results show that our intuitive grasp quality evaluation metric is competitive with a physically-inspired metric. Learning the reachability helps to reduce motion planning computation time by removing obviously unreachable candidates. The system achieves an overall picking speed of 560 PPH (pieces per hour).

Grasp Planning With a Soft Reconfigurable Gripper Exploiting Embedded and Environmental Constraints

Grasping in unstructured environments requires highly adaptable and versatile hands together with strategies to exploit their features to get robust grasps. This letter presents a method to grasp objects using a novel reconfigurable soft gripper with embodied constraints, the Soft ScoopGripper (SSG). The considered grasp strategy, called scoop grasp, exploits the SSG features to perform robust grasps. The embodied constraint, i.e., a scoop, is used to slide between the object and a flat surface (e.g., table, wall) in contact with it. The fingers are first configured according to the object geometry and then used to establish reliable contacts with it. This work introduces an algorithm that, given the object point cloud, computes the best pre-grasp gripper configuration from which to start the scoop grasp strategy. Several experimental trials in different scenarios confirmed the effectiveness of the proposed method.

Inflatable Particle-Jammed Robotic Gripper Based on Integration of Positive Pressure and Partial Filling.

In this work, we proposed an inflatable particle-jamming gripper based on a novel grasping strategy of integrating the positive pressure and partial filling, in which the positive pressure increases the contact area between the gripper and objects, and the grain package in a partial-filled state provides significant grasping adaptation for the gripper. First, we design and fabricate the inflatable particle-jamming gripper and clarify its working mechanism. Then three kinds of grippers, including the proposed inflatable gripper, full-filled gripper, and partial-filled gripper, are experimentally compared for the capability of grasping objects of various sizes, and their performances from four metrics (compliance, reliability, grasping robustness, and lifting efficiency) are evaluated as well. Furthermore, a theoretical analysis is carried out for different grasping performances among the three kinds of grippers, in which the inflatable gripper performs a more promising grasping performance. In this article, by inflating the gripper to an ordered extent with positive pressure, the originally full-filled gripper turns into a partial-filled state. Based on the unique grasping strategy of the proposed gripper, it is possible to achieve a brilliant compliance and robust grasps. Even though the object is located 20 mm away from the gripper-center-axis, valid grasps are observed as well. It is concluded that the proposed gripper could potentially have a wide range of applications in the industry and daily activities.

Visual Reconstruction and Localization-Based Robust Robotic 6-DoF Grasping in the Wild

The intelligent grasping expects that the manipulator has the ability to grasp objects with high degree of freedom in a wild (unstructured) environment. Due to low perception ability in handing targets and environments, most industrial robots are limited to top-down 4-DoF grasping. In this work, we propose a novel low-cost coarse to fine robotic grasping framework. First, we design a global localization based environment perception method, which enables the manipulator to roughly and automatically locate work space. Then, constrained by the above initial localization, a 3D point cloud reconstruction based 6-DoF pose estimation method is proposed for the manipulator further fine locating grasping target. Finally, our framework realizes full function of visual 6DoF robotic grasping, which includes two different visual servoing and grasp planning strategies for different objects grasping. Meanwhile, it also can integrate various state-of-arts 6DoF pose estimation algorithms to facilitate various practical grasping applications or researches. Experimental results show that our method achieves autonomous robotic grasping with high degree of freedom in an unknown environment. Especially for objects with occlusion, singular shape or small scale, our method can still maintain robust grasping.

Grasping With the SoftPad, a Soft Sensorized Surface for Exploiting Environmental Constraints With Rigid Grippers

A common trend in robotic manipulation is to build compliant hands that can exploit environmental constraints to perform robust grasps. However, in large-scale industrial applications, end-effectors are mostly rigid. How can we exploit environmental constraints using rigid industrial grippers? We propose to add compliance to the environment, thanks to a soft modular pneumatic surface: the SoftPad. Pressure sensors connected to its modules allow to estimate the object pose and center of mass and to detect the contact between the gripper and the SoftPad during a grasping task. A new grasp strategy that exploits such information for top-grasping objects, without using cameras or force sensors, is presented. It has been tested with objects having a wide range of sizes, shapes, and weights. The SoftPad design can easily be adapted to the set of objects that are used in a certain application.

