...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Robotica >A vector-format fuzzy logic approach for online robot motion planning in 3D space and its application to underwater robotic vehicle
【24h】

A vector-format fuzzy logic approach for online robot motion planning in 3D space and its application to underwater robotic vehicle

机译：矢量格式的模糊逻辑方法在3D空间在线机器人运动计划及其在水下机器人车辆中的应用

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Due to its inherent advantages such as reasoning in the format of heuristic rules based on human experience and less stringent requirement on environmental description, fuzzy logic is a promising tool for the robot motion planning in 3-dimensional dynamic environment. In general, in the Cartesian space, the variables used in characterizing the motion of a mobile robot, such as position, velocity, and force relative to other objects or coordinate frames, contain both the magnitude and the pointing information. In previous studies, the fuzzy reasoning on the pointing information was often developed based on the decomposition of the pointing vector followed by conventional fuzzy logic technique on individual vector components. Consequently, when multiple pointing variables are involved, the number of fuzzy variables that need to be considered simultaneously becomes large and the rule base may become very complex, which diminishes the advantages of the fuzzy reasoning approach. In this research, we tackle this issue by implementing a new fuzzy reasoning approach based on vector-format fuzzy variables. To achieve this, a set of new membership functions is defined for the vector-format fuzzy variables, followed by the establishment of a series of new vector-based fuzzification, fuzzy inference, and defuzzification procedures. By treating the multidimensional variables as unitary linguistic variables, the number of fuzzy variables in the fuzzy propositions and therefore the scale of the rule base can be reduced considerably. As an application example, the proposed new fuzzy reasoning approach for motion planning is applied to an Underwater Robotics Vehicle (URV) operating in an oceanic environment, where the pointing of the goal and the pointing vectors of the obstacles are treated as vector-type fuzzy variables, which leads to a compact and significantly simplified rule base. The motion planner can successfully guide the URV to move in the complicated dynamic environment in a real-time fashion, which clearly demonstrates the effectiveness and robustness of the new fuzzy logic approach.
机译：由于其固有的优势，例如基于人类经验的启发式规则格式的推理以及对环境描述的严格要求，模糊逻辑是3维动态环境中机器人运动规划的有前途的工具。通常，在笛卡尔空间中，用于表征移动机器人运动的变量（例如相对于其他对象或坐标系的位置，速度和力）既包含幅度信息，又包含指向信息。在先前的研究中，通常基于对指向向量的分解，然后对单个向量分量进行常规的模糊逻辑技术，来开发针对指向信息的模糊推理。因此，当涉及多个指向变量时，需要同时考虑的模糊变量数量变大，规则库可能变得非常复杂，从而削弱了模糊推理方法的优势。在这项研究中，我们通过基于矢量格式模糊变量实施一种新的模糊推理方法来解决此问题。为此，为矢量格式的模糊变量定义了一组新的隶属函数，然后建立了一系列新的基于矢量的模糊化，模糊推理和反模糊化过程。通过将多维变量视为单一语言变量，可以大大减少模糊命题中模糊变量的数量，从而可以大大减少规则库的规模。作为一个应用示例，将提出的运动计划的新模糊推理方法应用于在海洋环境中运行的水下机器人车辆（URV），其中目标的指向和障碍物的指向矢量被视为矢量类型的模糊变量，从而导致紧凑而显着简化的规则库。运动计划器可以成功地指导URV在复杂的动态环境中实时移动，这清楚地证明了新模糊逻辑方法的有效性和鲁棒性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号