Search

In robotics, decoding complex human movements of multiple degrees of freedom (DOFs) from surface electromyography (sEMG) remains challenging. Recently, the rapid development of artificial intelligence (AI) technology provides a new solution to this problem. In this paper, we propose an AI-based framework that consists of a series of deep learning approaches, for achieving a precise and robust decoding on three-dimensional (3D) wrist movements. A previously developed device (WMD) was utilized to tag the myoelectric signals with 3D kinematic labels. A public dataset (HIT-SimCo) was established, wherein the sEMG signals were collected from diverse wrist movements and multiple subjects. A lightweight convolutional neural network (CNN) was constructed, which can extract the motion-related features directly from raw sEMG, and make motion predictions in an end-to-end manner. In addition, several data augmentation strategies were explored to improve the robustness of the model against environmental variations; and a fine-tuning policy was proposed to further improve the subject-specific accuracy. The decoding model was finally tested in three scenarios: a robotic arm/hand system performing daily-living tasks (pouring, screwing, etc.), a supernumerary robotic hand playing blocks-building, and a virtual prosthesis conducting motor rehabilitation training.

This article develops a flexible and robust robotic system for autonomously drawing on 3-D surfaces. The system takes 2-D drawing strokes and a 3-D target surface (mesh or point clouds) as input. It maps the 2-D strokes onto the 3-D surface and generates a robot motion to draw the mapped strokes using visual recognition, grasp pose reasoning, and motion planning. The system is flexible compared to conventional robotic drawing systems as we do not fix drawing tools to the end of a robot arm. Instead, a robot recognizes and picks up pens online and holds the pens to draw 3-D strokes. Meanwhile, the system has high robustness thanks to the following crafts: First, a high-quality mapping method is developed to minimize deformation in the strokes. Second, visual detection is used to reestimate the drawing tool’s pose before executing each drawing motion. Third, force control is employed to compensate for noisy visual detection and calibration and ensure a firm touch between the pen tip and the surface. Fourth, error detection and recovery are implemented to deal with slippage and other anomalies. The planning and executions are performed in a closed-loop manner until the strokes are successfully drawn. We evaluate the system and analyze the necessity of the various crafts using different real-world tasks. The results show that the proposed system is flexible and robust to generate robotic motion that picks up the pens and successfully draws 3-D strokes on given surfaces.

On-skin stretchable electronic devices that can acquire electrophysiological signals for controllable human-machine interactions are of considerable importance in wearable robotics applications. The straightforward, large-area fabrication of structurally stretchable electronic sensors processed by ultrafast laser ablation techniques provides great insights into low-cost wearable stretchable sensors. In this study, a patch-based large-area frame-type stretchable sensor array system that covers a large portion (~20 cm wide) of the human armprocessed by a simple, ultrafast ( 100%)allows the sensor to conformally attach to the skin for long-term usage. The patch-based sensor exhibited robust electromechanical properties under significant mechanical loadings for 10 000 cycles, a promising characteristic for product commercialization. Moreover, the results suggest that the proposed method is suitable for the fabrication of diverse materials for stretchable electronic applications. We verified the application of electromyography (EMG) signals with human motion determination to control the movements of the robotic hand.

Origami structures can transform their form and function by changing the direction of their folds. This reconfiguration can enable multifunctional robots, but doing so requires a fast, robust, and repeatable actuation method. In this article, we present an origami gripper that uses dynamic transformation to change its kinematic behavior in less than a second. We characterize individual vertices to show that the transformation is predictable and repeatable for different designs and orientations. We then apply it to a multivertex template that is capable of a wide range of shapes and motion patterns, indicating that transformation can be generalized to complex and functional machines. To demonstrate this, we built a transforming origami gripper on a robotic arm to pick up multiple objects. Demonstrations show that the gripper can quickly reconfigure between three different grasping modes and has sufficient stiffness to engage with and lift multiple objects with distinct geometries.

This paper proposes and implements a compact wireless motor drive using orthogonal bipolar coils for the coordinated operation of robotic arms. The key is to orthogonally integrate two bipolar coils to form a compact magnetic coupler (CMC), while each CMC serves as the transmitting coil and receiving coil, respectively. Instead of adopting the one-to-many coil structure and operating at multiple frequencies, in this paper, two bipolar coils in the CMC are mutually decoupled and separately energized to drive two permanent magnet DC (PMDC) motors. As such, the wireless and selective motor drives can be achieved via the shared power-transfer channel at a single resonant frequency. All controls and switches are concentrated at the transmitter so that the receiver is entirely sealable. Accordingly, the coordinated operation of robotic arms can be realized with the high integration and no electrocution. Theoretical calculations and experimental results are given to validate the flexibility and feasibility of the proposed system.

Human collaborative robots (HCRs) are a useful future workforce because they can operate alongside people. Proximity and tactile sensing are important for HCRs to ensure safety. In this study, we propose a combined sensor module for HCRs using time-of-flight (ToF) as well as self-capacitance proximity and tactile sensors. The distance to an object in a noncontact range can be detected by a ToF sensor; however, the detection accuracy and the X-Y measurement range are lower for short ranges, with the Z axis as the measurement plane direction. The self-capacitance proximity and tactile sensors can detect objects and contact conditions in short ranges. For high-sensitivity proximity and contact measurements over a large distance, two of the aforementioned sensors can be combined. Prototypes of the sensor modules were prepared, and sixteen modules were mounted on a robot armto detect the position and distance of an object at 300 mm or less, along with the pressure and position upon contact. In addition, the robot arm was controlled using information obtained from the sensors. The proposed sensor modules can thus be employed for proximity and tactile sensing in HCRs.

