关键词： Inspection   Probes   Service robots   Wireless fidelity   Hardware   Oscilloscopes   Electromagnetic acoustic transducer   non-destructive evaluation   wireless   acquisition system   robotics  

摘要： The deployment of transducers to perform in situ inspections of industrial components can be complicated, and in many cases is still performed manually by a team of operators, which involves significant costs and can be dangerous. Robots capable of deploying probes in difficult to access locations are becoming available. Electromagnetic acoustic transducers (EMAT) are well suited to be used with robots since they are non-contact transducers that do not require a coupling medium, and can easily perform scans. However, existing acquisition systems for EMATs are generally not suitable to be directly mounted on robots. In this paper, a new wireless acquisition system for EMATs is presented. The system is standalone, it transmits the inspection data over WiFi, and is compatible with the robotics operating system (ROS). In addition, it is designed to be modular, small and lightweight so that it can be easily mounted on robots. The system design in terms of hardware and software is described in this paper. The resulting performance of the system is also reported.

关键词： 学有余力   机器人竞赛   中小学校   中小学生   全国青少年   竞赛活动   组织竞赛   教育行政部门  

摘要： 前不久,教育部公布2020至2021学年面向中小学生的全国性竞赛活动名单:中国青少年机器人竞赛、全国青少年无人机大赛等35项竞赛列入其中。这也意味着,对于不在名单上的全国竞赛,地方各级教育行政部门、各中小学校、各类教育机构均不得组织承办。中小学生需不需要竞赛?答案是肯定的。组织竞赛的初衷在于给学有余力的学生设置“跑道”,让人才在你追我赶中冒出来。

关键词： 船舶运动控制   航迹保持控制   间接式控制   机器人学   闭环增益成形算法   carrot following算法  

摘要： Carrot following是一种间接式航迹保持算法,它找到期望航向后只使用简单的比例控制,因此航迹保持控制效果较差,为了在保持原方法简洁性的同时改善船舶的航迹保持效果,本文通过引入闭环增益成形算法对其控制率做了改进。间接式航迹保持控制能够使相关成果简单迁移到航迹保持问题中。仿真结果表明:所提出的间接式控制方法能够实现船舶的航迹保持,仿真下的稳态误差小于5 m,而航向保持中的许多技巧在航迹保持中依然适用。本文所提方法简洁有效,具有推广价值。

关键词： 机器人学   工程学   营养需求   澳大利亚   墨尔本  

摘要： 博特伦兄弟从澳大利亚墨尔本搬到美国之后,就爱上了工程学与机器人学--并立下了满足世界营养需求的远大目标。抵达加州之后不到十年,他们共同创办了一点一农业科技公司,以及威洛--他们直接面对消费者的健康与生活方式的品牌。

关键词： 阿西莫夫   人工智能技术   技术伦理   机器人学   科幻小说   技术异化   乐观主义者   技术创新  

摘要： 著名的科幻作家阿西莫夫研究了以往机器人题材的科幻小说,总结出机器人学三定律:第一定律提出,机器人不得伤害人,也不得见人受到伤害而袖手旁观;第二定律明确,机器人应服从人的一切命令,但不得违反第一定律;第三定律指出,机器人应保护自身的安全,但不得违反第一、二定律。一些技术乐观主义者认为,有了机器人学三定律,人类对技术创新特别是人工智能技术创新安全性问题的担忧就可以打消了。然而,他们对技术异化的警惕性远远不够。

关键词： Robotic palpation   Tactile sensing   Physical sensing   Sensory-motor coordination  

摘要： This paper proposes a framework to investigate the influence of physical interactions to sensory information, during robotic palpation. We embed a capacitive tactile sensor on a robotic arm to probe a soft phantom and detect and classify hard inclusions within it. A combination of PCA and K-Means clustering is used to: first, reduce the dimensionality of the spatiotemporal data obtained through the probing of each area in the phantom;second categorize the re-encoded data into a given number of categories. Results show that appropriate probing interactions can be useful in compensating for the quality of the data, or lack thereof. Finally, we test the proposed framework on a palpation scenario where a Support Vector Machine classifier is trained to discriminate amongst different types of hard inclusions. We show the proposed framework is capable of predicting the best-performing motion strategy, as well as the relative classification performance of the SVM classifier, solely based on unsupervised cluster analysis methods.

