Search Results (22)

Apple picking is an inherently labor-intensive, time-consuming, and costly task, and robotic harvesting represents a potential alternative to address this challenge. This study presents the development and field evaluation of an integrated robotic system for apple harvesting, which combines machine vision, a dual four-degree-of-freedom (DoF) manipulator, and a mobile platform. The harvesting mechanism employed a streamlined 4-DoF manipulator driven by closed-loop stepper motors, incorporating a differential gear mechanism to execute yaw and pitch motions. Trajectory planning utilized linear interpolation with a harmonic acceleration/deceleration profile to ensure smooth end-effector movement. Fruit detection and localization within the canopy were performed by a stereo vision system running a lightweight deep neural network, achieving a mean hand-eye calibration accuracy of 4.7 ± 2.7 mm. Three negative-pressure driven soft end-effector designs—a suction soft end-effector (SSE), a grasping soft end-effector (GSE), and a suction-grasping soft end-effector (SGSE)—were assessed for their harvesting performance. Field trials conducted in a commercial spindle orchard demonstrated that the GSE achieved the highest performance, with a harvesting success rate of 80.80% among reachable fruits, a full-process success rate (from detection to collection) of 61.59%, an overall fruit damage rate of 10.89%, and an average single-fruit cycle time of 5.27 s. In contrast, the SSE and SGSE showed lower success rates (49.21% and 64.71%, respectively). This work provides a practical robotic harvesting solution. It validates the feasibility of a zoned, multi-manipulator harvesting strategy and delivers comparative data to guide the development of more efficient and robust harvesting robots. Full article

In nature, structures such as earwig wings and mimosa leaves exhibit remarkable folding and unfolding capabilities. Inspired by these biological mechanisms, this work investigates soft foldable and torsional actuators based on Kresling crease pattern, fabricated using soft TPE 85A material through 3D printing. These actuators enable both foldable grasping and torsional motions. An analytical geometric model is developed to characterize the relationship between structural parameters and the inscribed circle area of a single-layer soft actuator, thereby elucidating their influence on contraction magnitude and relative deflection angle. Treating the soft actuator as an equivalent spring system, a mechanical model relating vacuum pressure to contraction ratio is further established, revealing an approximately linear relationship. The actuators are subsequently integrated with suction cups to form two end-effectors, a foldable soft gripper and a torsional soft gripper, and mounted onto a UR5 robotic arm via a customized flange. Demonstration experiments show that the foldable gripper achieves gentle, adaptive grasping of diverse objects, while the torsional gripper replicates human-like twisting motion, such as opening a bottle cap. This study highlights the potential of Kresling-based soft grippers for practical deployment in automated production tasks, including precision assembly and fruit harvesting. Full article

Soft robotics provides compliance, safe interaction, and adaptability that rigid systems cannot easily achieve. The octopus offers a powerful biological model, combining reversible suction adhesion, continuum arm motion, and reliable performance in wet environments. This review examines recent octopus-inspired soft grippers through three functional dimensions: structural and sensing devices, control strategies, and AI-driven applications. We summarize suction-cup geometries, tentacle-like actuators, and hybrid structures, together with optical, triboelectric, ionic, and deformation-based sensing modules for contact detection, force estimation, and material recognition. We then discuss control frameworks that regulate suction engagement, arm curvature, and feedback-based grasp adjustment. Finally, we outline AI-assisted and neuromorphic-oriented approaches that use event-driven sensing and distributed, spike-inspired processing to support adaptive and energy-conscious decision-making. By integrating developments across structure, sensing, control, and computation, this review describes how octopus-inspired grippers are advancing from morphology-focused designs toward perception-enabled and computation-aware robotic platforms. Full article

This paper systematically reviews the research progress of underwater soft grasping devices in the field of bionic structure, function integration, and tactile sensing technology by drawing on the structural characteristics of marine organisms such as octopuses, jellyfish, and sea anemones (such as suction cups, umbrella-like muscles, and stinging cells). This paper analyzes the inspiration for the design, the application of innovative materials, and the integration of sensing and driving from marine organisms, including a review of soft robotics technologies, such as shape memory alloys (SMA), ionic polymer metal composite materials (IPMCs), magnetic nanocomposite cilia, etc. The research results emphasize that bionic soft robots have the potential for transformation in completely changing underwater operations by providing enhanced flexibility, efficiency, and environmental adaptability. This work provides a bionic design paradigm and perception-driven integration method for underwater soft operation systems, thereby promoting equipment innovation in the fields of deep-sea exploration and ecological protection. Full article