Reliable and accurate calibration for camera, inertial measurement unit (IMU) and robot is a critical prerequisite for visual-inertial based robot pose estimation and surrounding environment perception. However, traditional calibrations suffer inaccuracy and inconsistency. To address these problems, this paper proposes a monocular visual-inertial and robotic-arm calibration in a unifying framework. In our method, the spatial relationship is geometrically correlated between the sensing units and robotic arm. The decoupled estimations on rotation and translation could reduce the coupled errors during the optimization. Additionally, the robotic calibration moving trajectory has been designed in a spiral pattern that enables full excitations on 6 DOF motions repeatably and consistently. The calibration has been evaluated on our developed platform. In the experiments, the calibration achieves the accuracy with rotation and translation RMSEs less than 0.7° and 0.01 m, respectively. The comparisons with state-of-the-art results prove our calibration consistency, accuracy and effectiveness.

Obstacle avoidance for robotic manipulators can be challenging when they operate in unstructured environments. This problem is probed with the sim-to-real (sim2real) deep reinforcement learning, such that a moving policy of the robotic arm is learnt in a simulator and then adapted to the real world. However, the problem of sim2real adaptation is notoriously difficult. To this end, this work proposes (1) a unified representation of obstacles and targets to capture the underlying dynamics of the environment while allowing generalization to unseen goals and (2) a flexible end-to-end model combining the unified representation with the deep reinforcement learning control module that can be trained by interacting with the environment. Such a representation is agnostic to the shape and appearance of the underlying objects, which simplifies and unifies the scene representation in both simulated and real worlds. We implement this idea with a vision-based actor-critic framework by devising a bounding box predictor module. The predictor estimates the 3D bounding boxes of obstacles and targets from the RGB-D input. The features extracted by the predictor are fed into the policy network, and all the modules are jointly trained. This makes the policy learn object-aware scene representation, which leads to a data-efficient learning of the obstacle avoidance policy. Our experiments in simulated environment and the real-world show that the end-to-end model of the unified representation achieves better sim2real adaption and scene generalization than state-of-the-art techniques.

The present paper addresses the development of a closing and sealing system for a container which shall safely bring 100 g of regolith from the surface of Phobos, one of the moons of Mars. Based on a set of requirements defined by the ESA (European Space Agency), a design of the closing and sealing system was made and FEA (Finite Element Analysis) was employed to validate the design. The closing and sealing mechanism along with the Vault (container to be sealed) proved the capability to overcome the Robotic Arm misalignments, to ensure the Vault closing and to maintain the leak tightness (maximum admissible leak rate of 10−4 mbar*l/s Helium) during the trip back to Earth. All these features were validated following an extensive test campaign implying mechanical loads, shocks, thermal vacuum cycling, dust contamination, impact tests and several functional verifications. The mechanism demonstrated the targeted maturity level (TRL 5) and it can be further developed in order to be qualified for a specific mission/application.

A significant number of the planned on-orbit servicing and active debris removal missions will be performed by a spacecraft equipped with a robotic arm. In this paper we propose a new method for the path planning of the robotic arm mounted on the free-floating unmanned spacecraft. In the proposed approach the path of the arm is described in the joint space by a spline function. The coordinates of spline knots form the vector of decision variables. The constrained nonlinear optimization problem is formulated and solved with an active-set algorithm. The proposed method generates a collision-free path of the arm that results in the desired position and orientation of the gripper and the desired attitude of the spacecraft. The possibility of achieving all these goals at the same time is the major advantage of the proposed approach. The practical applicability of the presented method is demonstrated in experiments performed on the planar air-bearing microgravity simulator (for a planar case) and using numerical simulations performed with the Monte Carlo method (for a spatial case). In the planar case the optimal path is compared with the path obtained using the bi-directional Rapidly-exploring Random Trees (RRT) algorithm. It is shown that the path obtained using the proposed method is shorter and smoother than the RRT path.

Robotics and their application in industrial automation are increasing over the decades. There are a variety of conventional and non-conventional applications of robotic manipulators. One example of the non-traditional application of robot manipulators is the 3D printing-based construction of houses and buildings. Up to date, different ambitious solutions and methods are proposed, and they are expanding fast. In large-scale production, 6 DOF robotic arms, designed by common manufacturers such as KUKA, DENSO are widely used in 3D construction. The main objective of this work is to model a 6 DOF robot manipulator for 3D printing-based construction technology. This paper presents two new designs of robot manipulators for construction purposes; one is to transport the building materials, and the other is to help print with the concrete mixtures. The simulation results are obtained applying fundamental theories of robotics through Roboanalyzer software. The simulation parameters are chosen for the designed specific model.

Total knee arthroplasty has been around for decades and serves as a very successful procedure to alleviate pain and restore function in a knee with advanced degenerative joint disease. Over the years, there have been many advancements in surgical technique and even more so in implant design. One of the more recent technological breakthroughs in total knee arthroplasty is the use of a robotic assisted arm for enhanced preoperative planning and intra-operative guidance with dynamic joint balancing and bone preparation. This video outlines the operative technique used by the primary author in performing a posterior stabilizing total knee arthroplasty in a varus deformity degenerative knee using Mako robotic assistance.

Establishing a communication bridge by transferring data driven from different embedded sensors via internet or reconcilable network protocols between enormous number of distinctively addressable objects or "things", is known as the Internet of Things (IoT). IoT can be amalgamated with multitudinous objects such as thermostats, cars, lights, refrigerators, and many more appliances which will be able to build a connection via internet. Where objects of our diurnal life can establish a network connection and get smarter with IoT, robotics can be another aspect which will get beneficial to be brought under the concept of IoT and is able to add a new perception in robotics having "Mechanical Smart Intelligence" which is generally called "Internet of Robotic Things" (IoRT). A robotic arm is a part of robotics where it is usually a programmable mechanical arm which has human arm like functionalities. In this paper, IoRT will be represented by a 5 DoF (degree of freedoms) Robotic Arm which will be able to communicate as an IoRT device, controlled with heterogeneous devices using Social IoT and "Cloud Robotics".

