CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleDesign and Control of A Robotic Fish With Embeded Vision
Thesis Advisor喻俊志
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline控制理论与控制工程
Keyword嵌入式视觉 多控制面 阈值分割 视觉定位 Embedded Vision Multiple Control Surface Threshold Analysis Visual Localization
Abstract本文是在国家自然科学基金“基于耦合传感反馈的鱼游CPG的多模态控制”的支持下完成的。本文针对机器鱼的嵌入式视觉进行研究,实现仿机器鱼的视觉导航。 本文提出了一种基于嵌入式视觉系统能进行目标追踪和避障的新型机器鱼。该机器鱼能通过它的鱼眼采集图像,并且通过一系列的图像算法识别出有意义的色标块。这些行为是通过一个以ARM9(S3C2440)为核心处理器的控制系统,搭载30万像素的CMOS摄像头采集本地视觉信息来完成。依靠这些信息,机器鱼能够实现水下智能巡游。基于嵌入式视觉的机器鱼不仅能够根据实时的视觉信息来巡航,而且能够把探测结果同步传送到上位机。实验结果证明了该机器鱼设计的有效性。本文所开发的机器鱼具有如下三个特点: 首先,该机器鱼基于的是嵌入式视觉系统。因为加上了视觉反馈,它本身又是一个完整的控制环节,视觉、传感器等信息的处理不需要依靠外界辅助来完成。 其次,该机器鱼的机械结构采用的是多控制面的设计。它拥有四个关节的尾部,一对胸鳍和一个腹鳍。通过多个推进面间的有效配合和基于CPG算法的多模态控制,使机器鱼具有更多的游动步态和更高的游动性能。 最后,该机器鱼的核心处理器主频高达400 MHz,能够在运行图像处理算法的同时,保证系统的实时性。通过搜寻色标块和避障的实验充分验证了机器鱼游动的稳定性和控制的有效性。
Other AbstractThis dissertation is supported by the National Natural Science Foundation of China “Multi-mode motion control for fish swimming based on Central Pattern Generator with sensory feedback”. This dissertation is focused on embedded visual system of a multi-fin robotic fish and realization of autonomous navigation. The paper presents a new type of autonomous robotic fish with vision-based target tracking and obstacle avoidance. The robotic fish can sample images through its eye and recognize the meaningful color patch via a series of vision algorithms. More specifically, an ARM9 (S3C2440)-centered microcontroller in conjunction with a CMOS camera (300 thousand pixels) for image acquisition is developed to effectively handle local visual information serving as the basis of underwater navigation. Meanwhile, a wireless interactive control console is devised, facilitating two-way information transfer. It can access the environmental information captured by the robotic fish in real time and display the obtained results in a visual format online. Experimental results demonstrate the effectiveness of the proposed scheme. The robotic fish developed in this paper has three characteristics: First, the robotic fish is based on the vision system. It has a closed-loop control system with the introduction of visual feedback. The visual and other sensing information processing do not rely on the outside assistance. Next, the robotic fish is designed as a novel multiple control surfaces configuration, which has a four-joint tail, a pair of pectoral fins and a pelvic fin. This makes the autonomous robotic fish have more swimming gaits and enhanced swimming performance through the cooperation of multiple fins and CPG-based control method. Lastly, the frequency of the core processor of the robotic fish is up to 400 MHz. So it can afford a series of image processing algorithms and also ensures realtimeness in control. The experiments on searching color patch and avoiding obstacles validate the swimming stability and control effectiveness.
Other Identifier200828014628015
Document Type学位论文
Recommended Citation
GB/T 7714
王恺. 具有嵌入式视觉功能的机器鱼设计与控制[D]. 中国科学院自动化研究所. 中国科学院研究生院,2011.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20082801462801(6392KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王恺]'s Articles
Baidu academic
Similar articles in Baidu academic
[王恺]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王恺]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.