关键词： Robot health monitoring   Industrial robot   PHM   Machine learning   Augmented reality  

摘要： In this manuscript we report on a vision-based data-driven methodology for industrial robot health assessment. We provide an experimental evidence of the usefulness of our methodology on a system comprised of a 6-axis industrial robot, two monocular cameras and five binary squared fiducial markers. The fiducial marker system permits to accurately track the deviation of the end-effector along a fixed non-trivial trajectory. Moreover, we monitor the trajectory deflection using three gradually increasing weights attached to the end-effector. When the robot is loaded with the maximum allowed payload, a deviation of 0.77mm is identified in the Z-coordinate of the end-effector. Tracing trajectory information, we train five supervised learning regression models. Such models are afterwards used to predict the deviation of the end-effector, using the pose estimation provided by the visual tracking system. As a result of this study, we show that this procedure is a stable, robust, rigorous and reliable tool for robot trajectory deviation estimation and it even allows to identify the mechanical element producing non-kinematic errors.

关键词： dexterous manipulation   adaptive and robust control   deep reinforcement learning   imitation learning   transfer learning  

摘要： Dexterous manipulation of the robot is an important part of realizing intelligence, but manipulators can only perform simple tasks such as sorting and packing in a structured environment. In view of the existing problem, this paper presents a state-of-the-art survey on an intelligent robot with the capability of autonomous deciding and learning. The paper first reviews the main achievements and research of the robot, which were mainly based on the breakthrough of automatic control and hardware in mechanics. With the evolution of artificial intelligence, many pieces of research have made further progresses in adaptive and robust control. The survey reveals that the latest research in deep learning and reinforcement learning has paved the way for highly complex tasks to be performed by robots. Furthermore, deep reinforcement learning, imitation learning, and transfer learning in robot control are discussed in detail. Finally, major achievements based on these methods are summarized and analyzed thoroughly, and future research challenges are proposed.

关键词： Knee   Robotics   Total knee arthroplasty   Prosthesis  

摘要： The recent introduction of new robotic systems for total knee arthroplasty (TKA) has created somewhat of a craze. Nevertheless, we can ask ourselves whether it is justified to use these new but very costly technologies. The results and limitations of these robotic tools must be analyzed systematically before confirming their benefits. Most of the newest robotic systems are interactive ones. These systems can accurately restore the mechanical axis and can improve the ligament balance and implant positioning. Theoretically, this can lead to better survival, function and outcomes. Recent studies have shown that use of robotics for TKA implantation does not increase the surgery time and does not cause more complications. Nevertheless, the long-term advantages of robotics use in this context remains to be proven. This task will be more difficult since there is currently no consensus as to the ideal positioning of TKA implants for a given patient. The aim of this study is to summarize this topic by answering the following questions: What are the different types of robots that can be used for TKA implantation? Which steps of the TKA surgical procedure are done with robotic arm assistance? What are the outcomes of these new implantation techniques? What are the limitations of these new implantation techniques? (C) 2020 Published by Elsevier Masson SAS.

关键词： Digital agriculture   Robotics   Automation   Artificial intelligence   Anticipation   Responsible research and innovation   Apples   Assemblage   More-than-human  

摘要： With the growth of new collaborative design (co-design) strategies for technology development, and increasing media attention on future automation of the farm, food producers are aware of new robotics on the horizon. This paper will discuss how apple growers are anticipating new robotic technologies intended to use artificial intelligence (AI) to automate aspects of the farm, paying particular attention to the ways that anticipation relates to preparatory assembling and reassembling of landscapes, work, and institutions. Our analysis considers the varying ways growers are practically assembling their orchards in anticipation of new technologies, and how their actions map onto ecological systems, labour relations, and farm capitalization. Our findings reveal some of the challenges to democratic forms of engagement with a robotic future, as well as some of the ways that growers enhance their capacity to engage meaningfully with new technologies.

关键词： Minimally invasive surgery   Pediatric robotic surgery   Pediatric urologic reconstruction   Ureteropelvic junction obstruction   Vesicoureteral reflux   Bladder augmentation  

摘要： Almost 30 years have passed since the inception of minimally invasive surgery in urology and specifically in pediatric urology. Laparoscopy has now become an essential tool in the pediatric urologic armamentarium. The application of robot-assisted surgery in pediatrics has allowed for widespread utilization for common reconstructive procedures such as pyeloplasty and ureteral reimplantation. Understanding the implementation, technical considerations, and outcomes are critical for continued success and adoption. This has allowed for increased use in more complex urologic procedures such as redo pyeloplasty, dismembered ureteral reimplantation, catheterizable channel creation, and bladder augmentation.