Research in human–robot interaction for assistive robotics usually presents many technical challenges for experimenters, forcing researchers to split their time between solving technical problems and conducting experiments. In addition, previous work in virtual reality setups tends to focus on a single assistive robotics application. In order to alleviate these problems, we present ArmSym, a virtual reality laboratory with a fully simulated and developer-friendly robot arm. The system is intended as a testbed to run many sorts of experiments on human control of a robotic arm in a realistic environment, ranging from an upper limb prosthesis to a wheelchair-mounted robotic manipulator. To highlight the possibilities of this system, we perform a study comparing different sorts of prosthetic control types. Looking at nonimpaired subjects, we study different psychological metrics that evaluate the interaction of the user with the robot under different control conditions. Subjects report a perception of embodiment in the absence of realistic cutaneous touch, supporting previous studies in the topic. We also find interesting correlations between control and perceived ease of use. Overall our results confirm that ArmSym can be used to gather data from immersive experiences prosthetics, opening the door to closer collaboration between device engineers and experience designers in the future.

This paper explores a scheme of tuning a basic input-output (I/O) gain (BIOG) depending on usage conditions for improving the work performance of human-operated machines. I/O gain tuning is effective for improving operability and workability, but continual and/or huge changes makes operators confuse the machine dynamics, and then degrade the operability. Thus, the proposed tuning system tunes the BIOG at long terms according to comprehensive characteristics of the work content and operator, collected from a control lever input histogram. The target value is specified by a Gaussian distribution, meaning that all ranges of the spring-type control lever are equally used. This approach was chosen because leveling the control lever histogram independently of the operator and work content provides a consistent operational experience, leading to comfortable operations. In this study, BIOG curves are specified as a polygonal line involving a break and saturation point. These points are adjusted by reciprocal conversion of differential areas between the Gaussian distribution and obtained histogram curves. Experimental results obtained with a robot arm indicated that the developed BIOG tuning system could improve time efficiency by decreasing the differential area and increase the subjective usability as compared to a conventional fixed BIOG system. Moreover, the relationship between the histogram and BIOG curve could reveal features of both the work content and the operators skill level.

The combination of two rapidly evolving technologies such as additive manufacturing technology and robotics opens up a wide potential for solving new production tasks. In advance, several challenges need to be addressed in order to intensify the possibilities for developing the combination of these technologies. The aim of the article is to point out the possibility of designing a simple universal printing system for the collaborative robot UR5 with an orientation on the need to implement 3D printing. The solution proposed in this way makes it possible to simplify the design of the movements to reduce any further structural modifications and also to reduce the potential mechanical deficiencies of the structure of the printing device.

This paper focuses on the tension reduction method for a Modular Cable-Driven Robotic Arm (MCDRA) that consists of a number of 2-degree-of-freedom (2-DOF) cable-driven joint modules. The MCDRA has implemented a cable routing scheme in which every two adjacent modules co-share one driving cable in order to reduce the number of cables to the minimum required. To investigate the tension distribution of the cables, a new tension analysis algorithm is proposed, in which the cable tension is decomposed into the load-carrying tension and the internal tension. It is revealed that the MCDRA with alternatively co-shared driving cables has inevitable internal tensions, which results in tension magnification. To reduce the cable tensions, the MCDRA is modified by adding two revolute joints with one connected to the base and the other one placed at its distal end. By rotating the base-mounted revolute joint and controlling each of the joints as well as the revolute joint on the distal end accordingly, the modified MCDRA can rotate like a universal joint chain and keep the end-effector pose unchanged. A global optimization algorithm based on interval analysis is proposed to find the optimal rotation angle of the base-mounted revolute joint that produces the lowest cable tensions. The effectiveness of the cable tension reduction method is validated through both simulation and experimental studies.

We describe the use of an automated co-ordinate measurement machine (CMM) directly or in concert with a three-axis robot arm to map the distortion of a 3D structured light scanner's field of view. This enables us to compare the claimed accuracy and resolution of different structured light scanners. In addition, we can also use the distortion mapping to generate a correction mechanism to improve the performance of the scanner. We present the results of experiments obtained using this novel approach on three commercially available 3D scanners.

We propose a micro-data ( 10 trials) sensorimotor learning and adaptation (SEED) model for human-like arm inverse dynamics control. The SEED model consists of a feedforward Gaussian motor primitive (GATE) neural network and an adaptive feedback impedance (AIM) mechanism. Sensorimotor weights over trials are learned in the GATE network, while the AIM mechanism is used to online tune impedance gains in a trial. The model was validated by periodic and non-periodic tracking tasks on a two-joint robot arm. As a result, the proposed model enables the arm to stably learn the tasks within 10 trials, compared to thousands of trials required by state-of-art deep learning. This model facilitates the exploration of unknown arm dynamics, in which the elbow joint requires much less active control compared to the shoulder. This control goes below 3% of the overall effort. This finding complies with a proximal–distal control gradient in human arm control. Taken together, the proposed SEED model paves a way for implementing data-efficient sensorimotor learning and adaptation of human-like arm movement.

Robot-assisted surgery is evolving to incorporate a higher number of minimally invasive techniques. There is a growing interest in robotic breast reconstruction that uses autologous tissue. Since a traditional latissimus dorsi (LD) flap leads to a long donor scar, which can be an unpleasant burden to patients, there have been many attempts to decrease the scar length using minimally invasive approaches. This study presents the case of a patient who underwent a robot-assisted nipple-sparing mastectomy followed by immediate breast reconstruction with an LD flap using a single-port robotic surgery system. With the assistance of a single-port robot, a simple docking process using a short and less visible incision is possible. Compared to multiport surgery systems, single-port robots can reduce the possibility of collision between robotic arms and provide a clear view of the medial border of the LD where the curvature of the back restricts the visual field. We recommend the use of single-port robots as a minimally invasive approach for harvesting LD flaps.

