Self-supervised reinforcement learning for multi-step object manipulation skills

强化学习 对象(语法) 计算机科学 钢筋 人工智能 心理学 社会心理学
作者
Jiaqi Wang,Chuxin Chen,Jingwei Liu,Guanglong Du,Xiaojun Zhu,Quanlong Guan,Xiaojian Qiu
出处
期刊:Industrial Robot-an International Journal [Emerald Publishing Limited]
卷期号:52 (6): 853-865
标识
DOI:10.1108/ir-12-2024-0534
摘要

Purpose The purpose of this study is to address the challenge of object manipulation in scenarios where the target is not explicitly defined, requiring robots to engage in efficient planning to determine the sequence of actions for picking, placing and positioning objects. The aim is to develop a multistep skill learning method that integrates perception with a set of primitive actions, including a novel action of orienting, to enable robots to perform complex tasks that require multistep planning and interaction with various objects in cluttered and unstructured environments. Design/methodology/approach To achieve the purpose, the authors propose a pipeline that decomposes the object manipulation task into three independent stages, each trained end-to-end with raw visual inputs using off-policy reinforcement learning algorithms. The Q-learning algorithm is used to simultaneously train three fully convolutional neural networks for each primitive action – grasping, pushing, placing and orienting – from scratch. The framework is designed to be modular, allowing for easy extension to multistep manipulation tasks. Findings The findings demonstrate that robots can learn complex behaviors through both simulated and real-world experiments. In simulation, the robot achieved an efficient block-stacking success rate of up to 98% during testing. When transferring the model to a real universal robots UR3 (UR3) robot using effective domain randomization, the robot achieved a 100% completion rate with convex objects and a 92% completion rate with various objects not seen during training. Originality/value We develop a novel multistep skill learning method that integrates perception with multiple primitive actions, including a new action of orienting, and the use of off-policy reinforcement learning algorithms for end-to-end training. The modular design of the framework allows for easy extension to more complex manipulation tasks, and the encouraging results in both simulated and real-world experiments demonstrate significant improvements over current long-term planning methods.
最长约 10秒,即可获得该文献文件

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
nl发布了新的文献求助10
刚刚
1秒前
脑洞疼的应助被燕麦片采纳,获得10
1秒前
amy发布了新的文献求助10
1秒前
crimson发布了新的文献求助10
2秒前
pophoo发布了新的文献求助20
2秒前
2秒前
2秒前
zhezhe发布了新的文献求助10
3秒前
吃的饱饱呀完成签到 ,获得积分10
3秒前
Ava的应助被嘿嘿采纳,获得10
4秒前
树123发布了新的文献求助10
4秒前
Albert关注了科研通微信公众号
4秒前
5秒前
5秒前
7秒前
完美芯发布了新的文献求助150
7秒前
7秒前
酷酷的浩天完成签到 ,获得积分10
7秒前
pericles发布了新的文献求助10
8秒前
8秒前
英姑的应助被小邪采纳,获得10
8秒前
9秒前
WR发布了新的文献求助10
9秒前
虚幻的白开水完成签到,获得积分10
9秒前
内向代珊发布了新的文献求助10
9秒前
10秒前
10秒前
zhezhe完成签到,获得积分10
11秒前
百事从欢发布了新的文献求助10
11秒前
yingji完成签到,获得积分10
11秒前
句号完成签到,获得积分10
11秒前
壮观的晓露完成签到,获得积分20
12秒前
12秒前
myz发布了新的文献求助10
12秒前
phhhhh关注了科研通微信公众号
12秒前
dddd发布了新的文献求助10
12秒前
13秒前
14秒前
Albert发布了新的文献求助10
14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
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 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 8188617
求助须知:如何正确求助?哪些是违规求助? 9576328
关于积分的说明 21846790
捐赠科研通 7786606
什么是DOI,文献DOI怎么找? 3435356
关于科研通互助平台的介绍 2559627
邀请新用户注册赠送积分活动 2482347