Search Results (31)

Agriculture is facing increasing challenges due to labor shortages, rising productivity demands, and the need to operate in unstructured environments. Robotics, particularly soft robotics, offers promising solutions for automating delicate tasks such as fruit harvesting. While numerous soft grippers have been proposed, most focus on grasping and lack the capability to detach fruits with rigid peduncles, which require cutting. This paper presents a novel modular hexagonal soft gripper that integrates soft pneumatic actuators, embedded mechano-optical force sensors for real-time contact monitoring, and a self-centering iris-type cutting mechanism. The entire system is 3D-printed, enabling low-cost fabrication and rapid customization. Experimental validation demonstrates successful harvesting of bell peppers and identifies cutting limitations in tougher crops such as aubergine, primarily due to material constraints in the actuation system. This dual-capability design contributes to the development of multifunctional robotic harvesters capable of adapting to a wide range of fruit types with minimal requirements for perception and mechanical reconfiguration. Full article

This paper presents a Self-Learning Robotic System (SLRS) for healthcare assistance using Deep Imitation Learning (DIL). The proposed SLRS solution can observe and replicate human demonstrations, thereby acquiring complex skills without the need for explicit task-specific programming. It incorporates modular components for perception (i.e., advanced computer vision methodologies), actuation (i.e., dynamic interaction with patients and healthcare professionals in real time), and learning. The innovative approach of implementing a hybrid model approach (i.e., deep imitation learning and pose estimation algorithms) facilitates autonomous learning and adaptive task execution. The environmental awareness and responsiveness were also enhanced using both a Convolutional Neural Network (CNN)-based object detection mechanism using YOLOv8 (i.e., with 94.3% accuracy and 18.7 ms latency) and pose estimation algorithms, alongside a MediaPipe and Long Short-Term Memory (LSTM) framework for human action recognition. The developed solution was tested and validated in healthcare, with the aim to overcome some of the current challenges, such as workforce shortages, ageing populations, and the rising prevalence of chronic diseases. The CAD simulation, validation, and verification tested functions (i.e., assistive functions, interactive scenarios, and object manipulation) of the system demonstrated the robot’s adaptability and operational efficiency, achieving an 87.3% task completion success rate and over 85% grasp success rate. This approach highlights the potential use of an SLRS for healthcare assistance. Further work will be undertaken in hospitals, care homes, and rehabilitation centre environments to generate complete holistic datasets to confirm the system’s reliability and efficiency. Full article

This study proposes a GPU-accelerated Position-Based Dynamics (PBD) system for realistic and interactive cloth simulation in Extended Reality (XR) environments, and comprehensively evaluates its performance and functional capabilities on standalone XR devices, such as the Meta Quest 3. To overcome the limitations of traditional CPU-based physics simulations, we designed and optimized highly parallelized algorithms utilizing Unity’s Compute Shader framework. The proposed system achieves real-time performance by implementing efficient collision detection and response handling with complex environmental meshes (RoomMesh) and dynamic hand meshes (HandMesh), as well as capsule colliders based on hand skeleton tracking (OVRSkeleton). Performance evaluations were conducted for both single-sided and double-sided cloth configurations across multiple resolutions. At a 32 × 32 resolution, both configurations maintained stable frame rates of approximately 72 FPS. At a 64 × 64 resolution, the single-sided cloth achieved around 65 FPS, while the double-sided configuration recorded approximately 40 FPS, demonstrating scalable quality adaptation depending on application requirements. Functionally, the GPU-PBD system significantly surpasses Unity’s built-in Cloth component by supporting double-sided cloth rendering, fine-grained constraint control, complex mesh-based collision handling, and real-time interaction with both hand meshes and capsule colliders. These capabilities enable immersive and physically plausible XR experiences, including natural cloth draping, grasping, and deformation behaviors during user interactions. The technical advantages of the proposed system suggest strong applicability in various XR fields, such as virtual clothing fitting, medical training simulations, educational content, and interactive art installations. Future work will focus on extending the framework to general deformable body simulation, incorporating advanced material modeling, self-collision response, and dynamic cutting simulation, thereby enhancing both realism and scalability in XR environments. Full article