Aims It is unknown whether gap laxities measured in robotic arm-assisted total knee arthroplasty (TKA) correlate to load sensor measurements. The aim of this study was to determine whether symmetry of the maximum medial and lateral gaps in extension and flexion was predictive of knee balance in extension and flexion respectively using different maximum thresholds of intercompartmental load difference (ICLD) to define balance. Methods A prospective cohort study of 165 patients undergoing functionally-aligned TKA was performed (176 TKAs). With trial components in situ, medial and lateral extension and flexion gaps were measured using robotic navigation while applying valgus and varus forces. The ICLD between medial and lateral compartments was measured in extension and flexion with the load sensor. The null hypothesis was that stressed gap symmetry would not correlate directly with sensor-defined soft tissue balance. Results In TKAs with a stressed medial-lateral gap difference of ≤1 mm, 147 (89%) had an ICLD of ≤15 lb in extension, and 112 (84%) had an ICLD of ≤ 15 lb in flexion; 157 (95%) had an ICLD ≤ 30 lb in extension, and 126 (94%) had an ICLD ≤ 30 lb in flexion; and 165 (100%) had an ICLD ≤ 60 lb in extension, and 133 (99%) had an ICLD ≤ 60 lb in flexion. With a 0 mm difference between the medial and lateral stressed gaps, 103 (91%) of TKA had an ICLD ≤ 15 lb in extension, decreasing to 155 (88%) when the difference between the medial and lateral stressed extension gaps increased to ± 3 mm. In flexion, 47 (77%) had an ICLD ≤ 15 lb with a medial-lateral gap difference of 0 mm, increasing to 147 (84%) at ± 3 mm. Conclusion This study found a strong relationship between intercompartmental loads and gap symmetry in extension and flexion measured with prostheses in situ. The results suggest that ICLD and medial-lateral gap difference provide similar assessment of soft-tissue balance in robotic arm-assisted TKA. Cite this article: Bone Jt Open 2021;2(11):974–980.

Longtime readers of this column will recall that the proliferation of space debris in near-Earth orbits is an issue that I have previously expressed concern about. Last May, the inevitable happened when a piece of space debris too small to be tracked has hit and damaged part of the International Space Station, namely, the Canadarm2 robotic arm [1] . The object punctured the thermal blanket and damaged the boom underneath, but fortunately, the instrument is still operational [1] .

It is evident that the technological growth of the last few decades has signaled the development of several application domains. One application domain that has expanded massively in recent years is robotics. The usage and spread of robotic systems in commercial and non-commercial environments resulted in increased productivity, efficiency, and higher quality of life. Many researchers have developed systems that improve many aspects of people’s lives, based on robotics. Most of the engineers use high-cost robotic arms, which are usually out of the reach of typical consumers. We fill this gap by presenting a low-cost and high-accuracy project to be used as a robotic assistant for every consumer. Our project aims to further improve people’s quality of life, and more specifically people with physical and mobility impairments. The robotic system is based on the Niryo-One robotic arm, equipped with a USB (Universal Serial Bus) HD (High Definition) camera on the end-effector. To achieve high accuracy, we modified the YOLO algorithm by adding novel features and additional computations to be used in the kinematic model. We evaluated the proposed system by conducting experiments using PhD students of our laboratory and demonstrated its effectiveness. The experimental results indicate that the robotic arm can detect and deliver the requested object in a timely manner with a 96.66% accuracy.

The development of a novel 3D-printed three-claw robotic gripper shall be described in this paper with the goal of incorporating various design considerations. Such considerations include the grip reliability and stability, grip force maximization, wide object grasping capability. Modularization of its components is another consideration that allows its parts to be easily machined and reusable. The design was realized by 3D printing using a combination of tough polylactic acid (PLA) material and thermoplastic polyurethane (TPU) material. In practice, additional tolerances were also considered for 3D printing of materials to compensate for possible expansion or shrinkage of the materials used to achieve the required functionality. The aim of the study is to explore the design and eventually deploy the three-claw robotic gripper to an actual robotic arm once its metal work fabrication is finished.

Assistive technologies (ATs) often have a high-dimensionality of possible movements (e.g., assistive robot with several degrees of freedom or a computer), but the users have to control them with low-dimensionality sensors and interfaces (e.g., switches). This paper presents the development of an open-source interface based on a sequence-matching algorithm for the control of ATs. Sequence matching allows the user to input several different commands with low-dimensionality sensors by not only recognizing their output, but also their sequential pattern through time, similarly to Morse code. In this paper, the algorithm is applied to the recognition of hand gestures, inputted using an inertial measurement unit worn by the user. An SVM-based algorithm, that is aimed to be robust, with small training sets (e.g., five examples per class) is developed to recognize gestures in real-time. Finally, the interface is applied to control a computer’s mouse and keyboard. The interface was compared against (and combined with) the head movement-based AssystMouse software. The hand gesture interface showed encouraging results for this application but could also be used with other body parts (e.g., head and feet) and could control various ATs (e.g., assistive robotic arm and prosthesis).

The emergence of robotic body augmentation provides exciting innovations that will revolutionize the fields of robotics, human-machine interaction and wearable electronics. Although augmentative devices such as extra robotic arms and fingers are informed by restorative technologies in many ways, they also introduce unique challenges for bidirectional human-machine collaboration. Can humans adapt and learn to operate a new robotic limb collaboratively with their biological limbs, without restricting other physical abilities? To successfully achieve robotic body augmentation, we need to ensure that, by giving a user an additional (artificial) limb, we are not trading off the functionalities of an existing (biological) one. Here, we introduce the 'neural resource allocation problem' and discuss how to allow the effective voluntary control of augmentative devices without compromising control of the biological body. In reviewing the relevant literature on extra robotic fingers and arms, we critically assess the range of potential solutions available for this neural resource allocation problem. For this purpose, we combine multiple perspectives from engineering and neuroscience with considerations including human-machine interaction, sensory-motor integration, ethics and law. In summary, we aim to define common foundations and operating principles for the successful implementation of robotic body augmentation., The development of extra fingers and arms is an exciting research area in robotics, human-machine interaction and wearable electronics. It is unclear, however, whether humans can adapt and learn to control extra limbs and integrate them into a new sensorimotor representation, without sacrificing their natural abilities. The authors review this topic and describe challenges in allocating neural resources for robotic body augmentation.

