Search

• A deep-learning-based flexible four-finger gripper grasping detection method. • A tool for marking pixel-level labels. • A powerful neural network. • Capable of grasping a wide variety of objects. The flexible four-finger gripper, as a specialized robotic end-effector, is highly valued for its ability to passively adapt to the shape of objects and perform non-destructive grasping. However, the development of grasping detection algorithms for flexible four-finger grippers remains relatively unexplored. This paper addresses the unique characteristics of the flexible four-finger gripper by proposing a grasping detection method based on deep learning. Firstly, the Acute Angle Representation model (AAR-model), which is based on the structure of the flexible four-finger gripper and consists of grasp points and angles, is designed as the grasping representation model that reduces unnecessary rotations of the gripper and improves its versatility in grasping objects. Then, the Flexible Gripper Adaptive Attribute model (FGAA-model) is proposed to represent the grasping attributes of objects, calculate the grasp angles that meet the criteria of the AAR-model, and aggregate the AAR-models on the image data into a unified set, thereby circumventing the time-consuming process of pixel-level annotation. Finally, the Adaptive Grasping Neural Net (AGNN), which is based on Adaptive Feature Fusion and the Grasp Aware Network (AFFGA), is introduced by eliminating redundant network detection headers, fusing color and depth images as inputs, and incorporating a Series Atrous Spatial Pyramid (SASP) structure to produce more accurate grasp poses. Our method not only attains a remarkable accuracy of 97.62% on the Cornell dataset but also swiftly completes grasping detection within 25 ms. In practical robotic arm grasping tests, where a robot is outfitted with a flexible four-finger gripper, it successfully grasps unknown objects with a 96% success rate. These results underscore the reliability and real-time performance of our method, significantly enhancing the gripper's adaptability and precision when handling objects of varying sizes and shapes. This advancement provides a powerful technical solution for robots utilizing flexible four-finger grippers, enabling autonomous, real-time, and highly accurate grasping maneuvers. Moreover, it addresses the persistent challenge of the scarcity of efficient grasping detection techniques tailored for flexible four-finger grippers. [ABSTRACT FROM AUTHOR]

Behavior trees (BTs) are increasingly popular in the robotics community. Yet in the growing body of published work on this topic, there is a lack of consensus on what to measure and how to quantify BTs when reporting results. This is not only due to the lack of standardized measures, but due to the sometimes ambiguous use of definitions to describe BT properties. This work provides a comprehensive overview of BT properties the community is interested in, how they relate to each other, the metrics currently used to measure BTs, and whether the metrics appropriately quantify those properties of interest. Finally, we provide the practitioner with a set of metrics to measure, as well as insights into the properties that can be derived from those metrics. By providing this holistic view of properties and their corresponding evaluation metrics, we hope to improve clarity when using BTs in robotics. This more systematic approach will make reported results more consistent and comparable when evaluating BTs. [ABSTRACT FROM AUTHOR]

• Interaction of human and socially assistive robot can have applicability in actual settings, and adoption to function in human environment for Alzheimer's disease. • To achieve this, the overall review revealed that there are still several technical challenges that must be addressed in future advancements before being integrated in real life of individuals with Alzheimer's disease. • The results will help move towards the establishment of best practices for the development of human and socially assistive robot interaction for Alzheimer's disease and, in turn, help enhance the experience of people suffering from this disease. The most common form of dementia, Alzheimer's Disease (AD), is challenging for both those affected as well as for their care providers, and caregivers. Socially assistive robots (SARs) offer promising supportive care to assist in the complex management associated with AD. To conduct a scoping review of published articles that proposed, discussed, developed or tested SAR for interacting with AD patients. We performed a scoping review informed by the methodological framework of Arksey and O'Malley and adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist for reporting the results. At the identification stage, an information specialist performed a comprehensive search of 8 electronic databases from the date of inception until January 2022 in eight bibliographic databases. The inclusion criteria were all populations who recive or provide care for AD, all interventions using SAR for AD and our outcomes of inteerst were any outcome related to AD patients or care providers or caregivers. All study types published in the English language were included. After deduplication, 1251 articles were screened. Titles and abstracts screening resulted to 252 articles. Full-text review retained 125 included articles, with 72 focusing on daily life support, 46 on cognitive therapy, and 7 on cognitive assessment. We conducted a comprehensive scoping review emphasizing on the interaction of SAR with AD patients, with a specific focus on daily life support, cognitive assessment, and cognitive therapy. We discussed our findings' pertinence relative to specific populations, interventions, and outcomes of human-SAR interaction on users and identified current knowledge gaps in SARs for AD patients. [ABSTRACT FROM AUTHOR]

• LegUp robot enables the motion of the lower limb in the sagittal and coronal planes. • The mathematical models for legup are representative for the rehabilitation task. • Numerical optimizations lead to a singularity-free operational workspace. The paper presents the mathematical modeling and analysis of LegUp, a novel parallel robotic system for lower limb rehabilitation of bedridden patients. The operational workspace of the robotic system is defined based on a set of parameters that describe the motion of the lower limb joints, which is natural in the rehabilitation task. To comply with this representation of the operational workspace, the parallel robot kinematic models describe the dependency between the robotic system actuators and the lower limb joints. Furthermore, the singularity analysis is achieved in the joint space, which shows whether the operational workspace is singularity-free. To achieve a feasible mechanical design for the prescribed operational workspace and to ensure safe operation, the design parameters of the parallel robotic system are determined based on a multi-objective optimization problem. Numerical simulations show that the operational workspace is singularity-free for the selected design parameters, which are then used to construct the experimental model of LegUp. [ABSTRACT FROM AUTHOR]

