【摘要】 开发了一种能在未知环境下实现快速障碍检测与障碍回避的基于同时发射声纳环移动机器人导航系统。为了消除由于同时发射造成的串话干扰,提出了一种基于神经网络模式识别的过滤方法;并制作了由24个声纳传感器组成的声纳环安装到实际的移动机器人上,实现了扫描频率最大可达到66Hz的全景检测。系统中应用了动态窗口法来完成快速障碍回避的运动规划。实际的导航实验表明,系统可用于室内未知环境中的移动机器人快速导航。更多还原

【Abstract】 A navigation system for mobile robot based on simultaneous-firing sonar ring is developed. To eliminate error data due to crosstalk in the simultaneous firing, a filter method based on pattern matching using neural network is used in the system. To show the advantage of this method, a prototype of sonar ring with 24 sonar sensors is fabricated and installed to a mobile robot. As a result, a scanning rate up to 66 Hz of panoramic detection is achieved. The experimental results show that the navigation system is applicable to rapid navigation for mobile robot in unknown indoor environments.更多还原