Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

作者
Alireza Ranjbar,Ngo Anh Vien,Hanna Ziesche,Joschka Boedecker,Gerhard M. Neumann
出处
期刊: [Institute of Electrical and Electronics Engineers]
卷期号:: 2383-2390 被引量:12
标识
DOI:10.1109/iros51168.2021.9636176
摘要

While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, residual policy learning (RPL) offers a formulation to improve existing controllers with reinforcement learning (RL) by learning an additive "residual" to the output of a given controller. However, the applicability of such an approach highly depends on the structure of the controller. Often, internal feedback signals of the controller limit an RL algorithm to adequately change the policy and, hence, learn the task. We propose a new formulation that addresses these limitations by also modifying the feedback signals to the controller with an RL policy and show superior performance of our approach on a contact-rich peg-insertion task under position and orientation uncertainty. In addition, we use a recent Cartesian impedance control architecture as the control framework which can be available to us as a black-box while assuming no knowledge about its input/output structure, and show the difficulties of standard RPL. Furthermore, we introduce an adaptive curriculum for the given task to gradually increase the task difficulty in terms of position and orientation uncertainty. A video showing the results can be found at https://youtu.be/SAZm_Krze7U.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
慕青的应助被科研通管家采纳,获得10
刚刚
fantasy的应助被科研通管家采纳,获得30
刚刚
思源的应助被科研通管家采纳,获得100
刚刚
上官若男的应助被科研通管家采纳,获得10
刚刚
秋风的应助被科研通管家采纳,获得10
刚刚
刚刚
西北一枝花的应助被jing采纳,获得10
刚刚
刚刚
怡然破茧完成签到,获得积分10
1秒前
星辰大海的应助被科研通管家采纳,获得10
1秒前
汉堡包的应助被科研通管家采纳,获得10
1秒前
malen111完成签到 ,获得积分10
1秒前
共享精神的应助被科研通管家采纳,获得10
1秒前
赘婿的应助被暴躁莹子采纳,获得10
1秒前
斯文败类的应助被科研通管家采纳,获得10
1秒前
斯文败类的应助被科研通管家采纳,获得10
1秒前
邦尼老师完成签到,获得积分10
1秒前
炒米粉完成签到,获得积分0
1秒前
1秒前
李爱国的应助被科研通管家采纳,获得10
1秒前
聂的苏发布了新的文献求助50
1秒前
慕青的应助被二马三乡采纳,获得10
2秒前
2秒前
liubole完成签到,获得积分10
2秒前
2秒前
3秒前
wanci的应助被呼呼呼呼采纳,获得10
3秒前
3秒前
cc完成签到,获得积分20
4秒前
4秒前
小蘑菇的应助被能干的故事采纳,获得10
4秒前
4秒前
5秒前
5秒前
5秒前
兰瓜瓜完成签到,获得积分10
6秒前
6秒前
molihuakai的应助被Kraghc采纳,获得10
6秒前
7秒前
氨气发布了新的文献求助10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175707
求助须知:如何正确求助?哪些是违规求助? 9567353
关于积分的说明 21792214
捐赠科研通 7770334
什么是DOI,文献DOI怎么找? 3431908
关于科研通互助平台的介绍 2556260
邀请新用户注册赠送积分活动 2477417