Transformable Quadruped Wheelchairs Capable of Autonomous Stair Ascent and Descent

Atsuki Akamisaka, Katashi Nagao
{"title":"Transformable Quadruped Wheelchairs Capable of Autonomous Stair Ascent and Descent","authors":"Atsuki Akamisaka, Katashi Nagao","doi":"10.3390/s24113675","DOIUrl":null,"url":null,"abstract":"Despite advancements in creating barrier-free environments, many buildings still have stairs, making accessibility a significant concern for wheelchair users, the majority of whom check for accessibility information before venturing out. This paper focuses on developing a transformable quadruped wheelchair to address the mobility challenges posed by stairs and steps for wheelchair users. The wheelchair, inspired by the Unitree B2 quadruped robot, combines wheels for flat surfaces and robotic legs for navigating stairs and is equipped with advanced sensors and force detectors to interact with its surroundings effectively. This research utilized reinforcement learning, specifically curriculum learning, to teach the wheelchair stair-climbing skills, with progressively increasing complexity in a simulated environment crafted in the Unity game engine. The experiments demonstrated high success rates in both stair ascent and descent, showcasing the wheelchair’s potential in overcoming mobility barriers. However, the current model faces limitations in tackling various stair types, like spiral staircases, and requires further enhancements in safety and stability, particularly in the descending phase. The project illustrates a significant step towards enhancing mobility for wheelchair users, aiming to broaden their access to diverse environments. Continued improvements and testing are essential to ensure the wheelchair’s adaptability and safety across different terrains and situations, underlining the ongoing commitment to technological innovation in aiding individuals with mobility impairments.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"10 6","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sensors (Basel, Switzerland)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/s24113675","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Despite advancements in creating barrier-free environments, many buildings still have stairs, making accessibility a significant concern for wheelchair users, the majority of whom check for accessibility information before venturing out. This paper focuses on developing a transformable quadruped wheelchair to address the mobility challenges posed by stairs and steps for wheelchair users. The wheelchair, inspired by the Unitree B2 quadruped robot, combines wheels for flat surfaces and robotic legs for navigating stairs and is equipped with advanced sensors and force detectors to interact with its surroundings effectively. This research utilized reinforcement learning, specifically curriculum learning, to teach the wheelchair stair-climbing skills, with progressively increasing complexity in a simulated environment crafted in the Unity game engine. The experiments demonstrated high success rates in both stair ascent and descent, showcasing the wheelchair’s potential in overcoming mobility barriers. However, the current model faces limitations in tackling various stair types, like spiral staircases, and requires further enhancements in safety and stability, particularly in the descending phase. The project illustrates a significant step towards enhancing mobility for wheelchair users, aiming to broaden their access to diverse environments. Continued improvements and testing are essential to ensure the wheelchair’s adaptability and safety across different terrains and situations, underlining the ongoing commitment to technological innovation in aiding individuals with mobility impairments.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
能自主上下楼梯的可变形四足轮椅
尽管在创造无障碍环境方面取得了进步,但许多建筑物仍设有楼梯,这使得无障碍环境成为轮椅使用者的一大担忧,他们中的大多数人在外出前都会查看无障碍环境信息。本文的重点是开发一种可变形的四足轮椅,以应对楼梯和台阶给轮椅使用者带来的行动挑战。这款轮椅的设计灵感来自 Unitree B2 四足机器人,它结合了用于平坦路面的轮子和用于在楼梯上行走的机械腿,并配备了先进的传感器和力探测器,能与周围环境有效互动。这项研究利用强化学习(特别是课程学习)来教授轮椅爬楼梯的技能,并在 Unity 游戏引擎制作的模拟环境中逐步增加复杂性。实验表明,轮椅上下楼的成功率都很高,展示了轮椅在克服行动障碍方面的潜力。然而,当前的模型在应对各种类型的楼梯(如螺旋楼梯)时面临着局限性,需要进一步提高安全性和稳定性,尤其是在下楼阶段。该项目向提高轮椅使用者的行动能力迈出了重要一步,旨在扩大他们进入不同环境的机会。为了确保轮椅在不同地形和情况下的适应性和安全性,继续改进和测试是必不可少的,这也彰显了公司在帮助行动不便者方面不断进行技术创新的决心。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Flexible Ammonia Gas Sensor Based on a Grafted Polyaniline Grown on a Polyethylene Terephthalate Film Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks EMR-HRNet: A Multi-Scale Feature Fusion Network for Landslide Segmentation from Remote Sensing Images Measuring DNI with a New Radiometer Based on an Optical Fiber and Photodiode Highly Sensitive Balloon-like Fiber Interferometer Based on Ethanol Coated for Temperature Measurement
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1