关键词： Catastrophic forgetting   State primitives   Robotics   Continual learning  

摘要： People can learn continuously a wide range of tasks without catastrophic forgetting. To mimic this functioning of continual learning, current methods mainly focus on studying a one-step supervised learning problem, e.g., image classification. They aim to retain the performance of previous image classification results when neural networks are sequentially trained on new images. In this paper, we concentrate on solving multi-step robotic tasks sequentially with the proposed architecture called state primitive learning. By projecting the original state space into a low-dimensional representation, meaningful state primitives can be generated to describe tasks. Under two kinds of different constraints on the generation of state primitives, control signals corresponding to different robotic tasks can be separately addressed only with an efficient linear regression. Experiments on several robotic manipulation tasks demonstrate the new method efficacy to learn control signals under the scenario of continual learning, delivering substantially improved performance over the other comparison methods.

关键词： Special issues and sections   Robots   COVID-19   Pandemics   Business   Market opportunities   Investment   Humand factors   Social factors   Automation  

摘要： The articles in this special section focus on how the COVID-19 pandemic has and will continue to impact the robotics industry.

关键词： Robotics  

关键词： Ambient assisted living technologies   Dementia   Elderly care   Internet-of-things security   Social robotics  

摘要： Nowadays, longevity studies have become a distinguished multidisciplinary field merging with cutting-edge computer science technologies to outline innovative ideas to cater to the needs of seniors. Since the global geriatric population is anticipated to rise, the number of people seeking to obtain caregiving services and wishing to be more actively engaged in life will be more apparent. Therefore, seniors aspiring day-to-day special care in home settings, interested in improving their living standards can likewise benefit from an amiable companion. A comprehensive search strategy was developed and selected databases were looked through with relevant keywords. This scoping review qualitatively examines the literature on the use of companion robots, including both pet-like and humanoid robots, and Internet-of-Things (IoT) security, coupled with the new 5G technology for the home-based elder care. From 355 full-text articles that were found, 90 articles were selected to be investigated respectively. In order to ascertain their operation in the future, we discuss remaining challenges, unused opportunities, security risks and suggested remedies and suggest a dementia-centred concept and an implementation framework.

关键词： COVID-19   Pandemics   Robots   Service robobts   Market opportunities   Testing   Mobile robots   Telerobotics   Human factors   Social factors  

摘要： Examines how the COVID-19 pandemic has impacted the robotics industry. Although it might appear the pandemic has ushered in the age of robotics, we are still far from universal service robots that can truly help us overcome infrastructure shortcomings in hospitals, nursing homes, and the testing facilities of diagnostic laboratories. This situation is even more pressing as shelter-in-place orders and social distancing regulations further diminish the workforce. If we really want to make a difference here, we need to act more decisively and boldly take our robotic solutions out of the labs and into the real world.

关键词： Medical systems   COVID-19   Robot sensing systems   Robot kinematics   Vaccines   Pandemics   Medical robotics   Digital systems  

摘要： The use of robotics in health care has seen a recent rise in interest due to its potential for use during the SARS-CoV-2 pandemic. The transmission rate of COVID-19 has meant that health-care workers are under increasing pressure, risks, and workload to manage the requirements of personal protective equipment, strict disinfection procedures, and the heightened medical needs of patients. Patients are suffering from isolation, and not just in hospitals: higher-risk individuals must shelter, meaning social interactions, particularly in care homes, are limited. Robots can help by providing disinfection and logistics services that support patients and health-care professionals, by acting as devices to be used for rehabilitation at home (for both pre-existing conditions and for COVID-19-related treatment), and via interventional systems that can widely distribute future vaccinations.

摘要： Presents information on various RAS Society chapters.

关键词： Soft robotics   Computational modeling   Large-scale systems   Numerical models   Stability analysis   Trajectory tracking   Large-scale systems   model-order reduction   robust control   soft robotics  

摘要： This article presents new results to control process modeled through linear large-scale systems. Numerical methods are widely used to model physical systems, and the finite-element method is one of the most common methods. However, for this method to be precise, it requires a precise spatial mesh of the process. Large-scale dynamical systems arise from this spatial discretization. We propose a methodology to design an observer-based output feedback controller. First, a model reduction step is used to get a system of acceptable dimension. Based on this low-order system, two linear matrix inequality problems provide us, respectively, with the observer and controller gains. In both the cases, model and reduction errors are taken into account in the computations. This provides robustness with respect to the reduction step and guarantees the stability of the original large-scale system. Finally, the proposed method is applied to a physical setup-a soft robotics platform-to show its feasibility.

关键词： Cooperative learning   Pair programming   Robotics education   Pair learning   Roles assignment   Learning style  

摘要： Pair learning (PL) in robotics education is derived from pair programming, and impacted by many factors. Two important factors were identified including roles assignment and learning styles in this study. The roles assignment involved Driver-Navigator Pair and Software-Hardware Pair. For the learning style, the dimension of active/reflective was adopted. Therefore, a 2*3 factorial design was employed with the between-subjects factors roles assignment and learning styles. After a one-semester robotics course, we evaluated 66 fifth-grade students' learning achievements, attitude towards robotics, engagement, mental efforts, compatibility, and attitude towards PL. The results indicated that there was no statistically significant difference among different pairs in the above six indicators. Moreover, there was no significant difference in the learning outcomes among pairs of different learning styles. One important explanation is that the joint effect of PL might bridge the difference in learning performance that may be caused by learning style.

关键词： Soccer robotics   Deep learning   Convolutional neural networks   Robot detection   Ball detection   Robot orientation determination  

摘要： The goal of this paper is to describe a vision system for humanoid robot soccer players that does not use any color information, and whose object detectors are based on the use of convolutional neural networks. The main features of this system are the following: (i) real-time operation in computationally constrained humanoid robots, and (ii) the ability to detect the ball, the pose of the robot players, as well as the goals, lines and other key field features robustly. The proposed vision system is validated in the RoboCup Standard Platform League, where humanoid NAO robots are used. Tests are carried out under realistic and highly demanding game conditions, where very high performance is obtained: a robot detection accuracy of 94.90%, a ball detection accuracy of 97.10%, and a correct determination of the robot orientation 99.88% of the times when the observed robot is static, and 95.52% when the robot is moving.