【作者】 杨武强；

【导师】 张华；

【作者基本信息】 南昌大学 ， 控制理论与控制工程， 2007， 硕士

【摘要】 目前，随着机器人技术的发展，机器人的智能性越来越重要，所以避开障碍物是机器人智能化的一个重要指标。本文采用超声波传感器实现机器人避障控制：首先设计超声波测距系统用于探测机器人周围环境，并建立全局环境坐标分析超声波传感器所探得的障碍物的信息；然后通过一种避障控制算法完成障碍物的模式识别；最后应用到爬行式焊接机器人和智能轮椅上实现自主避障。其具体内容如下：用51单片机设计超声测距系统，该系统的测距精度为±5cm，基本上满足避障控制要求。为了增加单个超声波传感器的测量精度和减小多个超声波传感器所产生的干涉现象，在硬件上采用多个传感器分时测量，在软件上设置时间隔离，从而减少了系统的串干扰。提出了一种用于移动机器人自主避障的模糊CAMC避障控制算法。通过将一定量的模糊规则和CMAC小脑模型结合，得到了一种启发式的模糊神经网络，并通过对该模糊神经网络进行离线非监督式的训练，建立了超声波传感器输入信号和移动机器人速度之间的模式映射关系，从而实现了移动机器人连续、快速避障。最后，采用MATLAB建立了一个虚拟环境并进行了避障仿真。为了验证方案的可行性，通过在爬行机器人和智能轮椅上的实验，表明该系统能够满足机器人避障要求。更多还原

【Abstract】 At present,With the development of robot technology,the robot intelligence becomes more and more important,therefore,it is an important indicator for the robot intelligence to avoid obstacles.This article uses the ultrasonic sensor to realize the control of robotic avoiding obstacles. Firstly, we design an ultrasonic ranging system to probe the environment on every side of the robot, and analysis the obstruction information by building an overall situation coordinate. Secondly,a control algorithm has been worked out to accomplish pattern recognition. Lastly, avoiding obstacle system has been applied on the crawl robot and intelligent wheel chair by the experiments,then independently realizes the avoiding obstacle.The content as follows:with the accuracy of±5 centimeters,Use 51 micro-chip to design a measurement ranging system, which satisfy the requirement of blocker avoiding controls.In order to increase the measurement precision of single ultrasonic sensor and decrease the interference degree produced by multiple ultrasonic sensors,we have adopted the method of many sensors time division measures on the hardware and set the isolation interposed time to decrease system interference on the software.This paper also presents a Fuzzy-CMAC recognition algorithm,which used to achieve autonomous obstacle avoidance of a mobile robot.Through the combination of heuristic fuzzy rules with the CMAC network,a heuristic fuzzy-neuro network is developed. By applying the off-line and unsupervised training in this method,we build up pattern-mapping between ultrasonic sensory input data and velocity command.Thus,the mobile robot realizes continuous and fast motion for obstacle avoidance.Finally,a virtual environment has been built and the emulation has been in progress in MATLAB.In order to verify the effectiveness of these proposed methods,this paper gives the results of obstacle avoidance through the experiments in crawl robot and intelligent wheel chair.The results show that the system meets the requirements of obstacle avoidance.更多还原