关键词： user profiling   rehabilitation   social robot   machine learning  

摘要： Physical rehabilitation therapies for children present a challenge, and its success-the improvement of the patient's condition-depends on many factors, such as the patient's attitude and motivation, the correct execution of the exercises prescribed by the specialist or his progressive recovery during the therapy. With the aim to increase the benefits of these therapies, social humanoid robots with a friendly aspect represent a promising tool not only to boost the interaction with the pediatric patient, but also to assist physicians in their work. To achieve both goals, it is essential to monitor in detail the patient's condition, trying to generate user profile models which enhance the feedback with both the system and the specialist. This paper describes how the project NAOTherapist-a robotic architecture for rehabilitation with social robots-has been upgraded in order to include a monitoring system able to generate user profile models through the interaction with the patient, performing user-adapted therapies. Furthermore, the system has been improved by integrating a machine learning algorithm which recognizes the pose adopted by the patient and by adding a clinical reports generation system based on the QUEST metric.

关键词： Rehabilitation robotics   Assessment   Machine learning   Musculoskeletal diseases   Compensation and redress  

摘要： Introduction Occupational rehabilitation often involves functional capacity evaluations (FCE) that use simulated work tasks to assess work ability. Currently, there exists no single, streamlined solution to simulate all or a large number of standard work tasks. Such a system would improve FCE and functional rehabilitation through simulating reaching maneuvers and more dexterous functional tasks that are typical of workplace activities. This paper reviews efforts to develop robotic FCE solutions that incorporate machine learning algorithms. Methods We reviewed the literature regarding rehabilitation robotics, with an emphasis on novel techniques incorporating robotics and machine learning into FCE. Results Rehabilitation robotics aims to improve the assessment and rehabilitation of injured workers by providing methods for easily simulating workplace tasks using intelligent robotic systems. Machine learning-based approaches combine the benefits of robotic systems with the expertise and experience of human therapists. These innovations have the potential to improve the quantification of function as well as learn the haptic interactions provided by therapists to assist patients during assessment and rehabilitation. This is done by allowing a robot to learn based on a therapist's motions ("demonstrations") what the desired workplace activity ("task") is and how to recreate it for a worker with an injury ("patient"). Through Telerehabilitation and internet connectivity, these robotic assessment techniques can be used over a distance to reach rural and remote locations. Conclusions While the research is in the early stages, robotics with integrated machine learning algorithms have great potential for improving traditional FCE practice.

关键词： Artificial intelligence   Endovascular   Cerebrovascular   Telerobotics   Tele-surgery   Robotic surgery  

摘要： In the last forty years, the field of medicine has experienced dramatic shifts in technology-enhanced surgical procedures - from its initial use in 1985 for neurosurgical biopsies to current implementation of systems such as magnetic-guided catheters for endovascular procedures. Systems such as the Niobe Magnetic Navigation system and CorPath GRX have allowed for utilization of a fully integrated surgical robotic systems for perioperative manipulation, as well as tele-controlled manipulation systems for telemedicine. These robotic systems hold tremendous potential for future implementation in cerebrovascular procedures, but lack of relevant clinical experience and uncharted ethical and legal territory for real-life tele-robotics have stalled their adoption for neurovascular surgery, and might present significant challenges for future development and widespread implementation. Yet, the promise that these technologies hold for dramatically improving the quality and accessibility of cerebrovascular procedures such as thrombectomy for acute stroke, drives the research and development of surgical robotics. These technologies, coupled with artificial intelligence (AI) capabilities such as machine learning, deep-learning, and outcome-based analyses and modifications, have the capability to uncover new dimensions within the realm of cerebrovascular surgery. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Deep learning   Convolutional neural networks   Robot assisted surgery   Shared control   Orientation estimation   Fetoscopy  

摘要： Purpose Twin-to-twin transfusion syndrome (TTTS) is a placental defect occurring in monochorionic twin pregnancies. It is associated with high risks of fetal loss and perinatal death. Fetoscopic elective laser ablation (ELA) of placental anastomoses has been established as the most effective therapy for TTTS. Current tools and techniques face limitations in case of more complex ELA cases. Visualization of the entire placental surface and vascular equator;maintaining an adequate distance and a close to perpendicular angle between laser fiber and placental surface are central for the effectiveness of laser ablation and procedural success. Robot-assisted technology could address these challenges, offer enhanced dexterity and ultimately improve the safety and effectiveness of the therapeutic procedures. Methods This work proposes a 'minimal' robotic TTTS approach whereby rather than deploying a massive and expensive robotic system, a compact instrument is 'robotised' and endowed with 'robotic' skills so that operators can quickly and efficiently use it. The work reports on automatic placental pose estimation in fetoscopic images. This estimator forms a key building block of a proposed shared-control approach for semi-autonomous fetoscopy. A convolutional neural network (CNN) is trained to predict the relative orientation of the placental surface from a single monocular fetoscope camera image. To overcome the absence of real-life ground-truth placenta pose data, similar to other works in literature (Handa et al. in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016;Gaidon et al. in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016;Vercauteren et al. in: Proceedings of the IEEE, 2019) the network is trained with data generated in a simulated environment and an in-silico phantom model. A limited set of coarsely manually labeled samples from real interventions are added to the training dataset to improve d

关键词： Parameter estimation   Fish-inspired robotics   Underwater robotics   Optimization   Anguilliform-inspired robot  

摘要： This paper presents an optimization-based approach to estimate the hydrodynamic parameters namely drag and added mass coefficients from free-running experiments conducted on an in-house developed Anguilliform-inspired robot. The objective of the optimization problem is to estimate the hydrodynamic parameters that minimize the differences between the trajectories obtained from the simulations and the physical experiments when operated for identical gait parameters and controller gains for both the straight and the turning motions. The hydrodynamic parameters obtained from the developed approach leads to a maximum root-mean-square (RMS) position error of 0.183 BL and a maximum RMS velocity error of 0.03 BL/s between the trajectories obtained from simulations and experiments. Experimental results suggest that the parameters estimated using the developed approach can be useful in predicting the robot's motion accurately. Accurate robot motion prediction is the fundamental requirement for localization, collision prediction, and motion planning algorithms which in turn are required for automated inspection, maintenance, and repair of sub-sea structures using Anguilliform-inspired robots.