Given the growing complexity of underwater operation tasks, particularly in confined spaces, turbulent environments, and dynamic object manipulation, the limitations of traditional rigid robotic arms are becoming ever more evident. To tackle these challenges, this paper proposes the development of a soft robotic arm modeled after octopus tentacles, incorporating biomimetic suckers. To tackle these challenges, this paper proposes the development of a soft robotic arm modeled after octopus tentacles, incorporating biomimetic suckers. By imitating the functional structure and suction cups of an octopus arm, a soft arm with a dual-segment continuous structure and eight-wire drive control is designed, integrating a flexible suction cup at the distal segment. A three-dimensional, dual-segment eight-wire driven segmented constant curvature motion model is developed to enable precise bending and rotational movements. In underwater grasping experiments, the soft robotic arm exhibited enhanced grasping stability, particularly in underwater environments, where it effectively copes with fluid disturbances and the capture of dynamic objects. This substantially increased the reliability and efficiency of underwater operations. Full article

Effective adaptive grasping capability is regarded as crucial for climbing robots. However, many dry adhesion legged climbing robots are primarily focused on mobility and load capacity to perform various climbing tasks, often overlooking their operational grasping abilities. Furthermore, flexible grippers designed for adaptive grasping are typically not capable of supporting autonomous climbing or perching motions; they must be rigidly integrated with legged climbing robots, which results in increased weight and reduced load capacity. To address this challenge, a novel dry adhesion climbing robot, MST-G, is proposed, featuring autonomous climbing, perching, and flexible adaptive grasping capabilities. During operation, MST-G is integrated with a legged climbing robot to perform tasks, but can autonomously climb when no task is present, thereby reducing load and ensuring stable motion. Additionally, a robust controller based on prescribed performance is introduced and tested on MST-G, which limits the joint tracking error to a prescribed safety limit, ensuring that motion trajectories can be executed safely and reliably. Full article

With the advent of robotics and artificial intelligence, the potential for automating tasks within human-centric environments has increased significantly. This is particularly relevant in the retail sector where the demand for efficient operations and the shortage of labor drive the need for rapid advancements in robot-based technologies. Densely packed retail shelves pose unique challenges for robotic manipulation and detection due to limited space and diverse object shapes. Vacuum-based grasping technologies offer a promising solution but face challenges with object shape adaptability. The study proposes a framework for robotic grasping in retail environments, an adaptive vacuum-based grasping solution, and a new evaluation metric—termed grasp shear force resilience—for measuring the effectiveness and stability of the grasp during manipulation. The metric provides insights into how retail objects behave under different manipulation scenarios, allowing for better assessment and optimization of robotic grasping performance. The study’s findings demonstrate the adaptive suction cups’ ability to successfully handle a wide range of object shapes and sizes, which, in some cases, overcome commercially available solutions, particularly in adaptability. Additionally, the grasp shear force resilience metric highlights the effects of the manipulation process, such as in shear force and shake, on the manipulated object. This offers insights into its interaction with different vacuum cup grasping solutions in retail picking and restocking scenarios. Full article

This research study represents a polydexterous deep reinforcement learning-based pick-and-place framework for industrial clutter scenarios. In the proposed framework, the agent tends to learn the pick-and-place of regularly and irregularly shaped objects in clutter by using the sequential combination of prehensile and non-prehensile robotic manipulations involving different robotic grippers in a completely self-supervised manner. The problem was tackled as a reinforcement learning problem; after the Markov decision process (MDP) was designed, the off-policy model-free Q-learning algorithm was deployed using deep Q-networks as a Q-function approximator. Four distinct robotic manipulations, i.e., grasp from the prehensile manipulation category and inward slide, outward slide, and suction grip from the non-prehensile manipulation category were considered as actions. The Q-function comprised four fully convolutional networks (FCN) corresponding to each action based on memory-efficient DenseNet-121 variants outputting pixel-wise maps of action-values jointly trained via the pixel-wise parametrization technique. Rewards were awarded according to the status of the action performed, and backpropagation was conducted accordingly for the FCN generating the maximum Q-value. The results showed that the agent learned the sequential combination of the polydexterous prehensile and non-prehensile manipulations, where the non-prehensile manipulations increased the possibility of prehensile manipulations. We achieved promising results in comparison to the baselines, differently designed variants, and density-based testing clutter. Full article

