多传感器融合机器人室内定位系统设计与实现

目前,室内机器人的应用越来越广,位置信息作为机器人自主技术的基本信息,亟需完善的室内定位系统解决方案.对基于多传感器融合的室内机器人定位系统进行设计与实现,以航位推算为基础方法,加之超声、激光测距信息以及地图信息,通过粒子滤波进行融合,从而得到更精确的定位信息.通过具体的实验测试和结果分析,文中设计的室内机器人定位系统具有很好的定位效果,可在航位推算的基础上,将定位误差降低到原误差的十分之一.     

对于驾驶机器人性能综合评价的研究

为了综合评价驾驶机器人的驾驶性能,在单纯指标评价的基础上,提出一种新的综合评价方法.经过对驾驶机器人的实测验证,获得的数据证明此方法能时驾驶机嚣人驾驶性能进行定性的、直观的综合评价.     

Development of a robotic system for the bed-ridden

The ability to live without the help of a caretaker enhances the quality of life of those who are bed-ridden or confined to a wheel-chair. A lot of systems have been proposed to support the daily life of bed-ridden. A smart home, especially a bed-type robot system, can help the movement and action of patients.This paper discusses the development of an intelligent bed robot system (IBRS), which can help the elderly and the disabled have independent life in bed. The IBRS is a special bed equipped with two robot arms and an array of pressure sensors attached to the mattress. The pressure distribution on the mattress is used to estimate the pose of the patient, and an appropriate assistance is provided by the robot arms. The proposed system has been tested experimentally for its effectiveness while maximizing the therapeutic outcome.     

Fabrication of Stable Metallic Patterns Embedded in Poly(dimethylsiloxane) and Model Applications in Non‐Planar Electronic and Lab‐on‐a‐Chip Device Patterning

This article describes the fabrication of durable metallic patterns that are embedded in poly(dimethylsiloxane) (PDMS) and demonstrates their use in several representative applications. The method involves the transfer and subsequent embedding of micrometer‐scale gold (and other thin‐film material) patterns into PDMS via adhesion chemistries mediated by silane coupling agents. We demonstrate the process as a suitable method for patterning stable functional metallization structures on PDMS, ones with limiting feature sizes less than 5 μm, and their subsequent utilization as structures suitable for use in applications ranging from soft‐lithographic patterning, non‐planar electronics, and microfluidic (lab‐on‐a‐chip, LOC) analytical systems. We demonstrate specifically that metal patterns embedded in both planar and spherically curved PDMS substrates can be used as compliant contact photomasks for conventional photolithographic processes. The non‐planar photomask fabricated with this technique has the same surface shape as the substrate, and thus facilitates the registration of structures in multilevel devices. This quality was specifically tested in a model demonstration in which an array of one hundred metal oxide semiconductor field‐effect transistor (MOSFET) devices was fabricated on a spherically curved Si single‐crystalline lens. The most significant opportunities for the processes reported here, however, appear to reside in applications in analytical chemistry that exploit devices fabricated using the methods of soft lithography. Toward this end, we demonstrate durably bonded metal patterns on PDMS that are appropriate for use in microfluidic, microanalytical, and microelectromechanical systems. We describe a multilayer metal‐electrode fabrication scheme (multilaminate metal–insulator–metal (MIM) structures that substantially enhance performance and stability) and use it to enable the construction of PDMS LOC devices using electrochemical detection. A polymer‐based microelectrochemical analytical system, one incorporating an electrode array for cyclic voltammetry and a microfluidic system for the electrophoretic separation of dopamine and catechol with amperometric detection, is demonstrated.     

A two stream convolutional neural network with bi-directional GRU model to classify dynamic hand gesture

Dynamic hand gesture recognition is still an interesting topic for the computer vision community. A set of feature vectors can represent any hand gesture. A Recurrent Neural Network (RNN) can recognize these feature vectors as a hand gesture that analyzes the temporal and contextual information of the gesture sequence. Thus, we proposed a hybrid deep learning framework to recognize dynamic hand gestures. In the Hybrid model GoogleNet is pipelined with a Bidirectional GRU unit to recognize the dynamic hand gesture. Dynamic hand gestures consist of many frames, and features of each frame need to be extracted to get the temporal and dynamic information of the performed gesture. As RNN takes input as a sequence of feature vectors, we extract features from videos using pretrained GoogleNet. As Gated Recurrent Unit is one of the variants of RNN to classify the sequential data, we created a feature vector that corresponds to each video and passed it to the bidirectional GRU (BGRU) network to classify the gestures. We evaluate our model on four publicly available hand gesture datasets. The proposed method performs well and is comparable with the existing methods. For instance, we achieved 98.6% accuracy on Northwestern University Hand Gesture(NWUHG), 99.6% on SKIG, 99.4% on Cambridge Hand Gesture (CHG) datasets respectively. We performed our experiments on DHG14/28 dataset and achieved an accuracy of 97.8% with 14-gesture classes and 92.1% on 28-gesture classes. DHG14/28 dataset contains skeleton and depth data, and our proposed model used depth data and achieved comparable accuracy.     

室外移动机器人自主充电系统研究

为了满足机器人长期自主工作的电源要求,对室外环境下工作的移动机器人自主充电问题进行了研究。设计了具有2个自由度对接功能的充电装置,提出了一种简单有效的对接策略,此外具有错位对接纠错功能。通过自主充电实验验证了充电装置的实用性和对接策略的可行性。     

淀粉色浆在手绘加工中的应用

用淀粉色浆代替颜料。扩大了手绘产品的花色品种。文中介绍了用酸性染料色浆绘制真丝绸，用直接染料色浆绘制棉、麻、粘胶丝织物，用分散染料绘制合纤织物等。使用效果好。同时，分别总结了各色浆的调制方法和产品加工要求。     

人机共存环境下巡检机器人自主移动与避障方法

为提高人机混杂环境中移动机器人自主巡检效率,提出一种基于模糊逻辑理论的避障方法。通过分析人 类的社会行为规则,结合机器人的运动特性,建立移动机器人系统的数学模型,将人机距离、人的行为模式和人与 机器人间的相对速度参数进行模糊化处理,得出基于模糊推理方法的机器人速度变化决策,利用模糊控制规则,实 现模糊逻辑控制,并通过穿越和相遇2 种运动行为进行了实验验证。仿真结果验证了该方法具有抗干扰性和良好的 避障性能。     

基于主导—主体教学模式的机器人教学研究

本篇文章以机器人教学的实际内容,详细探讨一下主导——主体的机器人教学模式内容,从而为后续进一步提升机器人教学水平提供一定的理论基础.     

基于ARM处理器的吸尘机器人硬件设计

设计一款具有自主吸尘功能并且结构简单、成本低的小型家用吸尘机器人,实现了室内半自动或者全自动的清洁工作,从一定程度上代替人们做繁杂的家务。在硬件选型上,以ARM Cortex??M3处理器为核心,设计了专门的电机驱动板,通过光电编码反馈电路实现行走模块的闭环控制。主要对传感器模块进行开发,通过合理布置传感器,采用多种传感器融合,使超声波和红外光电传感器协调工作实现对远近距离障碍物的精确检测,提高了对障碍物的准确识别,能够实现自主避障吸尘。