VALSE

VALSE 首页 活动通知 查看内容

VALSE 论文速览 第143期:Multi-skill Mobile Manipulation

2023-10-28 14:35| 发布者: 程一-计算所| 查看: 610| 评论: 0

摘要: 为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速 ...

为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自加州大学圣地亚哥分校和Meta AI的多技能移动机器人操作 (Multi-skill Mobile Manipulation)的工作。该工作由Devendra Singh Chaplot研究员,苏昊教授,Jitendra Malik教授指导,论文一作顾家远同学录制。


论文题目:Multi-skill Mobile Manipulation for Object Rearrangement

作者列表:

顾家远 (加州大学圣地亚哥分校),Devendra Singh Chaplot (Meta AI),苏昊 (加州大学圣地亚哥分校),Jitendra Malik (加州大学伯克利分校,Meta AI)


B站观看网址:

https://www.bilibili.com/video/BV1JM411X7QH/



论文摘要:

We study a modular approach to tackle long-horizon mobile manipulation tasks for object rearrangement, which decomposes a full task into a sequence of subtasks. To tackle the entire task, prior work chains multiple stationary manipulation skills with a point-goal navigation skill, which are learned individually on subtasks. Although more effective than monolithic end-to-end RL policies, this framework suffers from compounding errors in skill chaining, e.g., navigating to a bad location where a stationary manipulation skill can not reach its target to manipulate. To this end, we propose that the manipulation skills should include mobility to have flexibility in interacting with the target object from multiple locations and at the same time the navigation skill could have multiple end points which lead to successful manipulation. We operationalize these ideas by implementing mobile manipulation skills rather than stationary ones and training a navigation skill trained with region goal instead of point goal. We evaluate our multi-skill mobile manipulation method M3 on 3 challenging long-horizon mobile manipulation tasks in the Home Assistant Benchmark (HAB), and show superior performance as compared to the baselines.


论文信息:

[1] Gu Jiayuan, et al. "Multi-skill Mobile Manipulation for Object Rearrangement." The Eleventh International Conference on Learning Representations. 2023.


论文链接:

[https://arxiv.org/abs/2209.02778]


代码链接:

[https://github.com/Jiayuan-Gu/hab-mobile-manipulation]


视频讲者简介:

Jiayuan Gu is a Ph.D. student at the University of California San Diego advised by Prof. Hao Su. He obtained his Bachelor degree at Peking University in 2018. His research interests include 3D vision and generalizable policy learning for Embodied AI.



特别鸣谢本次论文速览主要组织者:

月度轮值AC:黄雷 (北京航空航天大学)

季度轮值AC:叶茫 (武汉大学)


活动参与方式

1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们!

直播地址:

https://live.bilibili.com/22300737;

历史视频观看地址:

https://space.bilibili.com/562085182/ 


2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ S群,群号:317920537);


*注:申请加入VALSE QQ群时需验证姓名、单位和身份缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。


3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。


4您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。


小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2024-11-24 15:54 , Processed in 0.012723 second(s), 14 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

返回顶部