Camera calibration is essential for calculating camera parameters, and the parameters should be constant whenever the position tracker needs to be recalibrated. Manual camera calibration obtains a checkerboard image by tilting or positioning the checkerboard by hand. However, it makes difficult to obtain the same checkerboard images in every calibration, resulting in different camera parameters. Therefore, this study proposes robotic camera calibration to produce the constant camera parameters whenever the tracker needs to be calibrated. The robot arm moves the checkerboard according to the programmed positions and orientations so that the position tracker can obtain the same checkerboard image every calibration. Experiments were conducted to compare results of the manual and robotic camera calibrations. First, we compared the standard deviations of the intrinsic parameters and extrinsic parameters; the results show that robotic camera calibration produced the parameters with smaller standard deviations. We also compared the tracking precision of the cubic marker using manual and robotic camera calibration. As a result, the standard deviations of the tracking precision of cubic marker by the manual and the robotic camera calibration were 1.65 mm and only 0.35 mm, respectively. It reveals that the robotic camera calibration enables more precise and consistent tracking than the manual calibration.

This work describes the development of RBOT, a robot-driven radio base station maintenance system. RBS deployment and maintenance tasks are increasing both in complexity and density with the introduction of 5G microcells. The main objective behind our application is to reduce maintenance costs by developing an integrated system based on a robotic arm to operate on the RBS front plane. This work details the challenges and solutions for maintaining the connectivity of networking cables in such an environment. More specifically, it discusses the problems of inserting communication cables and removing defective ones attached to an RBS equipment. We also examine the creation and evolution of a maintenance system from a simulation scenario to a real-world setup. RBOT’s interface allows both remote teleoperation and autonomous operation. It also contains Augmented Reality features providing a first-person view for remote teleoperation to increase environmental awareness. Furthermore, by applying convolutional neural networks for faulty cable classification, RBOT can actuate over the RBS and manipulate the cables with a unique, accurate, and robust gripper we specially designed for cable connector handling.

The Cirq is a surgeon-controlled robotic arm that provides a new technique for accurately placing transpedicular screws. This report aims to present a technical report and our experience with this new robotic arm combined with intraoperative navigation. Technique and workflow using the Cirq robotic arm with intraoperative navigation is described. A retrospective review was conducted of all patients undergoing elective open thoracic/lumbar fusion surgery by a single surgeon in the first year of using the novel Cirq robotic arm. Descriptive analysis of patient and operative variables was performed. A total of 84 patients underwent placement of a total 714 transpedicular screws using the Cirq robotic arm. Most (69.1%) underwent 3–6 level fusion procedures. Mean operative time was 198 min total and 28 min when adjusted per screw. There was a learning curve with operative time per screw decreasing from 32 to 25 min from the first to second half of cases (p = 0.057). There were no intraoperative screw revisions and 2.4% (2/84) required instrumentation revision and return to the operating room. The Cirq robotic arm is seamlessly incorporated into the workflow of a transpedicular fusion. Our experience with over 700 pedicle screw placements using the Cirq robot demonstrates efficacy and safety although further comparative studies are needed.

This chapter focuses on the technological and scientific state of the art about information technology advances. It discusses the scientific improvements transforming the production lines and machines in intelligent systems following the logic of Industry 5.0. The chapter provides elements useful to comprehend how technologies can be implemented in flexible information architectures for innovative industrialization processes. The main flexible technologies are integrated in robotic systems. The chapter also provides different examples to comprehend how innovative tools, including artificial intelligence (AI), can be applied in a new production scenario. Intelligent systems are implemented by AI algorithms, applied also for the intelligent movements of robotic arms. The production process control is usually performed by image vision techniques and by Internet of Things sensors placed inside the machines or outside. Technological approaches able to transform the production into an auto‐adaptive system are horizontal, vertical, and end to end integration.

Globally accurate manipulation and localization of the terminal of a mobile robot arm within a large workspace has always been a bottleneck problem. In this article, a planar-laser-guided solution is proposed for this issue. The core of this solution is using three movable planar lasers to designate a unique reference point with orientation information within the workspace, and designing a sensor module mounted on the terminal of the robot arm with photoelectric position sensitive devices (PSDs) to measure the relative pose between the terminal and the reference point. Thus, the terminal of the robot can be guided by this relative pose to the target in a given orientation. According to this concept, a parameterized model of the moveable planar lasers and the poses of the PSDs, as well as an expression of their geometric relationship, were derived. The manipulation strategy of the robot arm was further investigated through the model, and an error compensation method to improve the manipulation accuracy was proposed. Finally, a reduced-scale prototype system, based on this solution, was built, on which tracking and positioning experiments of the robot arm were carried out to verify the feasibility of the solution. It has been shown that this laser-guided solution is not sensitive to the blockage (occlusion) of several laser transmitters, which could be an advantage for its application in future autonomous settings.