Multi-Modal Transfer Learning for Grasping Transparent and Specular Objects

State-of-the-art object grasping methods rely on depth sensing to plan robust grasps, but commercially available depth sensors fail to detect transparent and specular objects. To improve grasping performance on such objects, we introduce a method for learning a multi-modal perception model by bootstrapping from an existing uni-modal model. This transfer learning approach requires only a pre-existing uni-modal grasping model and paired multi-modal image data for training, foregoing the need for ground-truth grasp success labels nor real grasp attempts. Our experiments demonstrate that our approach is able to reliably grasp transparent and reflective objects. Video and supplementary material are available at https://sites.google.com/view/transparent-specular-grasping.

Robotic grasp analysis using deformable solid mechanics

Given an object and a hand, identifying a robust grasp out of an infinite set of grasp candidates is a challenging problem, and several grasp synthesis approaches have been proposed in the robotics community to find the promising ones. Most of the approaches assume both the object and the hand to be rigid and evaluate the robustness of the grasp based on the wrenches acting at contact points. Since rigid body mechanics is used in these works, the actual distribution of the contact tractions is not considered, and contacts are represented by their resultant wrenches. However, the tractions acting at the contact interfaces play a critical role in the robustness of the grasp, and not accounting for these in detail is a serious limitation of the current approaches. In this paper, we replace the conventional wrench-based rigid-body approaches with a deformable-body mechanics formulation as is conventional in solid mechanics. We briefly review the wrench-based grasp synthesis approaches in the literature and address the drawbacks present in them from a solid mechanics standpoint. In our formulation, we account for deformation in both the grasper and the object and evaluate the robustness of grasp based on the distribution of normal and tangential tractions at the contact interface. We contrast how a given grasp situation is solved using conventional wrench space formulations and deformable solid mechanics and show how tractions on the contacting surfaces influence the grasp equilibrium. Recognizing that contact areas can be correlated to contact tractions, we propose a grasp performance index, $$\pi $$ , based on the contact areas. We also devise a grasp analysis strategy to identify robust grasps under random perturbations and implement it using Finite Element Method (FEM) to study a few grasps. One of the key aspects of our Finite Element (FE)-based approach is that it can be used to monitor the dynamic interaction between object and hand for judging grasp robustness. We then compare our measure, $$\pi $$ , with conventional grasp quality measures, $$\epsilon $$ and v and show that it successfully accounts for the effect of the physical characteristics of the object and hand (such as the mass, Young’s modulus and coefficient of friction) and identifies robust grasps that are in line with human intuition and experience.

A Fully Multi-Material Three-Dimensional Printed Soft Gripper with Variable Stiffness for Robust Grasping.

Multi-material three-dimensional (3D) printing has provided the possibility of direct 3D printing of soft actuators with high complexity and functionality in a fast and easy fabrication process. In this article, we present the design of a multi-material 3D printed variable stiffness soft robotic gripper to ensure grasping robustness during high acceleration. The proposed gripper contains two identical soft fingers, with each finger including a pneumatic actuator and an integrated layer jamming unit. Prototypes of the soft finger, with material hardness transfer from the soft-bodied actuator to the hard pneumatic tubing and layer jamming unit, are fully fabricated by one-step 3D printing. A multi-material 3D printer, Objet350Connex, is used to directly print out the whole finger without the need for an additional casting process. The printed soft finger has a complex inner geometry, which integrates a small, light, and flexible layer jamming unit. The proposed finger can freely deform at low stiffness and maintain its grasping robustness at high stiffness during high acceleration. To demonstrate the effectiveness of the proposed design, the gripper is mounted on a robotic arm to evaluate its grasping robustness. With the aid of the integrated layer jamming unit, grasping robustness can be guaranteed when the robotic arm is moving at acceleration up to 8 m/s2. The results show that the proposed soft gripper is an effective design, which can guarantee grasping robustness during high acceleration.

Fingertip Surface Optimization for Robust Grasping on Contact Primitives

We address the problem of fingertip design by leveraging on the fact that most grasp contacts share a few classes of local geometries. In order to maximize the contact areas for achieving more robust grasps, we first define the concept of Contact Primitive, which represents a set of contacts of similar local geometries. Thereafter, we propose a uniform cost algorithm, which is formulated as a decision making process in a tree structure, to cluster a set of example grasp contacts into a finite set of Contact Primitives. We design fingertips by optimization to match the local geometry of each contact primitive, and then three-dimensionally print them using soft materials to compensate for optimization residuals. For novel objects, we provide an efficient algorithm to generate grasp contacts that match the fingertip geometries while together forming stable grasps. Comparing to a baseline of flat fingertip design, the experiment results show that our design significantly improves grasp stability, and it is more robust against various uncertainties.

