全区域覆盖移动机器人避障策略与多传感器系统的设计研究

【作者】 樊明轩；

【导师】 王华坤；

【作者基本信息】 南京理工大学 ， 机械电子工程， 2003， 硕士

【摘要】 文中就一类全区域覆盖户外移动机器人(如割草机器人)的避障系统进行了详细的论述，并对相关的传感器技术、体系结构、多传感器信息融合技术等理论进行了研究。本文作者建立了移动机器人改进型基于行为的体系结构，提出了较完善的全区域覆盖移动机器人的避障理论和策略，定义了突发障碍和一般障碍，并给予不同的处理方式；同时重点构建了多传感器系统，采用五组超声波传感器用于检测环境信息；基于人工神经网络对每组获取的信息进行分析和融合，从而较准确地完成了对障碍的识别；最后，通过软硬件的设计，实现了特定的避障行为。通过课题的研究，形成了一套完整而实用的设计方法，为进行同类研究提供了理论依据。更多还原

【Abstract】 This paper studies a system for obstacle avoidance by a new kind of region-filling mobile robot (such as a robot lawn mower) in detail and discusses some related technology and theory such as sensor, architecture, multi-sensor information fusion and so on. First, the author builds the improved architecture based on behaviors for the mobile robot MORO-I, proposes a full strategy of obstacle avoidance for region filling, and defines random obstacle and general obstacle which will be dealt with differently,- moreover, the multi-sensor system is set up which includes five groups of ultrasonic sensors for detecting the environmental information and the artificial neural network is used to fuse the information from each sensor group to achieve a precision of obstacle identification; finally, the hardware and software are designed for the realization of obstacle avoidance. Through the work above, the full and practical design approach is proposed to provide the theoretical support for similar researches.更多还原