We propose a test-time adaptation for 6D object pose tracking that learns to adapt a pre-trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a model that extracts 3D keypoints. Given an RGB-D image and the mask of a target object for each frame, the proposed model consists of the self- and cross-attention modules to produce the features that aggregate the information within and across frames, respectively. By using the keypoints detected from the features for each frame, we estimate the pose changes between two frames, which enables 6D pose tracking when the 6D pose of a target object in the initial frame is given. Our model is first trained in a source domain, a category-level tracking dataset where the ground truth 6D pose of the object is available. To deploy this pre-trained model to track novel objects, we present a test-time adaptation strategy that trains the model to adapt to the target novel object by self-supervised learning. Given an RGB-D video sequence of the novel object, the proposed self-supervised losses encourage the model to estimate the 6D pose changes that can keep the photometric and geometric consistency of the object. We validate our method on the NOCS-REAL275 dataset and our collected dataset, and the results show the advantages of tracking novel objects. The collected dataset and visualisation of tracking results are available: https://qm-ipalab.github.io/TA-6DT/ • Test-time adaptation strategy for tracking novel objects. This strategy reduces the dependency on annotated data by introducing self-supervised loss functions based on photometric and geometric consistency. By leveraging RGB-D videos and initial pose information, our method enables accurate and robust 6D pose tracking for objects not encountered during training. • We propose a new model that incorporates transformers, enabling the model to find dependencies and relationships between keypoints. This design facilitates the accurate matching of 3D keypoints, crucial for robust 6D pose tracking. • We evaluate the performance of our method on a set of novel objects that we collected by using a robotic arm. This evaluation allows us to assess the ability of our method to achieve accurate 6D pose tracking for a wide range of novel objects. [ABSTRACT FROM AUTHOR]

The relationship between artificial entities' human likeness and aesthetic preference is thought to be best modelled by an N -shaped cubic "uncanny valley" function, which however suffers from conceptual criticisms and lack of parsimony. Here it is argued that uncanniness effects may instead be modelled by a linear function of deviation moderated by perceptual specialization. The two models are compared in an experiment with five incrementally distorted face types (cartoon, CG, drawing, real, robot). Recognition performance for upright and inverted faces were used as a specialization measure. Specialization significantly moderated the linear effect of distortion on uncanniness, and could explain the data better than a conventional uncanny valley. The uncanny valley may thus be better understood as a moderated linear function of specialization sensitizing the uncanniness of deviating stimuli. This simpler yet more accurate model is compatible with neurocognitive theories and can explain uncanniness effects beyond the conventional uncanny valley. • Face realism affects both specialization and deviation sensitivity. • Specialization moderates the effect of deviation on uncanniness in faces. • This moderated linear function explains uncanniness better than a cubic "uncanny valley" model. • Parsimony, accuracy, generalizability, and plausibility of the moderation model over the uncanny valley are discussed. [ABSTRACT FROM AUTHOR]

Little is known about how children perceive, trust and learn from social robots compared to humans. The goal of this study was to compare a robot and a human agent in a selective trust task across different combinations of reliability (both reliable, only human reliable, or only robot reliable). 111 children, aged 3 to 6 years, participated in an online study where they viewed videos of a human and a robot labelling both familiar and novel objects. We found that, although children preferred to endorse a novel object label from the agent who previously labelled familiar objects correctly, when both the human and the robot were reliable they were biased more towards the robot. Their social evaluations also tended much more strongly towards a general robot preference. Children's conceptualisations of the agents making a mistake also differed, such that an unreliable human was selected as doing things on purpose, but not an unreliable robot. These findings suggest that children's perceptions of a robot's reliability are separate from their evaluation of its desirability as a social interaction partner and its perceived agency. Further, they indicate that a robot making a mistake does not necessarily reduce children's desire to interact with it as a social agent. • 3–6 year old children prefer a reliable robot over a reliable human. • Children evaluate robot competency separately to social and agency judgements. • Humans are more likely to be seen as making a mistake on purpose than a robot. [ABSTRACT FROM AUTHOR]

The theory of Enactive Inference was proposed by Karl Friston and his colleagues to explain how the brain infers knowledge about the world through the subject's interactive experiences. Sensorimotor states induce perturbations in neural activity, and the brain infers hypothetical causes in the world that may explain these perturbations. This article aims to reconcile this neuroscience theory with computer science and artificial-intelligence theories wherein artificial agents receive input data derived from the environment's state and infer internal data structures used to guide decisions. Two critical challenges arise in both the agent's active role and the inference algorithm's scalability as the environment's complexity increases. To address these challenges, we formalize artificial enactive inference through a new Spatial Enactive Markov Decision Process (SEMDP) model. This model rests on low-level control loops enacted in a three-dimensional Euclidean space containing objects. Based on the SEMDP, we present a proof-of-concept cognitive architecture and an experiment to demonstrate the transcription of the theory of enactive inference into the domain of artificial intelligence and robotics. [ABSTRACT FROM AUTHOR]

The rapid growth of electric vehicles and advancements in self-driving technologies necessitate the development of specialized infrastructure to support autonomy. Accurate pose estimation of electric vehicles sockets is crucial for efficient and reliable plug-in charging operations. This process is inherently complex due to several factors, including the textureless black color of the socket, environment-dependent lighting conditions, and the presence of small geometrical features. To address these challenges, we propose a comprehensive method that combines Deep Neural Network-based pose estimation and auto-annotation methodology. Auto-annotation facilitates the generation of diverse training data, enhancing the accuracy, robustness, and generalization capabilities of the deep learning model. The advantages of the proposed method were evaluated through a comprehensive series of experiments conducted in both simulation and controlled laboratory settings. In our evaluation, we implemented a robotic charging system consisting of a manipulator with a charging plug and a hand-eye monocular camera and conducted plug-in testing in three scenarios: (A) uniform lighting conditions, (B) dark, and (C) highly uneven illumination of the socket surface. The experimental results show that our method can achieve precise and reliable pose estimation with mean absolute errors less than 0.73 mm and 0.82 deg, and an average Insertion Success Rate of over 97.5%. • DNN-based method for accurate and robust socket pose estimation of electric vehicle. • Methodology for fast and accurate dataset annotation. • Unique application of Keypoint R-CNN detector, SQPnP, and RANSAC methods. • Validation of the designed method in diverse lighting conditions. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence (AI) has the potential to revolutionise the pre-operative, intra-operative and post-operative stages of orthopaedic surgery. We conduct a systematic review and meta-analysis to investigate the role and effectiveness of AI in Orthopedic surgery. We compare the outcomes of AI-assisted and conventional surgery by focusing on the implementation of AI tools in the prediction, diagnosis and robot-assisted surgery. The results of the review and meta-analysis showed high accuracy in prediction outcomes, diagnosis and classification based on medical image analysis. However, the meta-analysis revealed longer operative times with robot-assisted surgery. Additionally, while robotics achieved enhanced implant positioning accuracy, definitive advantages in functional outcomes over conventional surgery were not observed. Future work should focus on extensive follow-up to validate the long-term advantages of AI-assisted procedures in orthopaedic surgery. • A review of application areas of artificial intelligence (AI) in Orthopedic surgery is conducted. • Potential application of AI in the preoperative, intraoperative, and postoperative stages are identified. • A meta-analysis was carried out to compare the performances of AI-assisted orthopedic surgery with conventional approach. • Challenges are identified and avenues for future research are highlighted. [ABSTRACT FROM AUTHOR]

