Real-time Path Planning in Changing Environments

该项目提出了新的方法，为在随时间变化的环境中运行的机器人生成无碰撞路径。本研究的典型应用包括安装在移动平台上的机械臂，在工厂设置中操作的机械臂，或在先验未知或可能随时间变化的环境中操作的任何其他操作系统。该方法包括预处理和在线两个阶段。预处理产生配置空间的表示，可以很容易地实时修改，以说明环境中的变化。为无障碍工作空间构造一维路线图，并对路线图中工作空间单元到节点和弧的映射进行编码。在在线阶段，当环境发生变化时，使用该映射对路线图进行适当的修改，并且可以通过搜索修改后的路线图来生成计划。该方法的核心是从工作空间障碍到配置空间障碍的映射编码。为了使所提出的方法真正可行，所提出的研究的主要组成部分将集中在鲁棒性和复杂性问题上。这些问题将通过使用图像处理、信息论、图论、计算几何和增量算法等领域的工具来解决。

This project addresses new methods to generate collision-free paths for robots that operate in environments that change over time. Typical applications of this research include robot arms mounted on mobile platforms, arms that operate in factory settings, or any other manipulation systems that operate in environments that are either unknown a priori or may change over time.The proposed approach comprises preprocessing and on-line stages. Preprocessing produces a representation of the configuration space that can be easily modified in real-time to account for changes in the environment. A one-dimensional roadmap is constructed for an obstacle-free workspace, and the mapping from workspace cells tonodes and arcs in the roadmap is encoded. In the on-line stage, when the environment changes, this mapping is used to make the appropriate modifications to the roadmap, and plans can be generated by searching the modified roadmap. At the heart of the method is the encoding for the mapping from workspace obstacles to configuration space obstacles. To make the proposed approach truly viable, a major component of the proposed research will focus on robustness and complexity issues. These issues will be addressed by using tools from the fields of image processing, information theory, graph theory, computational geometry, and incremental algorithms.