关键词： STEAM   LEGO Mindstorms   EV3   MATLAB   Simulink   computer science   robotics   computational thinking  

摘要： Over the last years, mobile robot platforms are having a key role in education worldwide. Among others, LEGO Robots and MATLAB/Simulink are being used mainly in universities to improve the teaching experience. Most LEGO systems used in the literature are based on NXT, as the EV3 version is relatively recent. In contrast to the previous versions, the EV3 allows the development of real-time applications for teaching a wide variety of subjects as well as conducting research experiments. The goal of the research presented in this paper was to develop and validate a novel real-time educational platform based on the MATLAB/Simulink package and the LEGO EV3 brick for academic use in the fields of robotics and computer science. The proposed framework is tested here in different university teaching situations and several case studies are presented in the form of interactive projects developed by students. Without loss of generality, the platform is used for testing different robot path planning algorithms. Classical algorithms like rapidly-exploring random trees or artificial potential fields, developed by robotics researchers, are tested by bachelor students, since the code is freely available on the Internet. Furthermore, recent path planning algorithms developed by the authors are also tested in the platform with the aim of detecting the limits of its applicability. The restrictions and advantages of the proposed platform are discussed in order to enlighten future educational applications.

关键词： Evolutionary robotics   neural networks   simulator neural networks   proprioception   path integration  

摘要： Taking inspiration from the navigation ability of humans, this study investigated a method of providing robotic controllers with a basic sense of position. It incorporated robotic simulators into robotic controllers to provide them with a mechanism to approximate the effects their actions had on the robot. Controllers with and without internal simulators were tested and compared. The proposed controller architecture was shown to outperform the regular controller architecture. However, the longer an internal simulator was executed, the more inaccurate it became. Thus, the performance of controllers with internal simulators reduced over time unless their internal simulator was periodically corrected.

关键词： Impedance   Force   Dynamics   Robot kinematics   IEEE transactions   Mechatronics   Markovian jump linear systems (MJLS)   robotic rehabilitation   robust control   robust estimation  

摘要： In this article, we deal with rehabilitation robot robust control in order to obtain best performance in the human-robot interaction. This class of system is subject to abrupt changes due to exogenous inputs and parameter variations caused, mainly, by the human dynamic behavior. In this context, Markovian jump linear systems offer suitable tools to model and control of this class of interactions. We propose force and impedance controllers based on robust recursive Markovian versions of the standard Kalman filter and the linear quadratic regulator. Different levels of the individual's actuation during the interaction with the robot define the Markov states. The measurement of electromyographic signals is used as jump parameter among Markov states. Also, a serious game is used to generate visual feedback, to promote active user participation, and to guide his movement routine. We compare our proposal with two other Markovian-based approaches and show the effectiveness our method through experiments with an ankle rehabilitation platform.

关键词： Pearl millet   Pennisetum glaucum (L   ) R   Br   Autonomous   robotic weeders   physical weed control   robotics  

摘要： Agricultural weeds remain an important production constraint, with labor shortages and a lack of new herbicide options in recent decades making the problem even more acute. Robotic weeding machines are a possible solution to these increasingly intractable weed problems. Franklin Robotics' Tertill((TM)) is an autonomous weeding robot designed for home gardeners that relies on a minimalistic design to be cost-effective. The objectives of this study were to investigate the ability of the Tertill to control broadleaf and grass weeds, and based on early observations, experiments were conducted with and without its string-trimmer-like weeding implement. Tertill demonstrated high weed-control efficacy, supporting its utility as a tool for home gardeners. Weeds were best controlled by the combined effect of soil disturbance caused by the action of the robot's wheels and the actuation of the string trimmer. Despite the regrowth potential of an annual grass due to its meristem location, Tertill maintained low densities of millet in an experimental arena. The simple and effective design of the Tertill may offer insights to inform future development of farm-scale weeding robots. Weed density, emergence periodicity, robot working rate, and robotic weeding mechanisms are important design criteria regardless of the technology used for plant detection.