Numerous biological studies of body and/or caudal fin fish have powerfully identified that the fish body's passive properties, such as stiffness and its distribution, contribute to the fish's outstanding swimming performance. In this study, we develop a free-swimming tensegrity fish robot (TenFiBot) to help scholars experimentally improve their understanding of the role of stiffness distribution in fish-like swimming. We detail the overall structure and parameters of TenFiBot, which can achieve body stiffness distribution with high stiffness controllability over a wide range. The effective variable stiffness principle is based on antagonistic stiffness that results from the prestress of tension structures in a kinematically singular configuration. We validate the effectiveness of variable stiffness for one variable-stiffness tensegrity joint (VSTJ) and demonstrate that the virtual rotational centers are always in the acceptable range during stiffness variation. We exemplify some cases of the stiffness distribution to verify the validity of body stiffness variation. The experimental results show that swimming performance, such as swimming velocity, varied dramatically when the stiffness distribution was varied for the robotic fish. The swimming performance of the robotic fish can be enhanced tremendously by changing the stiffness distribution. Moreover, the VSTJs in the fish body have great potential in constructing compliant robotic arms and snake-like robots.

The paper considers a new layout of a two-stage spacecraft designed to remove a group of large space debris objects such as the upper stages of ‘Zenit’ launch vehicles from low-earth orbit. The aim of the work is to preliminarily quantify the parameters of the shock-absorbing system of the robotic arm designed for capturing a redundant upper stage by the main rocket engine nozzle. The estimation will be conducted by means of numerical simulation of the motion dynamics of the "spacecraft - space debris object" system. The paper presents the results of calculating the transient mode of oscillations of objects connected by the manipulator using simplified and detailed dynamic models of parameters, the analysis of the placement options for the manipulator shock-absorbing system, the analysis of the load reduction possibility through the use of attitude control thrusters, the analysis of two dynamic design variants of the mechanism for grabbing the critical section of the nozzle, and analysis of the capture dynamics at different initial angular velocities of rotation of a space debris object. The most rational shock-absorbing solution for a robotic arm with two translational and two rotary dampers is found. It is shown that the dynamic design of the nozzle capture mechanism has the greatest effect on the robotic arm loading. The kinematic design of the gripper selected as a result of the simulation almost completely eliminates shock loads in the process of damping the system vibrations. It is shown that the robotic arm shock-absorbing design has a significant margin for the initial angular velocity of the space debris object.

Background Motion artifacts affect the images of coronary calcified plaques. This study utilized convolutional neural networks (CNNs) to classify the motion-contaminated images of moving coronary calcified plaques and to determine the influential factors for the classification performance. Methods Two artificial coronary arteries containing four artificial plaques of different densities were placed on a robotic arm in an anthropomorphic thorax phantom. Each artery moved linearly at velocities ranging from 0 to 60 mm/s. CT examinations were performed with four state-of-the-art CT systems. All images were reconstructed with filtered back projection and at least three levels of iterative reconstruction. Each examination was performed at 100%, 80% and 40% radiation dose. Three deep CNN architectures were used for training the classification models. A five-fold cross-validation procedure was applied to validate the models. Results The accuracy of the CNN classification was 90.2 ± 3.1%, 90.6 ± 3.5%, and 90.1 ± 3.2% for the artificial plaques using Inception v3, ResNet101 and DenseNet201 CNN architectures, respectively. In the multivariate analysis, higher density and increasing velocity were significantly associated with higher classification accuracy (all P P > 0.05). Conclusions The CNN achieved a high accuracy of 90% when classifying the motion-contaminated images into the actual category, regardless of different vendors, velocities, radiation doses, and reconstruction algorithms, which indicates the potential value of using a CNN to correct calcium scores.

En el desarrollo de los robots de asistencia un reto importante consiste en mejorar la percepción espacial de los robots para la identificación de objetos en diversos escenarios. Para ello, es preciso desarrollar herramientas de análisis y procesamiento de datos de visión estereoscópica artificial. Por esta razón, el presente artículo describe un algoritmo de redes neuronales convolucionales (CNN) implementado en una Raspberry Pi 3 ubicada en la cabeza de una réplica del robot humanoide de código abierto InMoov para estimar la posición en X, Y, Z de un objeto dentro de un entorno controlado. Este artículo explica la construcción de la parte superior del robot InMoov, la aplicación de Transfer Learning para detectar y segmentar un objeto dentro de un entorno controlado, el desarrollo de la arquitectura CNN y, por último, la asignación y evaluación de parámetros de entrenamiento. Como resultado, se obtuvo un error promedio estimado de 27 mm en la coordenada X, 21 mm en la coordenada Y y 4 mm en la coordenada Z. Estos datos son de gran impacto y necesarios al momento de usar esas coordenadas en un brazo robótico para que alcance el objeto y lo agarre, tema que queda pendiente para un futuro trabajo.

To achieve high-accuracy grasping of unknown objects, we present novel multilevel convolutional neural networks (CNNs) for robotic grasping with a parallel gripper or multifingered dexterous hand. The multilevel CNNs include four levels with different structures and functions. The first level is constructed to get the approximate position of the grasped object. The second level aims to obtain the preselected grasping rectangles. The third level is constructed to re-evaluate the preselected grasping rectangles and obtain substantially detailed features with quite a large network, so as to assess each preselected grasping rectangle exactly. By using a selection algorithm, the optimal grasping rectangle can be determined and unknown object grasping can be achieved with a parallel gripper. The purpose of the fourth level is to obtain the finger position distribution to complete the accurate grasping of unknown objects with a multifingered dexterous hand. The test results indicate that, compared to state-of-the-art methods, the proposed multilevel CNNs can greatly increase the precision of the grasping rectangle. Grasping experiments were implemented on a Youbot arm with five degrees of freedom and a Shadow four-fingered dexterous hand. The results show that the multilevel CNNs can determine the optimal grasping rectangle and finger position distribution, thereby achieving high-accuracy grasping of various unknown objects, even under several complex environmental conditions. Note to Practitioners—Robot grasping of objects lags far behind human experiences and poses a significant challenge in the robotics area. To solve it, we present new multilevel convolutional neural networks (CNNs) to process red green blue-depth (RGB-D) images and realize optimal grasping detection of unknown objects. Moreover, we provide details of the network structure, network training, and network testing. The testing results obtained from the open grasping data set show that the multilevel CNNs can significantly increase the accuracy of the grasping rectangle compared to state-of-the-art methods. Experiments were implemented on different robotic platforms, including a five-degrees-of-freedom Youbot arm with a parallel gripper and a UR5 robot arm with a Shadow multifingered dexterous hand. The results validate that the multilevel CNNs offer excellent generalization and robustness for handling different sizes and shapes of unknown objects, as well as background disturbances, which are key problems in robotic manipulation.