To address the challenge of low operational efficiency in apple harvesting robots, this study proposes an adaptive grasping sequence planning methodology that combines Self-Organizing Maps (SOMs) and genetic algorithms (GAs). The proposed adaptive SOM—GA hybrid algorithm aims to minimize cycle time by optimizing the path planning between the fruit detection and grasping phases. First of all, we propose a density-aware adaptive mechanism that dynamically adjusts planning strategies based on fruit count thresholds. In addition, the proposed grasping sequence planning framework for high-density dwarf cultivation (HDDC) orchards is validated through threshold sensitivity analysis and empirical analysis of over 500 real-world fruit distribution samples. Finally, comparative experiments demonstrate that our proposed method reduces path length in high-density scenarios. Statistical analysis reveals a bimodal fruit distribution, which aligns the algorithm’s adaptive thresholds with real-world operational demands. These advancements improve theoretical research and enhance the commercial viability in agricultural robotics. Full article

Soft pneumatic robot-arm end-effectors can facilitate adaptive architectural fabrication and building construction. However, conventional pneumatic grippers often suffer from air leakage and tear, particularly under prolonged grasping and inflation-induced stress. To address these challenges, this study suggests an enhanced anthropomorphic gripper by integrating a pre-stressed reversible mechanism (PSRM) and a novel self-healing material (SHM) polyborosiloxane–Ecoflex™ hybrid polymer (PEHP) developed by the authors. The results demonstrate that PSRM finger grippers can hold various objects without external pressure input (12 mm displacement under a 1.2 N applied), and the SHM assists with recovery of mechanical properties upon external damage. The proposed robotic hand was evaluated through real-world construction tasks, including wall painting, floor plastering, and block stacking, showcasing its durability and functional performance. These findings contribute to promoting the cost-effective deployment of soft robotic hands in robotic construction. Full article

The coupled-adaptive underactuated finger offers two motion modes: pre-grasping and self-adaptive grasping. It can execute anthropomorphic pre-grasp motions before the proximal phalanx contacts an object and transitions to adaptive enveloping once contact occurs. The key to designing a coupled-adaptive finger lies in its configuration and parameter, which are crucial for achieving a more human-like design for the prosthetic hand. Thus, this paper proposes a configuration topology and parameter optimization design method for a three-joint coupled-adaptive underactuated finger. The finger mechanism utilizes a combination of prismatic pairs and a compression spring to facilitate the transition between coupled motion and adaptive motion. This enables the underactuated finger to perform coupled movements in free space and adaptive grasping motions once it makes contact with an object. Furthermore, this paper introduces a finger linkage parameter optimization method that takes the joint motion angles and overall dimensions as constraints, aiming to linearize the joint coupling motion ratios as the primary optimization objective. The design method proposed in this paper not only presents a novel linkage mechanism but also outlines and compares its isomorphic types. Furthermore, the optimization results provide an accurate maximum motion value for the finger. Full article

The demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also subsequent assembly stages. Corrective strategies used to compensate for misalignment can increase cycle times or rely on pre-labeled datasets, offline training, and validation processes, delaying deployment and limiting adaptability in dynamic industrial environments. Our main contribution is an online self-supervised learning method that automates data collection, training, and evaluation in real time, eliminating the need for offline processes. Building on this, our system collects real-time data during each assembly cycle, using corrective strategies to adjust the data and autonomously labeling them via a self-supervised approach. It then builds and evaluates multiple regression models through an auto machine learning implementation. The system selects the best-performing model to correct the misalignment and dynamically chooses between corrective strategies and the learned model, optimizing the cycle times and improving the performance during the cycle, without halting the production process. Our experiments show a significant reduction in the cycle time while maintaining the performance. Full article