关键词： Educational robotics   Social robotics   Motivation to study robotics  

摘要： Nowadays robotics is one of promising avenues in the sphere of emerging technologies. In the teaching/learning environment we deal with educational robotics, which is a mixture of theory and practice, knowledge of computer technology, Mathematics and Physics. The two vectors are combined in educational robotics: the educational vector and the technological vector. As an academic discipline and an area of practical application, Robotics means a very broad spectrum of modern knowledge of diverse academic engineering specialties (fields of expertise). That means that Robotics is interdisciplinary in nature. The work provides an overview of the research aimed at studying Robot - Man interaction. Besides, the work considers some promising international cooperation between children from around the world on the development of robotics, and the experience and benefits gained from such cooperation. As an example of the international cooperation in the sphere of Robotics, the two countries, Russia and Kazakhstan, are considered. The article gives an example of the international cooperation of some educational centers, describes the experience of the work on robotics with children of various ages, and the cooperation of various schools working in this field in Kazakhstan and Russia. The working experience in the sphere of social robotics aimed at helping people has become a priority for the children from the interdisciplinary teams from Russia and Kazakhstan. Interaction and cooperation in the sphere of robotics was also used for introducing unconventional curricula, which included courses on robotic technologies as tools for considering social aspects of robotics and artificial intelligence.

关键词： chord recognition   multi-task learning   guitar-playing robot   convolutional neural network   data augmentation  

摘要： In recent years, many researchers have shown increasing interest in music information retrieval (MIR) applications, with automatic chord recognition being one of the popular tasks. Many studies have achieved/demonstrated considerable improvement using deep learning based models in automatic chord recognition problems. However, most of the existing models have focused on simple chord recognition, which classifies the root note with the major, minor, and seventh chords. Furthermore, in learning-based recognition, it is critical to collect high-quality and large amounts of training data to achieve the desired performance. In this paper, we present a multi-task learning (MTL) model for a guitar chord recognition task, where the model is trained using a relatively large-vocabulary guitar chord dataset. To solve data scarcity issues, a physical data augmentation method that directly records the chord dataset from a robotic performer is employed. Deep learning based MTL is proposed to improve the performance of automatic chord recognition with the proposed physical data augmentation dataset. The proposed MTL model is compared with four baseline models and its corresponding single-task learning model using two types of datasets, including a human dataset and a human combined with the augmented dataset. The proposed methods outperform the baseline models, and the results show that most scores of the proposed multi-task learning model are better than those of the corresponding single-task learning model. The experimental results demonstrate that physical data augmentation is an effective method for increasing the dataset size for guitar chord recognition tasks.

关键词： Multi-agent models   Self-organisation   D   discoideum   Quorum sensing   Swarm robotics   Kilobots  

摘要： By studying and modelling the behaviour of Dictyostelium discoideum, we aim at deriving mechanisms useful for engineering collective artificial intelligence systems. This paper discusses a selection of agent-based models reproducing second-order behaviour of Dictyostelium discoideum, occurring during the migration phase;their corresponding biological illustrations;and how we used them as an inspiration for transposing this behaviour into swarms of Kilobots. For the models, we focus on: (1) the transition phase from first- to second-order emergent behaviour;(2) slugs' uniform distribution around a light source;and (3) the relationship between slugs' speed and length occurring during the migration phase of the life cycle of D. discoideum. Results show the impact of the length of the slug on its speed and the effect of ammonia on the distribution of slugs. Our computational results show similar behaviour to our biological experiments, using Ax2(ka) strain. For swarm robotics experiments, we focus on the transition phase, slugs' chaining, merging and moving away from each other.

关键词： Optimal control   Mobile robots   Task analysis   Dynamical systems   Training   Real-time systems   Autoassembly mobile robot   Lyapunov techniques   path following   path integral   reinforcement learning (RL)  

摘要： Reinforcement learning (RL) combined with deep neural networks has led to a number of great achievements for robot control in virtual computer environments, where sufficient data can be obtained without any difficulty to train various models. However, thus far, only few and relatively simple tasks have been accomplished for practical robots, which is mainly caused by the following two reasons. First, training with real robots, especially with dynamic systems, is too complicated to be fully and accurately represented in simulations. Second, it is very costly to obtain training data from real systems. To address these two problems effectively, in this article, a path-integral-based RL algorithm is proposed for the task of path following of an autoassembly mobile robot, wherein three kernel techniques are introduced. First, a generalized path-integral-control approach is proposed to obtain the numerical solution of a stochastic dynamical system, wherein the calculation of the gradient and kinematics inverse is avoided to ensure fast and reliable training convergence. Second, a novel parameterization method using Lyapunov techniques is introduced into the RL algorithm to ensure good performance of the system when directly transferring simulation results into practical systems. Third, the optimal parameters for all discrete initial states are first learned offline and then tuned online to improve the generalization and real-time performance. In addition to the optimization control for the mobile robot, the proposed method also possesses general applicability for a class of nonlinear systems such as crane systems. Simulation and experimental results are included and analyzed to illustrate the superior performance of the proposed algorithm.