关键词： 机器人   输电线   铁塔   ADAMS   动力学  

摘要： 针对输电线路机器人在线作业或移动时状态不清晰的问题,研究输电线、机器人以及铁塔的刚柔耦合动力学响应。首先,通过UG软件创建铁塔、机器人三维实体模型,采用连续体法建立输电线三维模型,并设置装配约束关系。然后,模型导入ADAMS软件,并定义柔、刚体。最后,仿真得到机器人质心与输电线中点在XYZ方向的速度与加速度,以及机器人内部电机的力矩变化。将软件仿真得到的机器人质心位移与电机力矩的曲线与数值模型仿真结果进行比对,分析其结果差异率,进一步明确柔性输电线与刚性机器人之间的动力学关系,可为输电线路机器人的优化设计提供理论参考。

关键词： 人工智能   智能推荐   机器学习   数据挖掘   人脸识别   模式识别   机器人学   医学影像  

摘要： 人工智能是通过机器实现人的行为和思考模式的模拟以及扩展的一门新兴技术。自1956年斯坦福大学的约翰.麦肯锡第一次提出人工智能的概念后,人工智在短短几十年间经历了迅速的发展,逐渐衍生出了模式识别、机器学习、数据挖掘、机器人学等多项分支技术,并在无人驾驶、人脸识别、智能推荐等多个热门研究领域上得到了广泛的应用,为我们的生活带来了极大的便利。

关键词： 机器人教育   核心素养   创客教育   机器人竞赛   科研机构   教育课程体系   教学资源   综合能力的培养  

摘要： 机器人教育作为STEM教育、人工智能教育和创客教育的重要内容和有效途径,对培养和提高学生的综合素质和核心素养具有重要意义。VEX机器人竞赛作为开展机器人教育的平台,由众多团体和大学科研机构联合设计开发了配套课程,强调机器人教育与STEM课程的整合,以工程问题为引领,应用多种教学方法、丰富的教学资源开展教学,注重学生综合能力的培养。本文通过分析VEX机器人教育的课程设置与教学策略,提出对我国中小学开展机器人教育的一些具体途径和措施。

关键词： 机器人工程   机器人大赛   机器人竞赛   团队合作精神   领导才能   世界锦标赛   竞赛模式   数学领域  

摘要： 近年来,科学技术迅猛发展,对人类社会的政治经济产生了深刻的影响。机器人竞赛活动作为一项独具魅力的、能激发青少年科学兴趣的科技活动,在国内发展迅速。本文尝试去探寻竞赛模式下的中学VEX教学,从而为以后的VEX机器人活动开展提供思路。1 VEX机器人竞赛现状VEX机器人大赛又称VEX机器人世界锦标赛,是一项旨在通过推广教育型机器人,拓展中学生和大学生对科学、技术、工程和数学领域兴趣,提高并促进青少年的团队合作精神、领导才能和解决问题能力的世界级大赛。

关键词： 履带机器人   虚拟样机   动力学建模   软土地面   Recur Dyn  

摘要： 建立履带机器人软土地面行走的动力学模型,对履带式机器人驱动转矩、自身质量、滑转率、角加速度、加速度以及转动惯量进行分析。结果表明,滑转率和加速度对机器人驱动转矩的影响最大,且滑转率对驱动转矩的影响随机器人重量的增加而明显增长,角加速度和转动惯量对驱动转矩的影响较小。通过对机器人在软土地面行驶性能的分析,可为履带机器人的开发提供理论参考。

关键词： 井下巡检机器人   双臂   运动学分析   Newton-Euler法   动力学分析  

摘要： 针对煤矿井下巡检作业安全问题,设计一种可用于井下巡检的多任务型双臂机器人。基于D-H法建立巡检机器人双臂数学模型并进行正逆运动学分析,运用MATLAB机器人工具箱建立巡检机器人双臂模型,并进行运动学仿真及末端轨迹规划,验证了运动学模型建立的正确性和结构尺寸的合理性。采用Newton-Euler法建立机械臂动力学方程并计算各关节理论力矩,运用Adams建立巡检机器人双臂虚拟样机模型并进行动力学仿真,分析末端执行器运动轨迹为曲线时各关节的仿真力矩。通过理论计算与仿真结果对比分析,验证了井下巡检机器人双臂动力学模型的合理性,满足井下巡检作业要求,为后续井下巡检机器人样机设计及产品开发提供理论依据。

关键词： Admittance control   force tracking control   impedance control   robot manipulators   time-delayed control  

摘要： Force control for robot manipulators is increasingly demanded for stable and desired interaction between robots and environments. In this paper, several modifications of an admittance force control scheme are presented and derived from force tracking impedance functions to give a force tracking capability to position-controlled robot manipulators. Admittance force control known as the position-based force control has a structural advantage of easy implementation for the force control capability to the existing position-controlled robot systems by closing an outer force control loop. The admittance filter as an inverse of impedance function is implemented to filter force errors to modify the reference position such that the eventual force tracking impedance control is realized indirectly. Admittance filters are formulated from impedance functions that guarantee the desired force/position tracking performances with the help of the time-delayed controller. Desired contact force/position tracking control is achieved under uncertain environment and dynamics. Extensive simulation studies of force/position tracking control performances of the proposed control schemes for a robot manipulator are conducted to confirm the proposition.

