Search

Abstract Among tetrapods, grasping is an essential function involved in many vital behaviours. The selective pressures that led to this function were widely investigated in species with prehensile hands and feet. Previous studies namely highlighted a strong effect of item properties but also of the species habitat on manual grasping behaviour. African savannah elephants (Loxodonta africana) are known to display various prehensile abilities and use their trunk in a large diversity of habitats. Composed of muscles and without a rigid structure, the trunk is a muscular hydrostat with great freedom of movement. This multitasking organ is particularly recruited for grasping food items while foraging. Yet, the diet of African savannah elephants varies widely between groups living in different habitats. Moreover, they have tusks alongside the trunk which can assist in grasping behaviours, and their tusk morphologies are known to vary considerably between groups. Therefore, in this study, we investigate the food grasping techniques used by the trunk of two elephant groups that live in different habitats: an arid study site in Etosha National Park in Namibia, and an area with consistent water presence in Kruger National Park in South Africa. We characterised the tusks profiles and compared the grasping techniques and their frequencies of use for different foods. Our results show differences in food‐grasping techniques between the two groups. These differences are related to the food item property and tusk profile discrepancies highlighted between the two groups. We suggest that habitat heterogeneity, particularly aridity gaps, may induce these differences. This may reveal an optimisation of grasping types depending on habitat, food size and accessibility, as well as tusk profiles.

Among tetrapods, grasping is an essential function involved in many vital behaviours. The selective pressures that led to this function were widely investigated in species with prehensile hands and feet. Previous studies namely highlighted a strong effect of item properties but also of the species habitat on manual grasping behaviour. African savannah elephants (Loxodonta africana) are known to display various prehensile abilities and use their trunk in a large diversity of habitats. Composed of muscles and without a rigid structure, the trunk is a muscular hydrostat with great freedom of movement. This multitasking organ is particularly recruited for grasping food items while foraging. Yet, the diet of African savannah elephants varies widely between groups living in different habitats. Moreover, they have tusks alongside the trunk which can assist in grasping behaviours, and their tusk morphologies are known to vary considerably between groups. Therefore, in this study, we investigate the food grasping techniques used by the trunk of two elephant groups that live in different habitats: an arid study site in Etosha National Park in Namibia, and an area with consistent water presence in Kruger National Park in South Africa. We characterised the tusks profiles and compared the grasping techniques and their frequencies of use for different foods. Our results show differences in food‐grasping techniques between the two groups. These differences are related to the food item property and tusk profile discrepancies highlighted between the two groups. We suggest that habitat heterogeneity, particularly aridity gaps, may induce these differences. This may reveal an optimisation of grasping types depending on habitat, food size and accessibility, as well as tusk profiles. [ABSTRACT FROM AUTHOR]

Abstract: Exceptional coordination of grip (G; the normal force that prevents slippage of the grasped object) and load force (L; the tangential force originating from the object''s weight and inertia) has been interpreted as a part of evidence that both the anatomy and neural control of human hands have been predominantly designed for manipulation tasks. In the present study, we tested the hypothesis that the precision grasp (uses only the tips of fingers and the thumb of one hand) provides better indices of G and L coordination in static manipulation tasks than two bimanual grasps (palm–palm and fingers–thumb; both using opposing segments of two hands). However, in addition to a subtle difference in relative timing of G and L between the precision and two bimanual grasps, we only found that the fingers–thumb grasp is characterized with higher G/L ratio and somewhat higher modulation of G than not only the precision, but also the bimanual palm–palm grasp. However, all remaining data including the correlation coefficients between G and L demonstrated no difference among three evaluated grasping techniques. Therefore, we concluded that the elaborate G and L coordination associated with uni-manual grasps could be partly generalized to a variety of manipulation tasks including those based on bimanual grasping techniques. Taking into account the importance of manipulation tasks in both everyday life and clinical evaluation, future studies should extend the present research to both other grasping techniques and dynamic manipulation conditions. [Copyright &y& Elsevier]

Arthroscopic repair of wide rotator cuff ruptures is burdened by a percentage of recurrences that is greater than the repair carried out when an open technique is used. One of the main reasons for this difference can be searched for in the minor hold of stitching on the tendinous aspect obtained with arthroscopic repair. In fact, when an open technique is used, good hold can be guaranteed by using reinforced stitches such as the modified Mason-Allen. Thus, arthroscopic repair technique on the tendinous aspect, particularly in wide and massive injuries, must be improved. It was the purpose of this study to compare a new reinforced stitch that can easily be obtained in arthroscopy (simple stitch that orthogonally crosses a horizontal stitch previously knotted on the tendon: SS-HL), with traditional stitches (simple stitch, mattress-stitch and modified Mason-Allen stitch). Tests were carried out on sheep infraspinatus tendons in order to evaluate the resistance of pull-out. The SS-HL stitch showed resistance to loading that was similar to that when the modified Mason-Allen was used, but it was greater than that shown by the simple stitch (+48%) and the mattress stitch (+35%).

