Design and path planning for a remote-brained service robot

This article introduced an effective design method of robot called remote-brain, which is made the brain and body separated. It leaves the brain in the mother environment, by which we mean the environment in which the brain's software is developed, and talks with its body by wireless links. It also presents a real robot TUT06-B based on this method which has human-machine interaction, vision systems, manipulator etc. Then it discussed the path planning method for the robot based on ant colony algorithm in details, especially the Ant-cycle model. And it also analyzed the parameter of the algorithm which can affect the convergence. Finally, it gives the program flow chat of this algorithm.

虚拟现实水下机器人仿真系统

本文采用VR技术,模拟真实情况建立了一个水下机器人仿真系统。该系统使用与真实系统相同的控制器和输入设备,提供操作员训练、人—机智能控制仿真、机器人轨迹规划仿真等功能,仿真数据能够引导真实机器人运动。文中以仿真实例说明了系统的有效性。

非结构环境下基于人机合作技术的抓取作业研究

介绍了一种利用人机合作技术在非结构环境引导机械手抓取静态目标的方法.分别介绍了将激光—CCD摄像机系统与操作者的经验相结合获得抓取目标位置的方法,及将虚拟现实技术与操作者的经验相结合获得抓取目标姿态的方法.继而利用基于模型的视觉引导技术,引导手臂完成抓取操作.

人机系统在移动机器人平台的应用

针对机器智能发展研究存在的瓶颈问题 ,研究了人机结合应用的必要性 ,并在此基础上提出“人机系统”的概念 ,探讨了人机系统应用的一般性方法 ,给出人机系统的体系结构、交互原则、介入准则 ,并以移动机器人为平台结合改进的人工矢量场算法进行了应用

基于刺激－反应相容性的汉语拼音和弦键盘的实验研究

Stimulus-Response Compatibility is a key concept in human-machine interaction. It is proved that to map stimulus to response according to salient-feature coding principle will get a compatible pair. In the designing of Chinese Pinyin Code inputting devices, stimulus-response compatibility will bring the device with features of ease of use and ease of learning. In this research, Response time and error rates of two designs of salient-feature coding principle and one design of random mapping were tested along with the QWERTY keyboard. Cross-modal Compatibility Effects were found, and no significant difference between two salient-feature coding types, both on response time and error rates; but response time has shown difference between salient-feature coding designs and random mapping design. Compared with the QWERTY keyboard group, the error rates of subjects of chord keyboard group showed no significant differences. But subjects assigned to the QWERTY keyboard group have a shorter response time. One possible reason is the subjects of chord keyboard group only at beginner skill after at most 6 hours practice whereas subjects of QWERTY group were at least at novice level after take a foundation of computer class at their own college.

线索语义相容性的研究

With the studies of the Stimulus-Response Compatibility (SRC), more and more psychologists consider that the compatibility isn't only exist between stimulus and stimulus, response and response, but also any two sets in the information processing, it means that the compatibility is the basic feature of the human information processing. Research on the compatibility of the precue is a powerful evidence to support the issue. Dimension Overlap Model (Kornblum, 1990) is one of the most popular models to explain the mechanism of the SRC which focus on the dimension overlapping between the stimulus and response will activate the compatible response automatically, the compatibility effects origin from whether the compatible response prove or interference the response, the so the time course between the automatic activation and the task processing cause the dynamical time feature of the SRC (Kornblum, 1997). Yet the DO model has gotten many supports, it hasn't been tested in the paradigm of the precue task. At the same time, company with the development of the Environment Psychology, the effect of the ex-information in the environment on the inside information processing has drown much attention, does the validity probability of the cue have any influence on the cue compatibility? How about the relationship of the cue compatibility and the SRC? Research on the questions will reveal the characteristics of the human information processing, enhance the knowledge of the compatibility phenomena and resource, enlarge the field of SRC and produce more practice usage on the design of human-machine system. The mechanism and influence factors of symbolic compatibility between cue and stimulus were investigated within a precueing paradigm. The influence of the dimension overlapping relation between the cue and the stimulus, cue and the response on the reaction time were studied under the different kinds of SRC, to test whether or not it confirms the dimension overlap hypothesis, to test is there any effect of SOA and validity probability of cues on the cue compatibility. The results showed that the cue compatibility exists and owns such features: 1, It confirms the dimension overlap model that the cue which dimension overlapped with the stimulus or the response will influence the efficiency of the processing, the reaction time is shorter when the cue is congruent with the stimulus or the response that that of the incongruent cue; 2, Consistent to the automatic activation hypothesis, the time course is the important characteristic of the cue compatibility. The largest compatibility effect can be gotten from the middle duration of SOA. 3, The validity probability of cues influence the cue compatibility significantly, the strength of the cue compatibility effect grows stronger with the higher validity probability of cues. 4, The cue compatibility affect the effect of SRC, especially when the cue is compatible with the stimulus; 5, The cue compatibility has two-fold meaning, the cue-stimulus compatibility and the cue-response compatibility, the former is stronger than the later when they compete each other. In summary, the compatibility, the basic feature of human information processing, is proved by the research, and the dimension overlap model and automatic activation hypothesis is tested by the studying on the cue compatibility.

scenario-based interactive intention understanding in pen-based user interfaces

Interactive intention understanding is important for Pen-based User Interface (PUI). Many works on this topic are reported, and focus on handwriting or sketching recognition algorithms at the lexical layer. But these algorithms cannot totally solve the problem of intention understanding and can not provide the pen-based software with high usability. Hence, a scenario-based interactive intention understanding framework is presented in this paper, and is used to simulate human cognitive mechanisms and cognitive habits. By providing the understanding environment supporting the framework, we can apply the framework to the practical PUI system. The evaluation of the Scientific Training Management System for the Chinese National Diving Team shows that the framework is effective in improving the usability and enhancing the intention understanding capacity of this system.

Efficient HOG human detection

While Histograms of Oriented Gradients (HOG) plus Support Vector Machine (SVM) (HOG+SVM) is the most successful human detection algorithm, it is time-consuming. This paper proposes two ways to deal with this problem. One way is to reuse the features in blocks to construct the HOG features for intersecting detection windows. Another way is to utilize sub-cell based interpolation to efficiently compute the HOG features for each block. The combination of the two ways results in significant increase in detecting humans-more than five times better. To evaluate the proposed method, we have established a top-view human database. Experimental results on the top-view database and the well-known INRIA data set have demonstrated the effectiveness and efficiency of the proposed method. (C) 2010 Elsevier B.V. All rights reserved.

MULTIVARIATE CLASSIFICATION BASED ON METAL CONTENTS IN HUMAN SENILE CATARACT LENSES

Multivariate classification methods were used to evaluate data on the concentrations of eight metals in human senile lenses measured by atomic absorption spectrometry. Principal components analysis and hierarchical clustering separated senile cataract lenses, nuclei from cataract lenses, and normal lenses into three classes on the basis of the eight elements. Stepwise discriminant analysis was applied to give discriminant functions with five selected variables. Results provided by the linear learning machine method were also satisfactory; the k-nearest neighbour method was less useful.