Aims This study aimed to evaluate the accuracy of implant placement with robotic-arm assisted total hip arthroplasty (THA) in patients with developmental dysplasia of the hip (DDH). Methods The study analyzed a consecutive series of 69 patients who underwent robotic-arm assisted THA between September 2018 and December 2019. Of these, 30 patients had DDH and were classified according to the Crowe type. Acetabular component alignment and 3D positions were measured using pre- and postoperative CT data. The absolute differences of cup alignment and 3D position were compared between DDH and non-DDH patients. Moreover, these differences were analyzed in relation to the severity of DDH. The discrepancy of leg length and combined offset compared with contralateral hip were measured. Results The mean values of absolute differences (postoperative CT-preoperative plan) were 1.7° (standard deviation (SD) 2.0) (inclination) and 2.5° (SD 2.1°) (anteversion) in DDH patients, and no significant differences were found between non-DDH and DDH patients. The mean absolute differences for 3D cup position were 1.1 mm (SD 1.0) (coronal plane) and 1.2 mm (SD 2.1) (axial plane) in DDH patients, and no significant differences were found between two groups. No significant difference was found either in cup alignment between postoperative CT and navigation record after cup screws or in the severity of DDH. Excellent restoration of leg length and combined offset were achieved in both groups. Conclusion We demonstrated that robotic-assisted THA may achieve precise cup positioning in DDH patients, and may be useful in those with severe DDH. Cite this article: Bone Joint Res 2021;10(10):629–638.

Human–robot collaboration is increasingly present not only in research environments, but also in industry and many contemporary day-to-day activities. There is a need for the automation of tasks ranging from the simplest to the most complex ones. The insertion of robotic arms provides a considerable step useful in achieving this goal. In this context, safety remains a concern, however. Among the most frequent issue in this collaboration context is human–robot collision. While focus has been on automation efficiency of the of the activities, there is a growing need to reduce or even prevent damage to the involved agents. As part of this goal, a new mechanism for detecting human–robot collisions is proposed in this article. It has been tested in a well-controlled scenario using equipment commonly present in collaborative scenarios for maintenance on a radio base station. The robot used is a UR5 robotic arm in addition to three 2D cameras and a network rack. In our experimental scenario, a person interacts with the network devices installed within the rack while conducting basic collaborative activities inserted in this context. For collision detection, deep learning models were used and evaluated. These were trained to detect overlap between humans and robots considering the view and perspectives from three different cameras. Finally, a new ensemble learning system is proposed in order to establish whether or not a collision took place. It receives as input the result of overlap detection through deep learning models. Results suggest that the proposed system is capable of detecting collisions with an average global accuracy of 89.81% of correctness in a well-controlled scenario. The effectiveness of the proposed ensemble is exposed in comparison with the use of only one of the cameras for decision-making. Finally, the proposed system is shown to detect collisions in real time and to achieve a low response time.

Automation technology has been extensively recognized as an emerging field in various industrial applications. Recent breakthrough in flexible automation is primarily due to deployment of robotic arms or manipulators. Autonomy in these manipulators is essentially linked with the advancements in non-linear control systems. The objective of this research is to propose a robust control algorithm for a five degree of freedom (DOF) robotic arm to achieve superior performance and reliability in the presence of friction. A friction compensation-based non-linear control has been proposed and realized for the robotic manipulator. The dynamic model of the robot has been derived by considering the dynamic friction model. The proposed three-state model is validated for all the joints of the manipulator. The integral sliding mode control (ISMC) methodology has been designed; the trajectories of system every time begin from the sliding surface and it eliminates the reaching phase with assistance of integral term in the sliding surface manifold. The designed control law has been first simulated in Matlab/Simulink environment to characterize the control performance in terms of tracking of various trajectories. The results confirm the effectiveness of the proposed control law with model-based friction compensation. The transient parameters like settling and peak time have improvement as well have better results with friction than without considering the friction. The proposed control law is then realized on an in-house developed autonomous articulated robotic rducational platform (AUTAREP) and NI myRIO hardware interfaced with LabVIEW. Experimental results also witnessed the trajectory tracking by the robotic platform.

In this paper, a low-cost prototype for humanoid robotic arm that is controlled by either voice, gesture or brain signals is introduced. The prototype consists of a robotic arm that can rotate around a vertical axis and a hand with five fingers, which animates approximately the movements of a human hand. This model can be operated by brainwave signals from a Neurosky MindWaveTM Mobile 2 Brainwave Sensing Headset, by human gesture using Leap Motion device, by voice command using Google Assistant, or by web-based interface. All operations can be monitored by a user interface on web server, with the support from a Raspberry Pi board. The experiments show that the average accuracy of our mindwave control prototype is about 83%, which is similar to most of previous high-cost solutions, and can go up to nearly 100% for the case that the data acquisition time is larger than 10 s (which improves 2–8% compared to previous works). This model would be highly useful in practice, especially, for people with disabilities who cannot use their hands, as well as in academia when it is used for undergraduate students’ experiments on robotics.

