关键词： artificial bee colony   object detection  

摘要： We propose a framework to detect lug position and orientation in robotics that is insensitive to the lug orientation, incorporating a proposed optimization based on the artificial bee colony genetic algorithm. Experimental results show that the proposed optimization method outperformed traditional artificial bee colony and other meta-heuristics in the considered cases and was up to 3 times faster than the traditional approach. The proposed detection framework provided excellent performance to detect lug objects for all test cases.

关键词： Educational robotics   Metacognition   Problem solving   Teacher guidance  

摘要： Educational robotics (ER) is an innovative learning tool that offers students opportunities to develop higher-order thinking skills. This study investigates the development of students' metacognitive (MC) and problem-solving (PS) skills in the context of ER activities, implementing different modes of guidance in two student groups (11-12 years old, N1 = 30, and 15-16 years old, N2 = 22). The students of each age group were involved in an 18-h group-based activity after being randomly distributed in two conditions: "minimal" (with minimal MC and PS guidance) and "strong" (with strong MC and PS guidance). Evaluations were based on the Metacognitive Awareness Inventory measuring students' metacognitive awareness and on a think-aloud protocol asking students to describe the process they would follow to solve a certain robot-programming task. The results suggest that (a) strong guidance in solving problems can have a positive impact on students' MC and PS skills and (b) students reach eventually the same level of MC and PS skills development independently of their age and gender.

关键词： Computing skills   embedded systems   engineering curriculum   industrial engineering   project-based learning   robotics   student assessment  

摘要： This paper describes the design of an industrial informatics course, following the project-based learning methodology, and reports the experience of four academic years (from 2012-13 to 2015-16). Industrial Informatics is a compulsory course taught in the third year of the ***. degree in industrial electronics and automation engineering at the University of the Basque Country (UPV/EHU), Spain. The course had students develop an embedded controller for a 2DoF SCARA robot that drew a specific trajectory. The robot was built with the LEGO Mindstorms kit and the controller was implemented with NXC, a C-like programming language for the NXT brick. In this activity, students became aware of their learning needs and had to work proactively, both autonomously and in teams. The course design achieved several objectives: 1) students learned the course material;2) soft skills demanded by employers were reinforced;and 3) the material was structured into project tasks for students to perform. The article analyses two indicators: 1) qualification marks and 2) student satisfaction.

关键词： Surgical robotics   Surface registration   Stereo vision   Neurosurgery  

摘要： Current markerless registration methods for neurosurgical robotics use the facial surface to match the robot space with the image space, and acquisition of the facial surface usually requires manual interaction and constrains the patient to a supine position. To overcome these drawbacks, we propose a registration method that is automatic and does not constrain patient position. An optical camera attached to the robot end effector captures images around the patient's head from multiple views. Then, high coverage of the head surface is reconstructed from the images through multi-view stereo vision. Since the acquired head surface point cloud contains color information, a specific mark that is manually drawn on the patient's head prior to the capture procedure can be extracted to automatically accomplish coarse registration rather than using facial anatomic landmarks. Then, fine registration is achieved by registering the high coverage of the head surface without relying solely on the facial region, thus eliminating patient position constraints. The head surface was acquired by the camera with a good repeatability accuracy. The average target registration error of 8 different patient positions measured with targets inside a head phantom was , while the mean surface registration error was . The method proposed in this paper achieves automatic markerless registration in multiple patient positions and guarantees registration accuracy inside the head. This method provides a new approach for establishing the spatial relationship between the image space and the robot space.

关键词： Multi-agent systems   Virtual environments   Evolutive algorithms  

摘要： This paper presents a framework specially designed for the execution and adaptation of Intelligent Virtual Environments. This framework, called JaCalIVE, facilitates the development of this kind of environments managing in an efficient and realistic way the evolution of parameters for the adaptation of the physical world. The framework includes a design method and a physical simulator which is in charge of giving the Intelligent Virtual Environment the look of the real or physical world, allowing to simulate physical phenomena such as gravity or collision detection. The paper also includes a case study which illustrates the use of the proposed framework as an evolutive algorithm which allows the automatic adaptation of modular robots. (C) 2017 Elsevier B.V. All rights reserved.

关键词： External disturbances   Neural network models   Parallel robot manipulators   Real-time kinematic control problem   Robust solution   Zeroing neural-dynamics approach  

摘要： This paper proposes a zeroing neural-dynamics (ZND) approach as well as its associated model for solving the real-time kinematic control problem of parallel robot manipulators. Unlike existing works relying on the plausibly impractical assumption that neural network models are free of external disturbances, the proposed model features the suppression of multiple disturbances in addition to its nonlinear processing and control. Theoretical analyses prove that the ZND approach and its associated model inherently possess robustness. In addition, by using an appropriate activation function, the rapid convergence performance of the corresponding ZND model is further achieved. Simulation studies and comprehensive comparisons substantiate the effectiveness, robustness and superiority of the proposed ZND approach as well as its associated model for solving the real-time kinematic control problem of parallel robot manipulators against the superposition of multiple disturbances. Moreover, results of extensive tests verify that the processing of the ZND model can be accelerated by using an appropriate activation function. (c) 2017 Elsevier B.V. All rights reserved.

关键词： 口腔正畸   机器人学   诊疗   治疗效果   多学科交叉   生物力学   综合治疗   经验模式  

摘要： 基于机器人学、生物力学及口腔正畸学等多学科交叉的精准口腔正畸诊疗机器人，将从多个方面提高正畸治疗效果、降低综合治疗成本，从而推动临床口腔正畸诊疗从经验模式提升到精准模式，最终实现在合理的时间内给予患者个性化、可预测的口腔正畸治疗。

关键词： 机器人竞赛   直线   运动轨迹   训练课   学校  

摘要： 自从加入学校机器人竞赛队后，我就被乐高机器人吸引，深深地喜欢上了它。在平时的训练课中，我发现机器人在多种情况下走直线时都会走偏，继而导致其运动轨迹不确定，难以完成相应的任务。

关键词： 可重构机器人   变形旋量   柔性悬臂梁   动力学分析  

摘要： 利用变形旋量理论建立了6自由度AS-MRobot可重构机器人操作柔性悬臂梁系统的动力学模型。首先,通过简化处理将系统分解为刚性可重构机器人和柔性悬臂梁两个部分,分别建立动力学模型;其次,利用雅可比矩阵特性建立整个系统的动力学模型。该方法克服了传统建模方法只能在二维平面内考虑柔性悬臂梁的单方向变形问题,实现了在三维空间内考虑柔性悬臂梁的拉伸、扭转与弯曲等变形问题。建立的动力学模型更加逼近真实,有利于解决工业实际应用中柔性负载振动问题。然后,建立了整个系统的仿真模型,通过对比可重构机器人操作刚性悬臂梁和操作柔性悬臂梁的动力学曲线,验证了系统动力学模型的正确性。最后,分析操作柔性悬臂梁动力学中驱动力/力矩、柔性变形和模态等数据曲线,总结出可重构机器人操作柔性悬臂梁的动力学特性。