大工至善|大学至真分享 http://blog.sciencenet.cn/u/lcj2212916

博文

[转载]【计算机科学】【2017.07】智能室内机器人避障与路径规划

已有 1615 次阅读 2019-1-2 09:18 |系统分类:科研笔记|文章来源:转载


本文为美国罗切斯特理工学院(作者:Rasika M. Kangutkar)的硕士论文,共153页。

 

虽然电动轮椅上的操纵杆已经改善了许多人的生活,但是帕金森氏症、中风、肢体受伤或视力问题的患者仍然需要替代解决方案。此外,在杂乱的环境中驾驶轮椅而不碰撞到物体或人是一项具有挑战性的任务。由于这些原因,许多患者依赖于日常工作的看护人。为帮助残疾人士,机器智能实验室个人电子运输(Milpet)提供了一种解决方案。Milpet是一种有效的具有语音识别能力的轮椅。诸如“Milpet,带我去237房间”或“Milpet,向前走”等语音命令都可以实现。当Milpet执行患者命令时,它将计算最优路径,避免障碍,并在必要时重新计算路径。

 

本文介绍了模块化室内机器人避障及路径规划算法的研究进展。由于系统的模块化,对于不同的机器人,导航系统是可扩展的。避障系统可通过配置以实现各种行为。根据需要,所述机器人可根据具体的路径或环境,实现墙体跟随或走廊居中行动,或只是在自由空间中漫游,同时规避障碍物。该导航系统已经在各种条件下进行了测试,以证明障碍物和路径规划模块的鲁棒性。为了说明该导航系统的实用性,引入了障碍物接近度目的地接近度的测量方法。Milpet的这些能力是让许多依赖护理人员或亲人的患者重获独立和个人隐私的重要一步。

 

Although joysticks on motorized wheelchairshave improved the lives of so many, patients with Parkinson’s, stroke, limbinjury, or vision problems need alternate solutions. Further, navigatingwheelchairs through cluttered environments without colliding into objects orpeople can be a challenging task. Due to these reasons, many patients arereliant on a caretaker for daily tasks. To aid persons with disabilities, theMachine Intelligence Laboratory Personal Electronic Transport (Milpet),provides a solution. Milpet is an effective access wheelchair with speechrecognition capabilities. Commands such as “Milpet, take me to room 237 or“Milpet, move forward can be given. As Milpet executes the patients commands,it will calculate the optimal route, avoid obstacles, and recalculate a path ifnecessary. This thesis describes the development of modular obstacle avoidanceand path planning algorithms for indoor agents. Due to the modularity of the system,the navigation system is expandable for different robots. The obstacleavoidance system is configurable to exhibit various behaviors. According toneed, the agent can be influenced by a path or the environment, exhibit wallfollowing or hallway centering, or just wander in free space while avoidingobstacles. This navigation system has been tested under various conditions todemonstrate the robustness of the obstacle and path planning modules. Ameasurement of obstacle proximity and destination proximity have beenintroduced for showing the practicality of the navigation system. Thecapabilities introduced to Milpet are a big step in giving the independence andprivacy back to so many who are reliant on care givers or loved ones.

 

引言

项目背景

系统概述

人与机器人的交互

机器人避障

路径规划

机器人视觉与激光雷达数据融合

研究结果

结论

10 未来研究工作展望


下载英文原文地址:

http://page5.dfpan.com/fs/5l4c7j22029172a9169/


更多精彩文章请关注微信号:qrcode_for_gh_60b944f6c215_258.jpg



https://wap.sciencenet.cn/blog-69686-1154867.html

上一篇:[转载]【新书推荐】【2018.11】101种iPhone便利技术:关于iOS 12的更新、简化和修订
下一篇:[转载]【读书2】【2014】基于MATLAB的雷达信号处理基础(第二版)——分辨率(2)
收藏 IP: 222.190.121.*| 热度|

0

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...
扫一扫,分享此博文

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2024-3-29 20:35

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部