The convolutional neural networks commonly deployed for semantic understanding of visual inspection data can, in general, learn robust spatial features. However, they lack the ability to capture temporal dependencies that characterize the video data collected by various robotic inspection systems. As a result, they are found lacking in dealing with various challenges arising from cross-view illumination variation, perspective difference, scale change, background clutter, and occlusion. Their performance is further deteriorated by motion blur and other distortions induced by rapid camera movement. This study aims to address this challenge by extending the task of visual scene understanding from the still image domain to the video domain by incorporating cross-frame information fusion. A deep end-to-end network is developed by integrating an encoder–decoder-based convolutional neural network with a long short-term memory-based recurrent neural network for pixel-level semantic labeling of sequential visual inspection data. The proposed multishot architecture can jointly learn discriminative fusion features leading to a rich understanding of the complex spatiotemporal dynamics. The proposed approach is validated with two case studies involving automatic structural element segmentation in robotic building and bridge inspection videos. Two different multishot fusion techniques are suggested leveraging sequence-to-one and sequence-to-sequence architectures. Additionally, two different fusion schemes based on the sum-of-scores and Bayesian updating rules are examined to aggregate multiple label maps produced at each time step by an overlapping sliding window-based inference scheme. A comprehensive performance evaluation indicated that multishot fusion could enhance the intersection over union (IoU) score by 4.6% and 13.3% for building and bridge component segmentation tasks, respectively, compared to a baseline single-shot approach. [ABSTRACT FROM AUTHOR]

A series of liquid crystal elastomer-based printed electronic devices has been innovatively crafted through modifying screen-printing patterns. [Display omitted] • A printed liquid crystal elastomer soft actuator with multi-stimuli responsiveness and self-sensing capabilities is achieved. • A printed liquid crystal elastomer near-infrared light array sensor is fabricated. • A series of printed functional devices are fabricated through simple modifications of the printing patterns. Liquid crystal elastomers (LCEs) are valuable in soft actuators, sensors and other emerging fields. However, it is still a huge challenge to build high-performance LCE-based functional devices in a simple and fast way to achieve the orderly and patterned integration of multiple functional layers and LCE. Herein, screen-printing technology is used to realize the multi-layer pattern deposition of silver fractal dendrites conductive ink (with excellent Joule heating effect and strain-sensing function) and carbon black conductive ink (with photothermal conversion ability) on the surface of LCE. A series of LCE-based electronic devices are prepared through customized printing patterns. The as-obtained actuator possesses excellent electric actuating performance (bending angle of 102° at 200 mA) and self-sensing function (maximum relative resistance changes of −55.0%), and also exhibits NIR light-driven self-sensing bending actuation behavior (bending angle of 81° at 1.43 W/cm2), which can be used to control the robotic arm. The as-printed NIR light sensing array system can accurately sense the intensity, spot size and position of NIR light, showing good application potential in the field of unmanned aerial vehicle flight safety. This work provides a new strategy for the efficient preparation of LCEs-based flexible electronics. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative digital workflow for printability checking and prefabrication in robotic construction 3D printing based on Artificial Intelligence (AI) planning techniques. The proposed method generates operational sequences for a robotic manipulator tasked with concrete 3D printing by utilizing Planning Domain Definition Language (PDDL) 2.1-based AI planners. The planned sequences consider diverse geometry specifications, aligning with printability checks and prefabrication requisites. The sequences can then be executed in a robotic simulation environment, allowing operators to assess the 3D printing process in every aspect before real-world deployment, and potentially avoiding costly mistakes and the waste of resources. Compared to existing methods, the use of AI planning makes our approach more modular and easy to adapt across a variety of robotic platforms, diverse designs, materials, and printing conditions; and it is released as open-source software to the benefit of the community. The proposed method was tested by processing objects with multiple geometries and a varying number of printing layers, and by employing two different PDDL planners. Results prove the viability of the approach but also hint at possible scalability limitations for complex geometries that involve a large number of edges to be printed. [ABSTRACT FROM AUTHOR]

This article introduces a novel collaborative optimal motion planning framework for parallel aerial 3D printing. The proposed novel framework is efficiently capable of handling conflicts between the utilized Unmanned Aerial Vehicles (UAVs), as they follow predefined paths, allowing for a seamless enhancement of aerial 3D printing capabilities by employing multiple UAVs to collaborate in a parallel printing process. The established approach ingeniously formulates UAVs' motion planning as a multi-constraint optimization problem, ensuring minimal adjustments to their velocities within specified limits. This guarantees smooth and uninterrupted printing while preventing collisions and adhering to the requirements of aerial printing. To substantiate the effectiveness of our proposed motion planning algorithm, an extensive array of simulation studies have been undertaken, encompassing scenarios where multiple UAVs engage in the fabrication of diverse construction shapes. The overall novel concept is being extensively validated in simulations, while the obtained results promise for enhancing the viability and advancing the landscape of aerial additive manufacturing. • Handling conflicts of collaborative aerial 3D Printing UAVs. • UAVs' motion planning as a multi-constraint optimization problem (MIP). • Smooth and uninterrupted parallel printing while preventing collisions. [ABSTRACT FROM AUTHOR]

It is well-known that fish have the ability to adapt to complex water flow environments. However, most research on bionic robotic fishes has focused on static water conditions. There remains a lot of room on the control of robotic fish in water flow. While static flow serves as the fundamental element of water flow, this paper seeks to address the issue of target point approaching control for bionic robotic fish in static water environments. Recognizing the challenges posed by the proportional–integral–derivative (PID) control and model predictive control (MPC) methods encountering the complex non-linear system, this study proposes a hybrid control approach that based on model predictive decision-making strategy. The proposed hybrid control method is effective in guiding robotic fish towards target points in both static water and static flow environments and achieving rapid system convergence under the premise of significantly reducing the calculation error. This work provides a potential reference for the control of bionic robotic fish in static flow. [Display omitted] • Complete the target point approaching task of bionic robot fish in different water fields, including static water and static flow. • A dynamic model of a single joint robot fish considering the influence of the flow. • A hybrid controller combining PID controller and model predictive controller. • Comparative target point approaching experiments on PID control, MPC control and hybrid control. [ABSTRACT FROM AUTHOR]

