【作者】 房波；

【导师】 丛明；

【作者基本信息】 大连理工大学 ， 机械设计及理论， 2007， 硕士

【摘要】 随着经济的发展，城市绿化进程逐渐加快，草坪业也得到了迅猛发展，每年对城市草坪、足球场、高尔夫球场等公共绿地进行修剪和维护作业需要消耗掉大量的人力、物力和时间。使用传统割草机对草坪进行修剪时，产生巨大的噪声和废气不仅污染环境，而且会对从业人员的身心健康产生严重影响，因此有必要研制一种自动割草机器人，用于实现草坪修剪作业的自动化，将人们从高重复、枯燥、劳累的割草作业中解放出来。本文首先对国外市场上现有的自动割草机器人进行了介绍和比较，在总结国外自动割草机器人现有成果的基础之上，根据智能割草机器人的特点和发展方向，着重指出了在自动割草机器人研制过程中需要解决的多传感器融合技术、导航定位技术、避障控制技术以及路径规划等关键技术。其次，本文介绍了多传感器融合技术及其在移动机器人中的应用，并依据割草机器人的设计要求、割草机器人具体的工作环境以及市场价格等因素，选取合适的传感器并搭建传感器系统。不同于室内移动机器人，割草机器人工作在户外非结构化环境中。在整个工作区域内，割草机器人使用传感器来监测自身状态并感知周围环境，为其实现定位、地图建模、导航以及避障等任务提供来自外界情况和自身状态的实时信息和依据。由于割草机器人工作环境的复杂性和不确定性，单一种类的传感器不能完成上述任务。因此，本文设计了一种用于割草机器人导航避障的多传感器系统，该系统集成了超声波传感器、红外线传感器、温度传感器、碰撞传感器、编码器以及电子罗盘。然后，本文设计了一种多超声波传感器构成的割草机器人避障探测系统，并采用模糊神经网络算法来实现多超声波传感器信息融合。应用多个信息的互补性和冗余性来获得信息源的本质特征和准确状态，以减少或消除超声波传感器的不确定性，有效地提高了超声波传感器的测量精度，正确地反映障碍物的距离信息，为割草机器人避障提供了实时、准确的控制决策。最后，本文提出了一种基于多传感器融合的割草机器人地图建立及定位的方法，确定了采用基于多个超声波传感器信息融合方法的导航策略。仿真结果表明，本文设计的多传感器系统、多传感器融合方法以及该方法在割草机器人地图建立以及导航定位中应用的可行性和有效性。更多还原

【Abstract】 With the development of economy, urban greening process has been accelerated rapidly and the lawn industry spring up around quickly. Every year, it will consume lots of resources to maintain the public lawns such as city turf, football field and golf yard. Furthermore, those traditional lawn mowers bring huge noise and produce exhaust gas into the air, which have a bad effect on somatopsychic health of the workers and pollute the environment directly. It is necessary to develop a kind of autonomous robot lawn mower in order to liberate labors from high repetition, boring and tiring mowing work.Firstly, this paper introduces and compares the existing robot mowers domestic and overseas. According to the characteristics and the development direction of the robot mower, this paper points out the key technologies for robot mower such as multisensor fusion, navigation technology, obstacle avoidance control and path planning technology.Secondly, this paper introduces the application of multisensor fusion technology using in mobile robots and builds the sensing system for the robot mower according to the design requirements, specific working condition and market price factors. Robot mowers work in unstructured environment, it is important for an autonomous robot mower to explore its surroundings in performing the task of localization and navigation for mowing. Because of the complexity of the environment, one simple kind of sensors is not sufficient for robot mower to accomplish these tasks. This paper presents a multisensor system for combining measurements from ultrasonic sensors and navigation for robot mowers. The proposed sensing system integrates ultrasonic sensors, infrared sensors, collision sensors, encoders, a temperature sensor and an electronic compass.Then, this paper presents a multi-ultrasonic sensor system for obstacle detecting and uses fuzzy neural network to fuse the information from the ultrasonic sensors, which improves the measurement precision effectively. And this method provides real-time and accurate control decision for the robot mower.Finally, this paper presents a method of mapping and localization for robot mower and uses the navigation strategy based on multisensor fusion for robot mower. The simulation results indicate that the multisensor system, multisensor fusion method and the method using in mapping, navigation and localization for robot mower are feasible and effective.更多还原