VertiEncoder: Self-Supervised Kinodynamic Representation Learning on Vertically Challenging Terrain

Mohammad Nazeri, Aniket Datar, Anuj Pokhrel, Chenhui Pan, Garrett Warnell, Xuesu Xiao
{"title":"VertiEncoder: Self-Supervised Kinodynamic Representation Learning on Vertically Challenging Terrain","authors":"Mohammad Nazeri, Aniket Datar, Anuj Pokhrel, Chenhui Pan, Garrett Warnell, Xuesu Xiao","doi":"arxiv-2409.11570","DOIUrl":null,"url":null,"abstract":"We present VertiEncoder, a self-supervised representation learning approach\nfor robot mobility on vertically challenging terrain. Using the same\npre-training process, VertiEncoder can handle four different downstream tasks,\nincluding forward kinodynamics learning, inverse kinodynamics learning,\nbehavior cloning, and patch reconstruction with a single representation.\nVertiEncoder uses a TransformerEncoder to learn the local context of its\nsurroundings by random masking and next patch reconstruction. We show that\nVertiEncoder achieves better performance across all four different tasks\ncompared to specialized End-to-End models with 77% fewer parameters. We also\nshow VertiEncoder's comparable performance against state-of-the-art kinodynamic\nmodeling and planning approaches in real-world robot deployment. These results\nunderscore the efficacy of VertiEncoder in mitigating overfitting and fostering\nmore robust generalization across diverse environmental contexts and downstream\nvehicle kinodynamic tasks.","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11570","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

We present VertiEncoder, a self-supervised representation learning approach for robot mobility on vertically challenging terrain. Using the same pre-training process, VertiEncoder can handle four different downstream tasks, including forward kinodynamics learning, inverse kinodynamics learning, behavior cloning, and patch reconstruction with a single representation. VertiEncoder uses a TransformerEncoder to learn the local context of its surroundings by random masking and next patch reconstruction. We show that VertiEncoder achieves better performance across all four different tasks compared to specialized End-to-End models with 77% fewer parameters. We also show VertiEncoder's comparable performance against state-of-the-art kinodynamic modeling and planning approaches in real-world robot deployment. These results underscore the efficacy of VertiEncoder in mitigating overfitting and fostering more robust generalization across diverse environmental contexts and downstream vehicle kinodynamic tasks.
VertiEncoder:在垂直挑战性地形上进行自我监督的动力学表征学习
我们介绍的 VertiEncoder 是一种用于机器人在垂直挑战地形上移动的自监督表示学习方法。VertiEncoder 使用变形编码器,通过随机屏蔽和下一个补丁重构来学习其周围环境的局部上下文。我们的研究表明,在所有四种不同任务中,VertiEncoder 的性能都优于专门的端到端模型,其参数数量减少了 77%。我们还展示了 VertiEncoder 在实际机器人部署中与最先进的动力学建模和规划方法相媲美的性能。这些结果进一步证明了 VertiEncoder 在减少过拟合和促进在不同环境背景和下游车辆动力学任务中实现更强大的泛化方面的功效。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信