本文为美国新罕布什尔大学（作者：Kevin Rose）的硕士论文，共96页。

自主机器人越来越多地融入到人类日常活动中，这一趋势并没有任何减缓的迹象。自主机器人需要在人类和其他动态物体之间可靠地执行任务就需要进行运动规划。也就是说，在尽可能减少与其他物体碰撞的可能性的同时，尽可能快地将机器人可靠地导航到所需的位置。这不仅包括围绕动态障碍物预测的未来轨迹进行规划，还包括以实时方式进行规划，以便机器人能够对周围环境保持足够的反应。目前的方法不能直接解决这个问题。

本文提出了一种新的实时规划算法real-time R*(RTR*)。RTR*是基于R*搜索算法的，该算法将随机采样与启发式搜索相结合，并已在多个不同的机器人领域显示出良好的效果。描述了将R*转换为实时算法所需的一些修改，还详细介绍了专门为这个问题领域开发的其他修改。将RTR*与几种最新的运动规划和实时搜索算法进行了比较，给出了一个经验评估。RTR*显示出很有前途的性能，并在R*的基础上有所改进，但它的性能不如当前的最高水平。讨论了几种可以改善RTR*性能的增强方法。

Autonomous robots are increasingly becomingincorporated in everyday human activities, and this trend does not show anysigns of slowing down. One task that autonomous robots will need to reliably performamong humans and other dynamic objects is motion planning. That is, to reliablynavigate a robot to a desired pose as quickly as possible while minimizing theprobability of colliding with other objects. This involves not only planningaround the predicted future trajectories of dynamic obstacles, but doing so ina real-time manner so that the robot can remain reactive to its surroundings.Current methods do not directly address this problem. This thesis proposes anew real-time planning algorithm called real-time R* (RTR*). RTR* is based onthe R* search algorithm that couples random sampling with heuristic search andhas been shown to work well in several different robotics domains. Severalmodifications needed to transform R* into a real-time algorithm are described.Additional modifications that were developed specifically for this problemdomain are also detailed. An empirical evaluation is given comparing RTR* withseveral state-of-the-art motion planning and real-time search algorithms. RTR*shows promising performance and improves on R*, however it underperforms thecurrent state-of-the-art. Several enhancements are discussed that could improvethe behavior of RTR*.

1. 引言

2. 问题描述

3. 仿真器

4. 以前的相关工作

5. 实时R*算法

6. 结论

附录A R*算法伪码

附录B 通信协议

附录C 配置文件描述

附录D 具体分工

更多精彩文章请关注公众号：