• A novel dual-channel GC × GC–TOFMS instrument equipped with an online water sample pretreatment platform for online monitoring of both VOCs and SVOCs in water was fabricated for the first time. • The pretreatment methods of headspace and liquid–liquid extraction, for VOCs and SVOCs, respectively, were integrated into a single pretreatment platform and conducted automatically and online. • 159 types of target VOCs and SVOCs were quantitatively analyzed, with a satisfying result. Screening of nontarget pollutants is conducted simultaneously. The monitoring of organic compounds in aquatic matrices poses challenges due to its complexity and time-intensive nature. To address these challenges, we introduce a novel approach utilizing a dual-channel mono (1D) and comprehensive two-dimensional (2D) gas chromatography coupled with time-of-flight mass spectrometry (GC × GC–TOFMS) system, integrated with a robotic pretreatment platform, for online monitoring of both volatile organic compounds (VOCs) and semivolatile organic compounds (SVOCs) in water matrices. Employing the robotic platform, we establish a suite of online liquid–liquid extraction (LLE) pretreatment processes for water samples, marking the first instance of such procedures. Leveraging the automatic headspace (HS) module, dual robotic preparations of HS and LLE are sequentially executed to extract VOCs and SVOCs from water matrices. The GC × GC–TOFMS system is distinguished by its dual-channel analytical column configuration, facilitating sequential analysis of VOCs in GC–TOFMS mode and SVOCs in GC × GC–TOFMS mode. Quantitative detection of 55 target VOCs and 104 SVOCs is achieved in a water sample using the instrument system. Our method demonstrates excellent correlation coefficients ranging from 0.990 to 1.000, method detection limits ranging from 0.08 to 4.78 μg L–1, relative standard deviations below 19.3 %, and recovery rates ranging from 50.0 % to 124.0 %. To validate the online monitoring capabilities of our system, we assess target SVOCs at three different concentration levels over a 3-day period. Most compounds exhibit recovery rates ranging from 70.0 % to 130.0 %. Furthermore, we apply our method to analyze a real water sample, successfully identifying over 100 target and nontarget VOCs/SVOCs, including alcohols, aldehydes, ketones, acids, esters, and phenols. These results highlight the efficacy of the proposed analysis system, capable of conducting two distinct analyses in automatic sequence, thereby enhancing the efficiency and accuracy of organic compound analysis in water matrices. [ABSTRACT FROM AUTHOR]

Current technology has made it possible to automate a number of agricultural processes that were traditionally carried out by humans and now can be entirely performed by robotic platforms. However, there are certain tasks like soft fruit harvesting, where human skills are still required. In this case, the robot's job is to cooperate/collaborate with human workers to alleviate their physical workload and improve harvesting efficiency. To accomplish that in a safe and reliable way, the robot should incorporate a safety system whose main goal is to reduce the risk of harming human co-workers during close human–robot interaction (HRI). In this context, this paper presents a theoretical study, addressing the safety risks of using collaborative robots in agricultural scenarios, especially in HRI situations when the robot's safety system is not completely reliable and a component may fail. The agricultural scenarios discussed in this paper include automatic harvesting, logistics operations, crop monitoring, and plant treatment using UV-C light. A human injury assessment is conducted based on converting the HRI in each agricultural scenario into a formal mathematical representation. This representation is later implemented in a probabilistic model-checking tool. We then use this tool to perform a sensitivity analysis that allows us to determine the probability that a human may get injured according to the occurrence of failures in the robot's safety or perception systems. Results of the sensitivity analysis show that an agricultural robot with a robust human perception system can still harm people if they are not well-trained to interact with the robot for certain scenarios. This illustrates how the probabilistic modeling methodology presented in this work can be used by safety engineers as a guideline to construct their own HRI models and then use the results of the model-checking to enhance the safety and reliability of their robot's safety system architectures and on-site safety policies. • Templates for hazard analysis and mitigation strategies in cooperative agricultural robotics. • Human–robot interactions in agricultural scenarios can be represented as simplified probabilistic models. • The reliability of robot safety systems/policies can be tested by formal verification before real implementation. • An agricultural robot with a robust human perception system can still harm people if they are not well-trained. • Ensuring that only trained people interact with agricultural robots, minimizes chances of producing human injuries. [ABSTRACT FROM AUTHOR]