Some daily tasks involve grasping multiple objects in one hand and releasing them in a determined order, for example laying out a surgical table or distributing items on shelves. For training these tasks in Virtual Reality (VR), there is no technique for allowing users to grasp multiple objects in one hand in a realistic way, and it is not known if such a technique would benefit user experience. Here, we design a multi-object grasp technique that enables users to grasp multiple objects in one hand and release them in a controlled way. We tested an object placement task under three conditions: real life, VR with single-object grasp and VR with multi-object grasp. Task completion time, distance travelled by the hands and subjective experience were measured in three scenarios: sitting in front of a desktop table, standing up in front of shelves and a room-size scenario where walking was required. Results show that the performance in a real environment is better than in Virtual Reality, both for single-object and multi-object grasping. The single-object technique performs better than the multi-object, except for the room scenario, where multi-object leads to less distance travelled and reported physical demand. For use cases where the distances are small (i.e., desktop scenario), single-object grasp is simpler and easier to understand. For larger scenarios, the multi-object grasp technique represents a good option that can be considered by other application designers.

This study observed three advertisements each from Nivea, Dove, and Golden Peacock from the angle of critical discourse analysis. The study is mainly focused on the language used in the advertisements of these brands and the marketing strategies they use to persuade the audience to buy their products. Discourse of these commercials is analyzed using Norman Fairclough is three-dimensional model of critical discourse analysis. It explores how the ideology of "fair skin as beautiful and desirable" is portrayed in the advertisements. All three advertisements were analyzed using qualitative research methodology. The results confirmed that marketers employed different attention grasping techniques and made consumers believe that whatever shown in the ads is the reality. The study also shows that stereotype like "Fair is beautiful" was depicted/displayed more evidently in the advertisements from pre social media era than in today's time. This tells us that the ideology of "Fair skin equals to beauty" is now not promoted in a way as it was being promoted in back days. Such example in this study is portrayed through Golden peacock newspaper advertisement which was from old day and two advertisements (Dove and Nivea) from this era of social media. [ABSTRACT FROM AUTHOR]

This paper presents a multifunctional underactuated two fingered adaptive grippers for grasping a wide range of objects in different working scenarios. Two layered‐based novel multifunctional gripper design is proposed by stacking a multijointed closed‐chain mechanism over a multijointed double parallelogram mechanism to achieve a maximum number of grasping techniques. The multijointed closed‐chain mechanism is employed to perform power, shape‐adaptive grasping, and a multijointed double parallelogram mechanism is used to perform scooping, parallel, and pinch grasping. For stable shape‐adaptive/power grasping, the proposed design allows more contact points between the object and the contact surface of fingers as compared to previous gripper mechanisms. Moreover, a complete mathematical model relating the contact forces at the links of each finger to the linear actuation force and spring torque is developed to conduct stability analysis of the proposed gripper design. Finally, simulations and several experiments are performed using real objects in a reconfigurable environment to demonstrate and validate the stable grasping capabilities of the proposed gripper. [ABSTRACT FROM AUTHOR]

Robotic grasping techniques for regular targets with known shapes are now well established. However, unknown shaped objects have complex features such as texture, shape, and appearance, which leads to inaccurate recognition and localization of shaped objects during grasp detection. To improve the generalization ability of the grasping detection network for unfamiliar shaped objects, we propose a lightweight shaped object grasping detection network (LSOGD) based on feature fusion, which solves the problem that the network repeatedly extracts features from images and ultimately improves the accuracy of model detection by combining different features. The effectiveness of LSOGD is confirmed by performance evaluation on the Cornell dataset and Jacquard dataset, where the detection accuracy reaches 97.9% and 96.7% for unknown objects, respectively. In addition, due to the small proportion of shaped objects in the current publicly available dataset, we added a portion of industrial-shaped pieces based on the selection of some shaped objects in the Cornell grasping dataset to build a shaped object dataset named X-Cornell on which the accuracy of our proposed model for grasping and detecting the unknown shaped objects is 94.6%. Finally, an actual robot grasping experiment was conducted using a Realsense d435i camera and a Kinova robotic arm, and the success rate of grasping shaped objects was 94%. [ABSTRACT FROM AUTHOR]