关键词： variable structure control   fractional calculus   robot manipulator   fractional sensor   multidimensional scaling   information visualization  

摘要： This paper studies the use of multidimensional scaling (MDS) to assess the performance of fractional-order variable structure controllers (VSCs). The test bed consisted of a revolute planar robotic manipulator. The fractional derivatives required by the VSC can be obtained either by adopting numerical real-time signal processing or by using adequate sensors exhibiting fractional dynamics. Integer (fractional) VCS and fractional (integer) sliding mode combinations with different design parameters were tested. Two performance indices based in the time and frequency domains were adopted to compare the system states. The MDS generated the loci of objects corresponding to the tested cases, and the patterns were interpreted as signatures of the system behavior. Numerical experiments illustrated the feasibility and effectiveness of the approach for assessing and visualizing VSC systems.

关键词： Data augmentation   Deep learning   Semantic segmentation   Agricultural robot   Crop weed classification  

摘要： Deep learning methods such as convolutional neural networks (CNN) have become popular for addressing crops and weeds classification problems in agricultural robotics. However, to have satisfactory performance and avoid overfitting, training deep neural nets typically requires thousands of labeled images. This leads to tedious pixelwise labeling for semantic segmentation. In this paper, we hinge on the recent development in data augmentation and utilize the concept further for semantic segmentation and classification of crops and weeds. To be specific, we propose a novel data augmentation framework, based on the random image cropping and patching (RICAP) method, which is originally designed to augment data for generic image classification. The proposed framework introduces novel enhancements to the original RICAP so that it can be effectively used for data augmentation of semantic segmentation tasks. We evaluate the proposed methodology on two datasets from different farms. Comprehensive experimental evaluations and ablation studies show that the proposed framework can effectively improve segmentation accuracies, and the enhancements made over the original RICAP actually contribute to the performance gain. On average, the proposed method increases the mean accuracy and mean intersection over union (IOU) of the deep neural net with the conventional data augmentation (random flipping, rotation and colour jitter) from 91.01 to 94.02 and from 63.59 to 70.77 respectively for Narrabri dataset, and from 97.99 to 98.51 and from 74.26 to 77.09 respectively for Bonn dataset. The limitation of the proposed method, especially when a large number of training data is available, has also been discussed.

关键词： robotics   spondylolisthesis   pediatric   navigation  

摘要： Background: Accurate pedicle screw placement is critical to surgically correct pediatric high-grade spondylolisthesis (HGS). The recent advent of robotics coupled with computer-assisted navigation (RAN) may represent a novel option to improve surgical outcomes of HGS, secondary to enhanced pedicle screw placement safety. This series presents the HGS-RAN technique adopted by our site, describing its surgical outcomes and feasibility. Methods: Consecutive patients with a diagnosis of HGS (Meyerding grade III to V), operated on using RAN from 2019 to 2020 at a single-center were reviewed. Demographics, screw accuracy, sagittal L5-S1 parameters, complications, and perioperative outcomes were described. All patients were treated with instrumentation, decompression, posterior lumbar interbody fusion, and reduction. Robotic time included anatomic registration to end of screw placement. Screw accuracy-defined as a screw placed safely within the planned intrapedicular trajectory-was characterized by the Gertzbein-Robbins system for patients with additional 3-dimensional imaging. Results: Ten HGS patients, with an average age of 13.7 years old, were included in the series. All 62 screws were placed without neurological deficit or complication. Seven patients had additional 3-dimensional imaging to assess screw accuracy (42 of 62 screws). One hundred percent of screws were placed safely with no pedicle breaches (Gertzbein-Robbins-grade A). Thirty screws (48%) were placed through separate incisions that were percutaneous/transmuscular and 32 screws (52%) were inserted through the main incision. There were statistically significant improvements in L5 slippage (P=0.002) and lumbosacral angle (P=0.002), reflecting successful HGS correction. The total median operative time was 324 minutes with the robotic usage time consuming a median of 72 minutes. Median estimated blood loss was 150 mL, and length-of-stay was a median 3 days. Conclusions: This case-series demonstrates that RAN re