This study aims to investigate the significant dynamics of a Single Link Flexible Joint (SLFJ) Robotic Manipulator and implement chaotic control using the Adaptive Sliding Mode Control (ASMC) algorithm. The mathematical model of the system incorporates stiffness nonlinearity by introducing the function (x-x3) Various dynamical tools such as stability analysis of equilibrium points, sensitivity to initial conditions, orbit diagrams for parameter variations, Lyapunov spectrum, and frequency spectrum analysis are employed. The ASMC algorithm is utilized to suppress the chaotic behavior of the system. The equilibrium points are determined for critical parameter values, with the Jacobian matrix and corresponding eigenvalues exhibiting conjugate complex with negative real parts, indicating stability resembling a spiral saddle. Phase portraits illustrate the location and range of the chaotic attractor. Investigation of parameter ′ a ′ using orbit diagrams and Lyapunov spectrum reveals the transition from periodic to chaotic oscillations. The frequency spectrum confirms the chaotic nature of the system. Parameter estimation, state trajectories, and sliding surface analysis demonstrate that the ASMC scheme can effectively control the system in less than 0.3 s. Nonlinear stiffness has not been previously considered in SLFJ Robotic Manipulators, highlighting a novel aspect of this study. The results unveil new chaotic ranges for parameter variation previously undocumented. Frequency spectrum analysis is employed to distinguish between noise and chaotic oscillations, addressing a significant challenge in real-time systems. The ASMC algorithm is specifically designed to control chaotic oscillations, demonstrating its effectiveness in this context. • Novel Analysis: The research presents a comprehensive analysis of a Single Link Flexible Joint (SLFJ) Robotic Manipulator with nonlinear stiffness, shedding light on its intricate behavior and the impact of nonlinear dynamics. • Advanced Control Strategies: Through stability, bifurcation, and synchronization analyses, the study underscores the need for sophisticated control strategies, highlighting the effectiveness of the Adaptive Sliding Mode Controller (ASM) in achieving synchronization and stabilizing the system. • Practical Implications: By demonstrating the significance of nonlinear stiffness on system behavior and the efficacy of the ASM Controller in real-time applications, the research contributes valuable insights for enhancing the performance and reliability of robotic manipulator systems in practical scenarios. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence (AI) has the potential to revolutionise the pre-operative, intra-operative and post-operative stages of orthopaedic surgery. We conduct a systematic review and meta-analysis to investigate the role and effectiveness of AI in Orthopedic surgery. We compare the outcomes of AI-assisted and conventional surgery by focusing on the implementation of AI tools in the prediction, diagnosis and robot-assisted surgery. The results of the review and meta-analysis showed high accuracy in prediction outcomes, diagnosis and classification based on medical image analysis. However, the meta-analysis revealed longer operative times with robot-assisted surgery. Additionally, while robotics achieved enhanced implant positioning accuracy, definitive advantages in functional outcomes over conventional surgery were not observed. Future work should focus on extensive follow-up to validate the long-term advantages of AI-assisted procedures in orthopaedic surgery. • A review of application areas of artificial intelligence (AI) in Orthopedic surgery is conducted. • Potential application of AI in the preoperative, intraoperative, and postoperative stages are identified. • A meta-analysis was carried out to compare the performances of AI-assisted orthopedic surgery with conventional approach. • Challenges are identified and avenues for future research are highlighted. [ABSTRACT FROM AUTHOR]

The convolutional neural networks commonly deployed for semantic understanding of visual inspection data can, in general, learn robust spatial features. However, they lack the ability to capture temporal dependencies that characterize the video data collected by various robotic inspection systems. As a result, they are found lacking in dealing with various challenges arising from cross-view illumination variation, perspective difference, scale change, background clutter, and occlusion. Their performance is further deteriorated by motion blur and other distortions induced by rapid camera movement. This study aims to address this challenge by extending the task of visual scene understanding from the still image domain to the video domain by incorporating cross-frame information fusion. A deep end-to-end network is developed by integrating an encoder–decoder-based convolutional neural network with a long short-term memory-based recurrent neural network for pixel-level semantic labeling of sequential visual inspection data. The proposed multishot architecture can jointly learn discriminative fusion features leading to a rich understanding of the complex spatiotemporal dynamics. The proposed approach is validated with two case studies involving automatic structural element segmentation in robotic building and bridge inspection videos. Two different multishot fusion techniques are suggested leveraging sequence-to-one and sequence-to-sequence architectures. Additionally, two different fusion schemes based on the sum-of-scores and Bayesian updating rules are examined to aggregate multiple label maps produced at each time step by an overlapping sliding window-based inference scheme. A comprehensive performance evaluation indicated that multishot fusion could enhance the intersection over union (IoU) score by 4.6% and 13.3% for building and bridge component segmentation tasks, respectively, compared to a baseline single-shot approach. [ABSTRACT FROM AUTHOR]

[Display omitted] • The robot error-motion correlation is analyzed and the error step is defined. • Interpretable predictive mold components were designed. • Self-discovery and self-adaptive mechanism for error step is designed. • Online prediction and compensation experiments are validated in two tasks. • The proposed method reduces the mean error about 90% and improves the consistency. Error prediction and compensation are crucial requirements for improving robot accuracy. To this end, this paper introduces an advanced online method that integrates error-motion correlation for the precise prediction and compensation of robot position errors. The proposed method includes feature selection, model interpretability design, and compensation value smoothness. Analyzing the error characteristics and designing a model based on error-motion correlation reveals that the proposed method reduces position errors by 92 % and 89 % at a frequency of 250 Hz in two tasks with different working conditions. This reduction in position errors ensures smoother compensation, leading to a notable improvement in accuracy for high-precision robotics applications. Unlike existing research that focuses on mapping models, the proposed method prioritizes understanding error behavior, thereby resulting in a comprehensive approach for error management in robotic systems. This contribution is invaluable for advancing the field of precision robotics and ensuring reliable performances in various robotic tasks. [ABSTRACT FROM AUTHOR]

• Feature extraction method can extract required data from the raw scanning data. • Derive the optimal position of leapfrog balls and improve calibration accuracy. • Use SVM to determine the parameters of edge-determination method. • Complex components can be measured and analyzed. • The proposed method can significantly reduce time consumption. In the manufacturing industry of aviation equipment (e.g., ballistic missile, rocket, unmanned aerial vehicle (UAV), and airplane), the traditional assembly quality inspection methods mainly rely on manual operation of single- or multi-stations laser trackers, but they are powerless to measure and evaluate complex components on the aviation equipment. This paper introduces a method for automatically detecting and evaluating assembly accuracy: first, the global accurate calibration is performed automatically by deriving the optimized positioning of leapfrog balls; after selecting the aviation equipment type to determine the measurement tasks, each side of the aviation equipment is equipped with a robot and an accompanying FARO scanning arms that can move together on the U-shaped guide rail to the measurement station where the measurement task is to be performed; at each measurement station, the robot drives the movement of the FARO scanning arm through a linkage mechanism to perform scanning; after the whole measurement processes are completed, data from multiple measurement stations is integrated into the same coordinate system for calculation and assembly quality analysis. The algorithm module consists of path planning function for scanning various parts, feature extraction function for various geometric elements, and assembly quality evaluation function. Compared with laser tracker method, the proposed method can effectively and accurately measure and analyze basic measurement tasks: the maximum differences of length, concentricity, and perpendicularity are all less than 0.3%; while the time consumption can be significantly reduced to less than 5% of that of the laser tracker method. Moreover, the proposed method can also achieve the automatic measurement and analysis of complex positioning components that cannot be achieved by laser trackers, e.g., center of positioning hole, position deviation of the bump, and azimuth angle between the positioning surfaces. [ABSTRACT FROM AUTHOR]