Multiple-suction-cup grasping can improve the efficiency of bin picking in cluttered scenes. In this paper, we propose a grasp planner for a vacuum gripper to use multiple suction cups to simultaneously grasp multiple objects or an object with a large surface. To take on the challenge of determining where to grasp and which cups to activate when grasping, we used 3D convolution to convolve the affordable areas inferred by a neural network with the gripper kernel in order to find graspable positions of sampled gripper orientations. The kernel used for 3D convolution in this work was encoded, including cup ID information, which helps to directly determine which cups to activate by decoding the convolution results. Furthermore, a sorting algorithm is proposed to determine the optimal grasp among the candidates. Our planner exhibited good generality and successfully found multiple-cup grasps in previous affordance map datasets. Our planner also exhibited improved picking efficiency using multiple suction cups in physical robot-picking experiments. Compared with single-object (single-cup) grasping, multiple-cup grasping contributed to $1.45\times$, $1.65\times$, and $1.16\times$ increases in efficiency for picking boxes, fruits, and daily necessities, respectively. Full article

Under water, on land, or in the air, creatures use a variety of grasping methods to hunt, avoid predators, or carry food. Numerous studies have been conducted to construct a bionic surface for grasping tasks. This paper reviews the typical biomimetic structures and surfaces (wedge-shaped surface, suction cup surface and thorn claw surface) for grasping scenarios. Initially, progress in gecko-inspired wedge-shaped adhesive surfaces is reviewed, encompassing the underlying mechanisms that involve tuning the contact area and peeling behavior. The applications of grippers utilizing this adhesive technology are also discussed. Subsequently, the suction force mechanisms and applications of surfaces inspired by octopus and remora suction cups are outlined. Moreover, this paper introduces the applications of robots incorporating the principles of beetle-inspired and bird-inspired thorn claw structures. Lastly, inspired by remoras’ adhesive discs, a composite biomimetic adhesive surface is proposed. It integrates features from wedge-shaped, suction cup, and claw thorn surfaces, potentially surpassing the adaptability of basic bioinspired surfaces. This surface construction method offers a potential avenue to enhance adhesion capabilities with superior adaptability to surface roughness and curvature. Full article

Different species of toothed whales (Odontoceti) exhibit a variety of tooth forms and enamel types. Some odontocetes have highly prismatic enamel with Hunter-Schreger bands, whereas enamel is vestigial or entirely lacking in other species. Different tooth forms and enamel types are associated with alternate feeding strategies that range from biting and grasping prey with teeth in most oceanic and river dolphins to the suction feeding of softer prey items without the use of teeth in many beaked whales. At the molecular level, previous studies have documented inactivating mutations in the enamel-specific genes of some odontocete species that lack complex enamel. At a broader scale, however, it is unclear whether enamel complexity across the full diversity of extant Odontoceti correlates with the relative strength of purifying selection on enamel-specific genes. Here, we employ sequence alignments for seven enamel-specific genes (ACP4, AMBN, AMELX, AMTN, ENAM, KLK4, MMP20) in 62 odontocete species that are representative of all extant families. The sequences for 33 odontocete species were obtained from databases, and sequences for the remaining 29 species were newly generated for this study. We screened these alignments for inactivating mutations (e.g., frameshift indels) and provide a comprehensive catalog of these mutations in species with one or more inactivated enamel genes. Inactivating mutations are rare in Delphinidae (oceanic dolphins) and Platanistidae/Inioidea (river dolphins) that have higher enamel complexity scores. By contrast, mutations are much more numerous in clades such as Monodontidae (narwhal, beluga), Ziphiidae (beaked whales), Physeteroidea (sperm whales), and Phocoenidae (porpoises) that are characterized by simpler enamel or even enamelless teeth. Further, several higher-level taxa (e.g., Hyperoodon, Kogiidae, Monodontidae) possess shared inactivating mutations in one or more enamel genes, which suggests loss of function of these genes in the common ancestor of each clade. We also performed selection (dN/dS) analyses on a concatenation of these genes and used linear regression and Spearman’s rank-order correlation to test for correlations between enamel complexity and two different measures of selection intensity (# of inactivating mutations per million years, dN/dS values). Selection analyses revealed that relaxed purifying selection is especially prominent in physeteroids, monodontids, and phocoenids. Linear regressions and correlation analyses revealed a strong negative correlation between selective pressure (dN/dS values) and enamel complexity. Stronger purifying selection (low dN/dS) is found on branches with more complex enamel and weaker purifying selection (higher dN/dS) occurs on branches with less complex enamel or enamelless teeth. As odontocetes diversified into a variety of feeding modes, in particular, the suction capture of prey, a reduced reliance on the dentition for prey capture resulted in the relaxed selection of genes that are critical to enamel development. Full article