This research presents a novel approach to robotic grasping by integrating an attention mechanism and advanced U-Net architectures, specifically UNet and UNet++, into the Generative Grasping Convolutional Neural Network (GG-CNN). The proposed method, Attention UNet++ GG-CNN, aims to improve the performance and accuracy of robotic grasping predictions significantly. The attention mechanism allows the model to focus on the most relevant features in the depth image, enhancing the quality of grasp predictions. The UNet and UNet++ structures, renowned for their efficiency in semantic segmentation tasks, are adapted to generate a pixel-wise grasp quality map, providing a one-to-one mapping from depth images. The UNet++ structure, with its nested and dense skip pathways, further improves the model's ability to capture and propagate low-level details to higher-level features. This approach overcomes the limitations of traditional deep learning grasping techniques by avoiding discrete sampling of grasp candidates and reducing computation times. Preliminary results indicate that the Attention UNet++ GG-CNN significantly improves the accuracy and performance of robotic grasping,with the Attention UNet++ GG-CNN achieving Intersection over Union (IoU) scores up to 95.86%, and average performance metrics across 25%, 50%, and 75% thresholds reaching as high as 88.29%, confirming its potential for more effective and reliable robotic manipulation in various settings, paving the way for more efficient and reliable robotic manipulation in dynamic environments. [ABSTRACT FROM AUTHOR]

Grasping objects in cluttered environments remains a significant challenge in robotics, particularly when dealing with novel objects that have not been previously encountered. This paper proposes a novel approach to address the problem of robustly learning object grasping in cluttered scenes, focusing on scenarios where the objects are unstructured and randomly placed. We present a unique Deep Q-learning (DQN) framework combined with a full convolutional network suitable for the end-to-end grasping of multiple adhesive objects in a cluttered environment. Our method combines the depth information of objects with reinforcement learning to obtain an adaptive grasping strategy to enable a robot to learn and generalize grasping skills for novel objects in the real world. The experimental results demonstrate that our method significantly improves the grasping performance on novel objects compared to conventional grasping techniques. Our system demonstrates remarkable adaptability and robustness in cluttered scenes, effectively grasping a diverse array of objects that were previously unseen. This research contributes to the advancement of robotics with potential applications, including, but not limited to, redundant manipulators, dual-arm robots, continuum robots, and soft robots. [ABSTRACT FROM AUTHOR]

Commercially viable automated picking in unstructured environments by a robot arm remains a difficult challenge. The problem of robot grasp planning has long been around but the existing solutions tend to be limited when it comes to deploy them in open-ended realistic scenarios. Practical picking systems are called for that can handle the different properties of the objects to be manipulated, as well as the problems arising from occlusions and constrained accessibility. This paper presents a practical solution to the problem of robot picking in an online shopping warehouse by means of a novel approach that integrates a carefully selected method with a new strategy, the centroid normal approach (CNA), on a cost-effective dual-arm robotic system with two grippers specifically designed for this purpose: a two-finger gripper and a vacuum gripper. Objects identified in the scene point cloud are matched to the grasping techniques and grippers to maximize success. Extensive experimentation provides clues as to what are the reasons for success and failure. We chose as benchmark the scenario proposed by the 2017 Amazon Robotics Challenge, since it represents a realistic description of a retail shopping warehouse case; it includes many challenging constraints, such as a wide variety of different product items with a diversity of properties, which are also presented with restricted visibility and accessibility. [ABSTRACT FROM AUTHOR]

While rat models are frequently used to study tendon healing, there is a lack of research comparing various rotator cuff repair methods in this animal model. Determining the most effective method to begin with is pivotal for biological studies focused on healing augmentation. No study to date has shown the superiority of one repair over the other for rotator cuff repair in a rat model. We performed a biomechanic study using a rat model to study the strength of four common grasping techniques. We assessed if the bone tunnel trajectory influenced the early biomechanics of the repair at postoperative day 0 (POD0). Sixty cadaveric rat shoulders were divided equally into 6 groups; 4 groups were allocated for the biomechanical strength testing based on either a (1) modified Mason Allen (MM), (2) modified Kessler loop (MK), (3) horizontal mattress (HM), or a (4) simple interrupted stitch (SS) technique. The remaining 2 groups were used to evaluate two tunneling angles: a transverse tunnel (TT) that was perpendicular to the long humeral axis, or a longitudinal tunnel (LT) that was 30◦ angle to the humerus. MM had the highest mean failure load, followed by MK, HM, and SS. Pairwise comparison revealed that MM was stronger than SS and HM (P = 0.025 and P = 0.026, respectively), although similar to the MK (P = 0.881). MM was stiffer than MK (P < 0.001), HM (P = 0.008), and SS (P < 0.001). The TT and LT had similar loads to failure and stiffness. Our study suggests that the MM technique provides a stronger and stiffer rotator cuff repair than the others. [ABSTRACT FROM AUTHOR]