Soft robotics has attained significant attention in recent years due to their infinite degree of freedom, adaptability, and safer interaction with humans and objects in various applications, such as robotics, biomedical devices, search and rescue operations, and wearable technology. However, the soft pneumatic actuator (SPA) is one of the most commonly and frequently utilized actuators in soft robotics due to its higher output at lower energy consumption. Further, an important development was the embedding/integration of soft and flexible sensors within the SPAs. This review article provides a comprehensive review of the frequently utilized SPA designs (McKibben, Pneu-Nets, and material jamming-based actuators), soft sensors (strain, pressure, temperature, tactile, flex, optical, and magnetic sensors), and SPAs with integrated or embedded soft sensors. Further, various emerging trends and breakthroughs in the SPA-sensors integration along with the limitations and challenges are discussed. Finally, it is found that there is an enormous amount of potential for revolutionizing the robotic and associated industries through the integration or embedding of soft sensors into SPAs. Even though there has been a lot of progress, there are still various challenges that need to be resolved and are provided in the future work section. [Display omitted] [ABSTRACT FROM AUTHOR]

The PID controller is an elegant and versatile controller for set point tracking for a double integrator system, in particular, for engineering systems evolving on a Euclidean space. However, the configuration space of many mechanical systems, including interconnected ones, is a Lie group. Geometric PID control design has been proposed for mechanical systems evolving on Lie groups. In this work, we build upon this previously established framework for unconstrained mechanical systems to address systems with nonholonomic constraints. This extension encompasses many frequently encountered applications in robotics, where the constraints could either be holonomic or nonholonomic. [ABSTRACT FROM AUTHOR]

Trunk compensation is a common behavior observed in stroke patients during rehabilitation, and it can hinder their recovery outcomes. To address this issue, we developed a new upper-limb rehabilitation robot that takes advantage of both end-effector and exoskeleton robots. Moreover, we propose a compensation-corrective adaptive control (CCAC) strategy, which employs an admittance model and incorporates two estimators. Specifically, the first estimator is designed to assess human intention, allowing for compliant human-robot interaction. The second estimator calculates dynamic assistance that adjusts for trunk compensation, utilizing two virtual forces applied to the hand and shoulder. Based on this novel CCAC strategy, the newly designed robot is capable of assisting upper limb movements and correcting compensatory postures simultaneously. Results indicate a significant reduction in trunk compensation across three types of reaching tasks when the robot provides assistance. Moreover, the CCAC strategy enhances upper-limb motor performance, resulting in reduced position errors and increased shoulder and elbow joint angles. These findings underscore the potential of the proposed CCAC strategy, combined with upper-limb exoskeleton robots, as a promising approach for correcting compensatory postures and optimizing the advantages of robotic stroke rehabilitation. [ABSTRACT FROM AUTHOR]

The model-free controller is a powerful method because it does not require the knowledge of the robotic plant dynamic equation. Since most of the model-free controllers consider variants of the adaptive or reinforcement learning, one observer-based model-free controller could be a different alternative of interest in the researching community. In this study, an observer-based model-free controller is suggested for the perturbations estimation and attenuation in robotic plants, it contains the model-free observer and the model-free controller. The model-free observer based on the high gain method uses the bounds of the perturbations. The model-free controller based on the sliding mode method uses the bounds of the perturbations and gravity terms. The observer-based model-free controller is applied for the perturbations estimation and attenuation in a cylindrical robotic plant, and a scalar robotic plant. [Display omitted] • Observer-based model-free controller for perturbations estimation and attenuation in robotic plants. • Observer-based model-free controller contains model-free observer and model-free controller. • Model-free observer based on high gain uses perturbations bounds. • Model-free controller based on sliding mode uses perturbations and gravity terms bounds. • Observer-based model-free controller is applied in two robotic plants. [ABSTRACT FROM AUTHOR]

The transition to robotic construction requires advanced planning approaches to meet the specific requirements for successful robot deployment. Robots require precise information (e.g., position, velocity, force) to execute tasks reliably. Existing research focuses on robot-oriented construction processes but lacks real-time planning integration with building and construction information. To overcome these challenges, this paper proposes the Robot Construction Action Node (RCAN), serving as a middle layer system between BIM-based smart components and the Robot Operating System (ROS). RCAN breaks down construction planning into ordered activities for flexible adaptation and direct robot control. By assigning these construction activities to components, the macro construction process is linked to the micro construction methods. This procedure is tested and evaluated using a Linked Building Data (LBD) data modeling approach. The proposed solution is validated through three robot construction scenarios in an earlier built simulation environment. • An RCAN middle layer system is proposed for data linking and interaction between BIM and ROS. • A procedure converts IFC models and construction plannings into merged RDF graphs. • An RCAN-based framework allows interaction between smart components and robots. • A simulation presents execution of construction activities by a mobile manipulator using the RCAN system. [ABSTRACT FROM AUTHOR]

• Unifying six beam theories into a single equation. • Unified dynamic stiffness matrix and transfer matrix. • Frequency-dependent mass and stiffness matrices. • Thorough comparison and scope of different beam theories for curved beams. High-precision, efficient and streamlined methods for the dynamic modeling and analyzing of engineering structures have consistently captured attention of designers and researchers. This paper addressed this increasing demand by presenting a generalized modeling and analyzing method. Specially, a unified model was proposed to integrate six beam theories into a single formula. Upon this model, a unified dynamic stiffness matrix was derived, serving as an elemental building block for formulating the transfer matrix, frequency-dependent mass and stiffness matrices as well as further integrating finite element method, dynamic stiffness matrix method and transfer matrix method. Through this transition, challenges associated with transcendental eigenvalue in dynamic stiffness matrix method and transfer matrix method was effectively resolved and the advantages of transfer matrix method in handling complex structure were maximized. Given the widespread utilization of curved beams in buildings, bridges, robotics and sensors, the proposed method was validated through comparative analysis with other methods, focusing on both curved and straight beams. Furthermore, this study delineated applicability scopes of different beam theories and provided the strategic approach for curved and straight beams. The feasibility of this strategy was demonstrated through an investigation involving a corrugated structure comprising both straight and curved beams. [ABSTRACT FROM AUTHOR]