This paper proposes an underactuated dexterous hand with novel bidirectional self-locking joints (BSJs) that enable multiple fingertip motion trajectories. The BSJ design integrates a locking wheel, rack, finger side walls, and a self-holding electromagnetic actuator, combining rack-and-pinion transmission with friction self-locking principles. Building on the BSJ concept, an underactuated dexterous hand is developed. The study begins with an analysis of BSJ’s deviation angle, establishing the minimum deviation angle critical to its operation. A detailed mechanical model of a BSJ is formulated, and its parameters are quantitatively analyzed to determine a safety static friction coefficient (0.177). Five distinct finger motion modes are designed and kinematic analysis focuses on the index finger and the generation of 57 unique fingertip active motion trajectories. Experimental validation included single finger performance tests that confirmed the diversity of fingertip trajectories and the hand’s ability to withstand loading in both forward and reverse directions. Through envelope and precision grasping experiments, the dexterous hand demonstrated its adaptability and ability to grasp objects of various sizes and shapes, such as strawberries, apples, student ID cards, and water bottles. This capability underscores its potential for a wide range of applications, from prosthetic hands for rehabilitation, where precision and adaptability are key, to robotic hands in industrial automation, offering flexibility in diverse tasks. Full article

Transformer models have emerged as frontrunners in the field of natural language processing, primarily due to their adept use of self-attention mechanisms to grasp the semantic linkages between words in sequences. Despite their strengths, these models often face challenges in single-task learning scenarios, particularly when it comes to delivering top-notch performance and crafting strong latent feature representations. This challenge is more pronounced in the context of smaller datasets and is particularly acute for under-resourced languages such as Arabic. In light of these challenges, this study introduces a novel methodology for text classification of Arabic texts. This method harnesses the newly developed Reverse Positional Encoding (RPE) technique. It adopts an inductive-transfer learning (ITL) framework combined with a switching self-attention shared encoder, thereby increasing the model’s adaptability and improving its sentence representation accuracy. The integration of Mixture of Experts (MoE) and RPE techniques empowers the model to process longer sequences more effectively. This enhancement is notably beneficial for Arabic text classification, adeptly supporting both the intricate five-point and the simpler ternary classification tasks. The empirical evidence points to its outstanding performance, achieving accuracy rates of 87.20% for the HARD dataset, 72.17% for the BRAD dataset, and 86.89% for the LABR dataset, as evidenced by the assessments conducted on these datasets. Full article

The modern lifestyle of humans is leading to a limited exposure to nature. While several wild species are adapting and thriving in anthropic environments, natural history knowledge is declining, and positive attitudes and behaviours towards nature are facing challenges. Because anticipating attitudes and engendering broad-based support for nature-related measures requires a good grasp of social contexts, we set out to evaluate the sociodemographic factors driving the perception, attitudes towards, and natural history knowledge of a keystone species—the European hedgehog. In 2022, we conducted a questionnaire answered by 324 Portuguese adults. We found generally positive feelings and attitudes towards this species. A higher degree of academic qualifications and previous personal experience with the species seem to play a role in (i) people’s perception about human impacts on hedgehogs and (ii) positive attitudes, especially during encounters where the animals were in difficulty. Despite this, the extent of natural history knowledge was low overall, and the study population was self-aware of this. Our insights underline the need to tailor educational programmes if we are to encourage people to re-establish meaningful connections with nature, to foster social support for biodiversity stewardship, and to implement the One Health approach in a way that resonates with distinct social groups. Full article

In this paper, a back-drivable and miniature rotary series elastic actuator (RSEA) is proposed for robotic adaptive grasping. A compact arc grooves design has been proposed to effectively reduce the dimension of the RSEA system. The elastic elements could be reliably embedded in the arc grooves without any additional installation structures. The whole RSEA system is characterized as compact, miniature, and modular. The actuating force is controlled via a PI controller by tracking the deformation trajectory of the elastic elements. An underactuated finger mechanism has been adopted to investigate the effectiveness of the RSEA in robotic adaptive grasping. Results reveal that the underactuated finger mechanism could achieve adaptive grasping via the RSEA in a back-drive approach without the requirement of a fingertip force sensor. The RSEA could also exhibit an actuating compliance and a self-sensing characteristic. The actuating compliance characteristic helps in in guaranteeing the safety of human–robot interaction. The RSEA could estimate the external disturbance due to its self-sensing characteristic, which has the potential to replace the fingertip force sensor in grasping force perception applications. Full article