Accurately grasping objects with varying levels of hardness and softness is a challenging task. Current robotic grasping methods rely solely on visual to determine the grasping posture, without considering the grasping force of different objects, which might increase the risk of slippage or damage. For the purpose of realize the improvement and supplementation of visual information from the dimension of force, several robots include tactile sensors installed at fingertips. In this paper, we propose a method that integrates visual and tactile information to accurately determine the 6D posture and force for robot grasping. The main challenges of this research include (1) grasping representation of visual and tactile data from heterogeneous sources, (2) Construction of the implicit link between grasping posture and clutching force, (3) a visual–tactile training dataset. To address these challenges, we first use a grasping quality assessment module to filter the grasping posture and a transformer-depth separation convolution module to predict the grasping force; second, we propose a diffusion model with multi-stage convolution module to generate the optimal grasping. In addition, we created a visual–tactile grasping data representation form that included the grasping quality of grasping postures, and matching tactile data for objects of 8 distinct hardness. Experiments show that our method achieves a 98% success rate and decreases grasping force redundancy by 78% compared to purely visual methods,which significantly improves the accuracy and stability of the robot grasping. [ABSTRACT FROM AUTHOR]

Robot visual servoing for grasping has long been challenging to execute in complex visual environments because of issues with efficient feature extraction. This paper proposes a novel visual servoing grasping approach based on the Deep Visual Servoing Feature Network (DVSFN) to tackle this issue. The approach enables feasible to extract scale-invariant point features and target bounding boxes in real time by building an effective single-stage multi-dimensional feature extractor. The DVSFN is then integrated into a Levenberg–Marquardt–based image visual servoing (LM-IBVS) controller. The above creates a mapping link between the robot's joint space and image features. The robot is then guided in positioning and grabbing by converting the difference between the expected and present features into the corresponding robot joint velocities. Experimental results demonstrate that the proposed method achieves a mean average precision (mAP) of 0.80 and 0.87 for detecting target bounding boxes and point features, respectively, in scenarios with significant lighting variations and occlusions. Under low-light and partial occlusion conditions, the method achieves an average grasping success rate approximately 80%. [ABSTRACT FROM AUTHOR]

Soft grippers perform various handling tasks using passive conformability. This article reviews the improvements in their capabilities of dexterous manipulations, including how they achieve dexterity and how their performance could be evaluated. This article particularly points out the correlations between potential and real dexterity, and the relationship between the space of degrees of freedom and the corresponding dexterity level. Our main contribution is the proposition of a uniform framework for the characterization of soft grippers and their performance. We first present an introduction to soft grippers and those capable of in-hand manipulation. We emphasize their hybridization by combining soft and rigid materials or using several active materials. Next, we define and discuss the manipulation tasks and how to achieve dexterity, making a distinction between stable grasping and stable in-hand manipulation. We finally discuss the means to achieve assessment and how the performance can be evaluated, and we develop a general exploitable approach for characterizing soft grippers and their dexterous performance based on their architecture, DOF space, and physical performance. [ABSTRACT FROM AUTHOR]

This research presents a novel approach to robotic grasping by integrating an attention mechanism and advanced U-Net architectures, specifically UNet and UNet++, into the Generative Grasping Convolutional Neural Network (GG-CNN). The proposed method, Attention UNet++ GG-CNN, aims to improve the performance and accuracy of robotic grasping predictions significantly. The attention mechanism allows the model to focus on the most relevant features in the depth image, enhancing the quality of grasp predictions. The UNet and UNet++ structures, renowned for their efficiency in semantic segmentation tasks, are adapted to generate a pixel-wise grasp quality map, providing a one-to-one mapping from depth images. The UNet++ structure, with its nested and dense skip pathways, further improves the model's ability to capture and propagate low-level details to higher-level features. This approach overcomes the limitations of traditional deep learning grasping techniques by avoiding discrete sampling of grasp candidates and reducing computation times. Preliminary results indicate that the Attention UNet++ GG-CNN significantly improves the accuracy and performance of robotic grasping,with the Attention UNet++ GG-CNN achieving Intersection over Union (IoU) scores up to 95.86%, and average performance metrics across 25%, 50%, and 75% thresholds reaching as high as 88.29%, confirming its potential for more effective and reliable robotic manipulation in various settings, paving the way for more efficient and reliable robotic manipulation in dynamic environments.

Grasping and object manipulation is a key element of intelligent behavior. Many innovative cyberphysical systems involve some kind of object grasp and manipulation, to the extent that grasping has been recognized as a critical technology for the next generation industrial systems. In this survey, we aim to draw a broad landscape of applications and current research trends and topics relating to grasping techniques and tools. Applications range from biomedical and surgical to industrial warehouse pick and place tasks, covering a wide range of spatial scales, from micro to macro scales. The resources involved and research lines under development include the latest computational intelligence tools as well as the research on new materials and devices for sensing and actuation. [ABSTRACT FROM AUTHOR]