Glass fiber reinforced plastics (GFRP) are widely appiled for high-value components, but it faces limitations due to the heterogeneity and limited milling tool life. This study investigates the wear mechanism of tools in varying states of wear during the milling of GFRP under different combinations of cutting parameters. The findings demonstrate a significant increase in flank wear values of new tools, initially worn tools, moderate worn tools and severely worn tools associated with the large material removal rate (LMRR), exhibiting respective increments of 56.7%, 59.8%, 74.3%, and 26.5% in contrast to the small material removal rate (SMRR). The wear mechanisms in distinct cutting regions of the tool were systematically classified and characterized. The flank face and tool nose primarily experience abrasion and adhesion, while the rake face and cutting edge predominantly display characteristics of microchipping and abrasive wear. In contrast, the bottom edge is exclusively impacted by microchipping. The deposition of chemical elements on the cutting edge was examined through electron dispersive spectroscopy (EDS) and scanning electron microscopy (SEM). A comprehensive investigation was undertaken to elucidate the progression of tool wear. The findings indicate that the principal factors influencing tool wear in LMRR are adhesive wear resulting from cutting heat and chipping wear arising from substantial cutting loads. In contrast, tool wear during SMRR is predominantly attributed to abrasive wear caused by the presence of fiber-based hard points within GFRP workpieces. The wear characteristics of milling tools during the machining of GFRP are systematically investigated and analyzed. This study holds theoretical significance in guiding the design of tool materials for GFRP milling operations. • Under SMRR conditions, tool mainly suffers from abrasive wear, whereas in LMRR, it primarily undergoes chipping wear. • The rake face of the tool is more susceptible to friction and heat, and oxidative wear is more significant. • A comprehensive description of the evolution of tool wear at different material removal rates is presented. • Thermal effects primarily induce adhesion and edge chipping, whereas the existence of rigid particles results in abrasion. [ABSTRACT FROM AUTHOR]

• Developments of autonomous charging systems from academic and industry points of view. • We present a cost-effective and easily applicable solution for electric vessels. • We propose autonomous shore-to-ship robotic charging system based on YOLOv5. • The performance of the proposed method is demonstrated in the real-case scenario. Recently, there has been a rapid increase in electric vessels as in electric land vehicles. Since vessels such as ferries and ships operate on a specific schedule, the time to be spent for charging on the shore is limited. The charging process involves connecting equipment, transferring energy, and disconnecting equipment. The faster and easier connection and disconnection process is, the more time is for energy transfer. This paper introduces a novel autonomous robotic charging system that combines Programmable Logic Controller (PLC), embedded platform, camera, and lasers to detect the vessel's charging socket in the charging area by computer vision. Initially, the embedded platform detects the charging socket and position of the electric vessel with the camera using You-Only-Look-Once (YOLOv5). After that, when the charging socket is detected, laser sensors control it more precisely to align the robotic charging station and move it closer to the socket on the ship. Finally, the precise location information is transmitted to the PLC, and the robotic charging station transfers energy until the charging process is completed. Consequently, the proposed system achieved 94% accuracy in charging socket detection. This research can be a guide in demonstrating the shore-to-ship socket detection efficiency of autonomous and computer vision-based ship charging systems. [ABSTRACT FROM AUTHOR]

Dyna-style Model-based reinforcement learning (MBRL) methods have demonstrated superior sample efficiency compared to their model-free counterparts, largely attributable to the leverage of learned models. Despite these advancements, the effective application of these learned models remains challenging, largely due to the intricate interdependence between model learning and policy optimization, which presents a significant theoretical gap in this field. This paper bridges this gap by providing a comprehensive theoretical analysis of Dyna-style MBRL for the first time and establishing a return bound in deterministic environments. Building upon this analysis, we propose a novel schema called Model-Based Reinforcement Learning with Model-Free Policy Optimization (MBMFPO). Compared to existing MBRL methods, the proposed schema integrates model-free policy optimization into the MBRL framework, along with some additional techniques. Experimental results on various continuous control tasks demonstrate that MBMFPO can significantly enhance sample efficiency and final performance compared to baseline methods. Furthermore, extensive ablation studies provide robust evidence for the effectiveness of each individual component within the MBMFPO schema. This work advances both the theoretical analysis and practical application of Dyna-style MBRL, paving the way for more efficient reinforcement learning methods. • This paper makes an in-depth analysis of the monotonicity guarantee for the Dyna-style algorithm in the deterministic environment. • A practical schema called MBMFPO is proposed to improve policy performance in real environments. • Experimental results corroborate that the policy trained with MBMFPO schema outperforms the baseline methods in terms of sample efficiency and asymptotic performance. • Further experiments have been conducted to validate the efficacy of the individual components encompassed within the MBMFPO schema. [Display omitted] [ABSTRACT FROM AUTHOR]

Localization algorithms that rely on 3D LiDAR scanners often encounter temporary failures due to various factors, such as sensor faults, dust particles, or drifting. These failures can result in a misalignment between the robot's estimated pose and its actual position in the global map. To address this issue, the process of global re-localization becomes essential, as it involves accurately estimating the robot's current pose within the given map. In this article, we propose a novel global re-localization framework that addresses the limitations of current algorithms heavily reliant on scan matching and direct point cloud feature extraction. Unlike most methods, our framework eliminates the need for an initial guess and provides multiple top- k candidates for selection, enhancing robustness and flexibility. Furthermore, we introduce an event-based re-localization trigger module, enabling autonomous robotic missions. Focusing on subterranean environments with low features, we leverage range image descriptors derived from 3D LiDAR scans to preserve depth information. Our approach enhances a state-of-the-art data-driven descriptor extraction framework for place recognition and orientation regression by incorporating a junction detection module that utilizes the descriptors for classification purposes. The effectiveness of the proposed approach was evaluated across three distinct real-life subterranean environments. • Bridging gap between place recognition and re-localization. • Modular architecture adapts to unique environments. • Eliminates manual guess, reduces computation in re-localization. [ABSTRACT FROM AUTHOR]