The climate is changing worldwide and, with it, living conditions are changing to varying degrees. As a result, students need to be equipped with a wide range of competences in order to deal with the problems of climate change. In order to successfully acquire these competences, different methods are used in lesson planning. Therefore, in order to achieve the goal of raising awareness in Education for Sustainable Development, large-scale methodological learning form of the proposed model experiment will be used. For this purpose, it is necessary to first develop scientific knowledge about climate change and then present individual climate adaptation strategies using the example of climate-efficient buildings. The structure of the topic is grasped, and the didactically reduced core contents of the subject-specific scientific basics represent the specialist knowledge to be conveyed. This is followed by the construction of a self-designed model that is optimally adapted to the teaching of the subject knowledge. The subsequent series of measurements serves to evaluate the suitability of the model for the intended purpose of achieving a successful learning process under the aspects of quality criteria and practicability. The proposed model experiment has been found to be suitable and worthwhile for this purpose. Full article

Parallel pinch is an important grasp method. The end phalanx of the traditional parallel pinch and self-adaptive gripper moves in an arc trajectory, which requires the auxiliary lifting motion of the industrial manipulator, which is inconvenient to use. To solve this problem, a novel robot finger is designed and implemented—Hoecken’s finger. In this finger, the Hoecken linkage mechanism is used to realize the straight-line trajectory of the end joint, the differential mechanism set on the surface of the phalanxes is used to realize the shape self-adaptation of the first and second phalanxes, and the parallel four-bar linkage in series is used to realize the attitude keeping, thus comprehensively realizing the underactuated gripper driven by a single motor. After analyzing the grasp force and grasp motion of Hoecken’s fingers, the optimized parameters are obtained, and the Hoecken’s gripper is developed. The experimental results show that the gripper can realize the self-adaptive grasp function of straight parallel pinch, the grasp is stable, and the grasp range is large. It can be applied to more scenes that need to grasp objects. Full article

Tendon transfer surgery is often used to restore hand grasp function following high median-ulnar nerve palsy. This surgery typically reroutes and sutures the tendon of the extensor carpi radialis longus (ECRL) muscle to all four flexor digitorum profundus (FDP) tendons of the hand, coupling them together. This makes it difficult to grasp irregularly shaped objects. We propose inserting a novel implantable passive device between the FDP tendons to surgically construct a differential mechanism, enabling the fingers to individually adapt to the irregular contours during grasping. These passive implants with no moving parts are fabricated from biocompatible materials. We tested the implants’ ability to create differential flexion between the index and middle fingers when actuated by a single muscle in two human cadaver hands using a computerized closed-loop control paradigm. In these cadaveric models, the implants enabled significantly more differential flexion between the index and middle fingers for a wide range of donor tendon tensions. The implants also redistributed fingertip forces between fingers. When grasping uneven objects, the difference in contact forces between fingers reduced by nearly 23% compared to the current suture-based surgery. These results suggest that self-adaptive grasp is possible in tendon transfers that drive multiple distal flexor tendons. Full article

The current underactuated robot hands use a single actuator to drive multiple degrees of freedom, enabling them to perform grasping functions. This paper design a multi-mode compound grasping robot finger driven by linkage, called MCG hand. The MCG hand includes a base, two motors, three phalanx, multiple shafts, two motors, two driving wheels, four linkages, three springs, and two limit blocks. This unique design allows the MCG finger to perform various grasping modes, such as parallel, coupling, middle, and distal phalanx self-adaptive, proximal, and distal gesture-changeable modes, as well as their combinations. The device can independently control the rotation of the proximal phalanx and the distal joint and realize the parallel pinching action of the distal phalanx. It can also realize the coupling function of the proximal and distal phalanx. It has automatic adaptability to objects of different shapes and sizes. Furthermore, the MCG finger provides enveloping grasping with multiple contact points, resulting in a more stable grip. The easy switching between modes through simple control, along with its wide application range and low manufacturing and maintenance costs, make the MCG hand a versatile solution for various applications. Full article