Nowadays, a laboratory operator in the areas of chemistry, biology or medicine spends considerable time performing micropipetting procedures, a common, monotonous and repetitive task which compromises the ergonomics of individuals, namely related to wrist musculoskeletal disorders. In this work, the design of a kinesthetic teaching approach for automating the micropipetting technique is presented, allowing to redirect the operator to other non-repetitive tasks, aiming to reduce the exposure to ergonomic risks. The proposed robotic solution has an innovative gripping system capable of supporting, actuating and regulating the volume of a manual micropipette. The system is able to configure the position of diverse laboratory materials, such as lab containers and plates, on the workbench through a collaborative robotic arm, providing flexibility to adapt to different procedures. A projected human-machine interface, which combines the display of information on the workbench with an infrared based interaction device was developed, providing a more intuitive interaction between the operator and the system during the configuration and operation phases. In contrast to the majority of the existing liquid handling systems, the proposed system allows the operator to place the materials freely on the workbench and the usage of different materials’ variants, facilitating the implementation of the system in any laboratory. The attained performance and ease of use of the system were very encouraging since all the defined tasks in the conducted experiments were successfully performed by users with minimum training, highlighting its potential inclusion in the laboratory routine panorama.

Automation of the industrial sector is increasing rapidly. Many industrial applications involve robotic manipulators in a networked environment with sensor and an actual plant via a communication channel. Control of the robot manipulator is a challenging task due to its nonlinearity and parameter uncertainty. However, due to the necessity of lesser bandwidth allocation and to eliminate network congestion, this paper focuses on the development of an event-triggered constrained next-generation robustness, tracking, disturbance rejection and, overall aggressiveness (RTDA) controller for a single link robot arm. The constraints on torque input and torque rate are considered and incorporated in the optimization problem using the Lagrange multiplier method. The proposed event-trigger based next-generation controller has simplicity, flexibility in tuning, and closed form solution similar to PID controllers and superior performance like predictive controllers. In addition, the incorporation of event-triggered mechanism has improved the bandwidth utilization. The performance of the proposed RTDA controller with and without event-triggered mechanism is compared with constrained DMC controller.

In the process of Human-robot skill transfer, we require the robot to reproduce the trajectory of teacher and expect that the robot can generalize the learned trajectory. For the trajectory after generalization, we expect that the robot arm can accurately track. However, because the model of the robot can not be accurately obtained, some researchers have proposed using a neural network to approximate the unknown term. The parameters of the traditional RBF neural network are usually selected through the empirical and trial-and-error method, which maybe biased and inefficient. In addition, due to the end-effector of the mechanical arm trajectory will be constantly changing according to the needs of the task, when the neural network of compact set cannot contain the whole input vector, the neural network cannot achieve the ideal approximation effect. In this paper, the broad neural network is used to approximate the unknown terms of the robot. This method can reuse the motion controller that has been learned and complete other motions in the robot operating space without relearning its weight parameters. In this paper, the effectiveness of the proposed method is proved by the ultrasound scanning task.

Robotics technology is used widely in minimally invasive surgery (MIS) which provides high performance and accuracy. The most famous robot arm mechanisms, which are used in MIS, are tendon-driven mechanism (TDM), and concentric tube mechanism (CTM). Unfortunately, these mechanisms until now have some limitations, i.e. making friction with the tissue during extracting and retracting and strain limits, for TDM and CTM respectively. A new hybrid concentric tube-tendon driven mechanism (HCTDM) is proposed to overcome these limitations. HCTDM enables the end-effector to get close to and get away from the surgical area during the operation without harming the tissue and with more flexibility. In addition to that, the workspace increases as a result of this combination, too. This benefit serves MIS, especially endoscopic surgeries (ESs). We did an analytical study of this idea and got the forward kinematics. In the inverse kinematics, an intelligent approach which is called an adaptive neuro-fuzzy inference system (ANFIS) is used because the closed-form solution is more complicated for such these mechanisms. Finally, HCTDM is analyzed and evaluated by using a computer simulation. The simulation results show that the workspace becomes wider and has more dexterity than use TDM or CTM individually. Furthermore, various trajectories are used to test the mechanism and the kinematic analysis, which show the mechanism can follow and track the trajectories with maximum mean error 1.279, 0.7027, and [Formula: see text] for X, Y, and Z axes respectively.

Here we present two robotic sample changers integrated into the experimental stations for the macromolecular crystallography (MX) beamlines AMX and FMX, and the biological small-angle scattering (bioSAXS) beamline LiX. They enable fully automated unattended data collection and remote access to the beamlines. The system designs incorporate high-throughput, versatility, high-capacity, resource sharing and robustness. All systems are centered around a six-axis industrial robotic arm coupled with a force torque sensor and in-house end effectors (grippers). They have the same software architecture and the facility standard EPICS-based BEAST alarm system. The MX system is compatible with SPINE bases and Unipucks. It comprises a liquid nitrogen dewar holding 384 samples (24 Unipucks) and a stay-cold gripper, and utilizes machine vision software to track the sample during operations and to calculate the final mount position on the goniometer. The bioSAXS system has an in-house engineered sample storage unit that can hold up to 360 samples (20 sample holders) which keeps samples at a user-set temperature (277 K to 300 K). The MX systems were deployed in early 2017 and the bioSAXS system in early 2019.

We introduce a method to learn policies from expert demonstrations that are interpretable and manipulable. We achieve interpretability by modeling the interactions between high-level actions as an automaton with connections to formal logic. We achieve manipulability by integrating this automaton into planning via Logical Value Iteration, so that changes to the automaton have predictable effects on the learned behavior. These qualities allow a human user to first understand what the model has learned, and then either correct the learned behavior or zero-shot generalize to new, similar tasks. Our inference method requires only low-level trajectories and a description of the environment in order to learn high-level rules. We achieve this by using a deep Bayesian nonparametric hierarchical model. We test our model on several domains of interest and also show results for a real-world implementation on a mobile robotic arm platform for lunchbox-packing and cabinet-opening tasks.