关键词： Robot   Industrial robot system safety   Risk assessment   Collaborative   Safety standards  

摘要： • Collaborative robotics is paradigm shift in industrial robot system safety. • Collaborative robotics can permit closer work between people and robots. • Risk assessment is a crucial tool for collaborative robot system safety. • There are four types of collaborative robotic operations. • ANSI/RIA R15.06-2012 and its TRs specify safety requirements for industrial robots. [ABSTRACT FROM AUTHOR]

关键词： Contact force   Foot section shape   Multibody dynamics   Hexapod robot   Sinking in soft soil  

摘要： Hexapod robots have attracted attention for their excellent terrain adaptabilities. When a robot walks on soft soil, dynamic subsidence and slippage greatly reduce its walking performance. The influence of foot's shape is usually ignored or simply studied without considering the multibody dynamics of the robot. This study is focused on the influence of the foot shape on the walking performance of a robot by coupling the sinkage with multibody dynamics. A composite contact model based on the Bekker, spring-damping, and Janosi-Hanamoto models was used to model the interaction of the robot and soft soil. Non-uniform rational B-spline (NURBS) surface and mesh were used to describe the geometries of foot and soft soil, respectively. The influences of three foot shapes on the sinkage and walking stability of the robot were analyzed by comparsion. The improved X-shaped foot reduced the robot's sinkage and improved its walking stability.

关键词： In-space assembly   Transportation robot   Flexible module   Large translational and rotational maneuver   Coupling dynamics  

摘要： There are two major characteristics of in-space structure assembly missions. First, in order to improve the transport efficiency of assembly robot and reduce the number of structural modules, the size of each structural module is usually designed as large as possible. Second, it is necessary for autonomous assembly robot to quickly transport such large-sized flexible structural modules to the desired locations for integration. However, the coupling effect between the deformation of structural module and large-scale maneuver of robot is inevitably involved during transportation. In this paper, a dynamics modeling method for in-space assembly (ISA) robot with large translational and rotational maneuvers was proposed. The descriptions of dual quaternions were expanded, and a general expression for the dynamics model of rigid-flex system was derived to describe motion of the assembly robot. Innovation of this method is that it considered the complex coupling effect among deformation of structural modules, translational and rotational maneuvers of the assembly robot during transportation in ISA missions. On this basis, the proportional-derivative (PD) controllers were adopted as the in-space structural module assembly method. Finally, taking the ISA of antenna as an example, successful application of the proposed dynamics model and controller to the assembly mission was verified.

关键词： computer-assisted surgery   interventional endoscopy   navigation   surgical robots   telemanipulation  

摘要： Purpose of review Advanced endoscopy procedures are technically challenging and require extensive training. Recent technological advances made in computer science and robotics have the potential to enhance the performance of complex intraluminal and transluminal interventions and potentially optimize precision and safety. This review covers the different technologies used for robot-assisted interventions in the gastrointestinal tract, organized according to their clinical availability, and focusing on flexible endoscopy-based systems. Recent findings In the curvilinear gastrointestinal anatomy, robotic technology can enhance flexible endoscopes to augment effectiveness, safety, and therapeutic capabilities, particularly for complex intraluminal and transluminal interventions. Increased visual angles, increased degrees of freedom of instrumentation, optimized navigation, and locomotion, which may lead to a reduced physician learning curve and workload, are promising achievements with the promise to ultimately replace conventional endoscopy techniques for screening and therapeutic endoscopy. The majority of these devices are not commercially available yet. The best clinical applications are also currently being researched. Nonetheless, robotic assistance may encourage surgeons to use flexible endoscopes to administer surgical therapies and increase interest among gastroenterologists in advanced therapies. Robotics may be a means to overcome the technical obstacles of incisionless natural orifice procedures and favor an increased adoption of complex endoscopic procedures such as third-space therapies.

关键词： Thematic integration   Task-based instruction   Integrative curriculum   Integrative STEM   Robotics  

摘要： The study aimed to develop a cross-disciplinary integrative STEM (i-STEM) robotics curriculum by the thematic integration approaches of webbed and threaded models, and to understand high school students' cognitions, attitudes, and interests in robotics STEM after the instruction. The concurrent mixed methods including quantitative experimental design and embedded qualitative design were adopted in the present study. Participants were 42 students, with 17 females and 25 males in a high school class. The students were grouped with 2 members in each group, and there were totally 21 groups. The results revealed that cognition for seven fields were significantly improved. Among the seven fields, sailboat design improved the most, while mathematics and computer programming improved the least. The students' attitudes and interests in robotics STEM were significantly enhanced. The students' interests in engineering design were significantly enhanced the most, programming was the second;continuous study of engineering, science, or technology was the third;jobs related to engineering or programming was the fourth;and robotics was the least enhanced. Finally, the implications for teacher teaching and student learning practices were proposed.