Planning High-Quality Grasps Using Mean Curvature Object Skeletons

In this letter, we present a grasp planner that integrates two sources of information to generate robust grasps for a robotic hand. First, the topological information of the object model is incorporated by building the mean curvature skeleton and segmenting the object accordingly in order to identify object regions which are suitable for grasping. We show how this information can be used to derive different grasping strategies, which also allows to distinguish between precision and power grasps. Second, the local surface structure is investigated to construct feasible and robust grasping poses by aligning the hand according to the local object shape. We apply the approach to a wide variety of object models of the KIT and the YCB real-world object model databases and evaluate it with several robotic hands. The results show that the skeleton-based grasp planner is capable to generate high-quality grasps in an efficient manner. In addition, we evaluate how robust the planned grasps are against hand positioning errors as they occur in real-world applications due to perception and actuation inaccuracies. The evaluation shows that the majority of the generated grasps are of high quality since they can be successfully applied even when the hand is not exactly positioned.

Modeling and Calibration of a Tactile Sensor for Robust Grasping

Robust grasping of everyday objects is still an open problem in robotics due to uncertainties affecting object physical properties like weight and friction. The present paper proposes to exploit the perception data provided by a tactile sensor to obtain useful information on the contact state, like normal and tangential components of the contact force. A novel mechanical model of the contact between the soft fingertip and the grasped object is here presented and supported by both FEM analysis and experimental verification. The proposed algorithm to extract such information from tactile raw data, based on this model, is simple enough to allow implementation of the grasp control strategy on the control hardware embedded into a standard robotic parallel gripper, so as to mimic human reactive grip responses, which occur when the control of an held object appears uncertain.

Assistive grasping with an augmented reality user interface

Assisting impaired individuals with robotic devices is an emerging and potentially transformative technology. This paper describes the design of an assistive robotic grasping system that allows impaired individuals to interact with the system in a human-in-the-loop manner, including the use of a novel cranio-facial electromyography input device. The system uses an augmented reality interface that allows users to plan grasps online that match their task-oriented intents. The system uses grasp quality measurements that generate more robust grasps by considering the local geometry of the object and the effect of uncertainty during grasp acquisition. This interface is validated by testing with real users, both healthy and impaired. This work forms the foundation for a flexible, fully featured human-in-the-loop system that allows users to grasp known and unknown objects in cluttered spaces using novel, practical human–robot interaction paradigms that have the potential to bring human-in-the-loop assistive devices out of the research environment and into the lives of those that need them.

Grasping objects localized from uncertain point cloud data

Robotic grasping is very sensitive to how accurate is the pose estimation of the object to grasp. Even a small error in the estimated pose may cause the planned grasp to fail. Several methods for robust grasp planning exploit the object geometry or tactile sensor feedback. However, object pose range estimation introduces specific uncertainties that can also be exploited to choose more robust grasps. We present a grasp planning method that explicitly considers the uncertainties on the visually-estimated object pose. We assume a known shape (e.g. primitive shape or triangle mesh), observed as a–possibly sparse–point cloud. The measured points are usually not uniformly distributed over the surface as the object is seen from a particular viewpoint; additionally this non-uniformity can be the result of heterogeneous textures over the object surface, when using stereo-vision algorithms based on robust feature-point matching. Consequently the pose estimation may be more accurate in some directions and contain unavoidable ambiguities.The proposed grasp planner is based on a particle filter to estimate the object probability distribution as a discrete set. We show that, for grasping, some ambiguities are less unfavorable so the distribution can be used to select robust grasps. Some experiments are presented with the humanoid robot iCub and its stereo cameras.

1A1-J04 多指ハンドを用いた関節角の位置制御に基づく誤差に頑健な物体把持(ロボットハンドの機構と把持戦略(1))

1A1-J04 多指ハンドを用いた関節角の位置制御に基づく誤差に頑健な物体把持(ロボットハンドの機構と把持戦略(1))