The advent of construction robotics (CR) has been rendered technically and economically viable by the proliferation of microprocessors and a decline in costs. A captivating epoch in CR has emerged, and it defies conventional interpretation. We ask how to extract the frontier research topics from patents, which countries are driving innovation in CR, and what policies are contributing to the current situation. This paper uses patent analysis and text mining to study 1831 C R-related patents and finds four clusters from the Derwent Innovations (DI) database. The patent remaining life impact (PRLI) index is calculated. The results show an increase in the number of CR-related patents annually. China leads in the number of patent publications, while the US and other patent organizations have played critical roles in the field. An improved technology evolutionary path tracing visualization identifies several hotspots. Additionally, the policy strategy matrix (PSM) analyzes the industrial stimulation policies of the two countries with the most considerable proportion, providing an explanation for predicting future technology research and development (R&D) and the direction of optimization. [Display omitted] [ABSTRACT FROM AUTHOR]

Robotic-assisted laparoscopic surgery has become ubiquitous in most surgical disciplines. However, robotic surgery has seldom demonstrated a cost or outcome advantage versus pure laparoscopy over a diverse array of procedures. Robotic radical nephrectomy was previously shown to be more expensive than its laparoscopic counterpart, with similar complication rates and no clear oncologic advantage. Initial acquisition of robotic technology confers a significant fixed expense, and therefore, early proponents of robotic surgery posited that increased adoption should contribute to decreased marginal cost. While such economies of scale have been described in certain health services, no such effect has been demonstrated in robotic surgery. Here, we explore patterns of robotic adoption, and address whether increasing volume of robotic radical nephrectomy procedures provides a cost advantage relative to the laparoscopic approach. We analyzed patients (n=60,001) within the Premier Healthcare Database who underwent nephrectomy between 2010 and 2019. Patients who underwent partial nephrectomy, nephroureterectomy, or donor nephrectomy were excluded from the analysis. Robotic, laparoscopic, and open approaches to radical nephrectomy were identified from billing information. The primary outcome was total hospital costs of index admissions, adjusted to 2019 United States dollars using the consumer price index, amongst patients undergoing robotic versus laparoscopic radical nephrectomy. Patient and hospital characteristics were tabulated by surgical approach, and inverse probability treatment weighting was performed to compare costs between robotic and laparoscopic approaches. The mean annual change in total cost by surgical approach was estimated, and generalized linear regression models determined the difference in cost between robotic and laparoscopic procedures;as a function of treatment year or as a function of time since first adoption of robotic radical nephrectomy. 39,305 patients were included for analysis. Mean age was 62.2 years (SD;12.9), and 23,191 (59%) patients were men. 5,288, 11,908, and 22,109 patients underwent robotic, laparoscopic, and open radical nephrectomy, respectively. Proportional utilization of the robotic approach increased from 2.9% (111/3799 procedures) in 2010 to 31% (954/3072 procedures) in 2019 (Figure). Adjusted mean total costs were $18,922, $15,357, and $18,538;for the robotic, laparoscopic, and open approaches, respectively. Mean adjusted total costs of the robotic and laparoscopic approaches stratified by year of treatment or years since first robotic adoption are shown in the Table. The mean annual differences in adjusted total costs between robotic and laparoscopic approaches decreased over time based on year of treatment (-$1.26 [95% CI -408, 405], p=0.9) and years since robotic adoption (-$63 [95% CI -454, 328], p=0.8), but the differences were not statistically significant. Among patients undergoing radical nephrectomy between 2010 and 2019, the proportion of surgeries performed via the robotic approach increased relative to the proportion of laparoscopic or open procedures. While total costs decreased slightly over time for both robotic and laparoscopic techniques, there was no substantial decrease in the cost of robotic procedures relative to laparoscopic cases and suggests an "economy of scale" has yet to be achieved among hospitals performing robotic radical nephrectomies. More work is needed to validate the cost-effectiveness and long-term sustainability of performing robotic radical nephrectomies over purely laparoscopic techniques. [ABSTRACT FROM AUTHOR]

• A new method for constructing a family of Sarrus-inspired deployable polyhedral mechanisms is proposed. • Novel deployable tetrahedral, cubic and dodecahedral mechanisms with symmetric transformability are presented. • The equivalent analysis strategy for mobility of multiloop polyhedral mechanisms is proposed Deployable polyhedral mechanisms (DPMs) have witnessed flourishing growth in recent years because of their potential applications in robotics, space exploration, structure engineering, and so forth. This paper firstly presents the construction, mobility and kinematics of a family of Sarrus-inspired deployable polyhedral mechanisms. By carrying out expansion operation and implanting Sarrus linkages along the straight-line motion paths, deployable tetrahedral, cubic and dodecahedral mechanisms are identified and constructed following tetrahedral, octahedral, and icosahedral symmetry, respectively. Three paired transformations with synchronized radial motion between Platonic and Archimedean polyhedrons are revealed, and their significant symmetric properties are perfectly remained in each work configuration. Subsequently, with assistant of equivalent prismatic joints, the equivalent analysis strategy for mobility of multiloop polyhedral mechanisms is proposed to significantly simplify the calculation process. This paper hence presents the construction method and equivalent analysis of the Sarrus-inspired DPMs that are not only valuable in theoretical investigation, but also have great potential in practical applications such as mechanical metamaterials, deployable architectures and space exploration. [ABSTRACT FROM AUTHOR]

Robotic teleoperation is essential to perform a task where human presence is either impossible or undesirable. The key challenges in robotic teleoperation are capturing human arm-hand functionalities and accurately computing the corresponding joint angles. This paper proposes a lightweight wearable robotic arm-hand controller using Inertial Measurement Unit (IMU) sensors and potentiometers to capture the human arm-hand functionalities up to seventeen degrees of freedom (DoF) for robotic teleoperation. The proposed controller consists of master and slave sides. On the master side, the three wearable IMU sensors capture seven DoF of human-arm orientation, and two potentiometers at each finger capture two DoF. In addition, digital controllers on the master side collect and transmit three sets of quaternion data from IMU sensors and voltage signals from potentiometers to the slave side using a Radio Frequency (RF) communication network as digital data. The digital controller on the slave side computes the joint angles of a human arm and five fingers using the digital data from the master side. It should be noted that a method has been developed to compute the joint angles of the human arm using the Relative Orientation Vector (ROV) approach. The computed joint angles of the human arm-hand are then mapped with the joint angles of the robot arm-hand model designed using Vpython. The successful working of the proposed controller has been demonstrated extensively through simulation and experimental results. [Display omitted] [ABSTRACT FROM AUTHOR]