Developing different robotic platforms for farm operations is vital to addressing the increasing world population. A harvesting robot significantly increases a farm’s productivity while farmers focus on other relevant farm operations. From the literature, it could be summarized that the design concepts of the harvesting mechanisms were categorized as grasping and cutting, vacuum suction plucking systems, twisting and plucking mechanisms, and shaking and catching. Meanwhile, robotic system components include the mobile platform, manipulators, and end effectors, sensing and localization, and path planning and navigation. The robotic system must be cost-effective and safe. The findings of this research could contribute to the design process of developing a harvesting robot or developing a harvesting module that can be retrofitted to a commercially available mobile platform. This paper provides an overview of the most recent harvesting robots’ different concept designs and system components. In particular, this paper will highlight different agricultural ground mobile platforms and their associated mechanical design, principles, challenges, and limitations to characterize the crop environment relevant to robotic harvesting and to formulate directions for future research and development for cotton harvesting platforms. Full article

Soft Pneumatic-Network (Pneu-Net) Actuators (SPAs) have been used extensively in making soft grippers, due to their simple driving forms and large bending deformation. However, the capabilities of the regular SPAs in complex soft gripping application environments are alone insufficient. This work, thus, proposes a modular soft gripper that combines the functionalities of regular and herringbone actuators. The bending deformation characteristics of the two actuators under pneumatic pressures are verified by finite element (FE) simulations and experiments. The functional characteristics of the two actuators are investigated experimentally through a series of methods including the blocking force test, lifting test, grasping strength test, and suction force test. The experimental results show that the regular actuator has the advantages of greater longitudinal bending deformation and higher blocking force; while, the herringbone actuator has better lifting stability and grasping strength due to its conformal deformations both in longitudinal and transverse directions. In addition, the vacuum experiments demonstrate that the actuators can lift heavy plate-like objects through vacuum suction. Based on the functional behaviors of the two actuators, the proposed modular gripper is loaded onto automatic equipment, and the gripper is tested to hook, grasp, or lift various objects with different shapes, sizes, and weights. In essence, the modular and multi-functional characteristics of the design make it a promising candidate for relatively complex and advanced gripping applications. Full article

In nature, aquatic organisms have evolved various attachment systems, and their attachment ability has become a specific and mysterious survival skill for them. Therefore, it is significant to study and use their unique attachment surfaces and outstanding attachment characteristics for reference and develop new attachment equipment with excellent performance. Based on this, in this review, the unique non-smooth surface morphologies of their suction cups are classified and the key roles of these special surface morphologies in the attachment process are introduced in detail. The recent research on the attachment capacity of aquatic suction cups and other related attachment studies are described. Emphatically, the research progress of advanced bionic attachment equipment and technology in recent years, including attachment robots, flexible grasping manipulators, suction cup accessories, micro-suction cup patches, etc., is summarized. Finally, the existing problems and challenges in the field of biomimetic attachment are analyzed, and the focus and direction of biomimetic attachment research in the future are pointed out. Full article

This paper presents an autonomous grasping approach for complex-shaped objects using an anthropomorphic robotic hand. Although human-like robotic hands have a number of distinctive advantages, most of the current autonomous robotic pickup systems still use relatively simple gripper setups such as a two-finger gripper or even a suction gripper. The main difficulty of utilizing human-like robotic hands lies in the sheer complexity of the system; it is inherently tough to plan and control the motions of the high degree of freedom (DOF) system. Although data-driven approaches have been successfully used for motion planning of various robotic systems recently, it is hard to directly apply them to high-DOF systems due to the difficulty of acquiring training data. In this paper, we propose a novel approach for grasping complex-shaped objects using a high-DOF robotic manipulation system consisting of a seven-DOF manipulator and a four-fingered robotic hand with 16 DOFs. Human demonstration data are first acquired using a virtual reality controller with 6D pose tracking and individual capacitive finger sensors. Then, the 3D shape of the manipulation target object is reconstructed from multiple depth images recorded using the wrist-mounted RGBD camera. The grasping pose for the object is estimated using a residual neural network (ResNet), K-means clustering (KNN), and a point-set registration algorithm. Then, the manipulator moves to the grasping pose following the trajectory created by dynamic movement primitives (DMPs). Finally, the robot performs one of the object-specific grasping motions learned from human demonstration. The suggested system is evaluated by an official tester using five objects with promising results. Full article