• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于强化学习的人机交互。

Human-to-Robot Handover Based on Reinforcement Learning.

机构信息

Department of Electrical Engineering (Age Service-Tech), Kyung Hee University, Seoul 02447, Republic of Korea.

Department of Artificial Intelligence, College of Software, Kyung Hee University, Seoul 02447, Republic of Korea.

出版信息

Sensors (Basel). 2024 Sep 27;24(19):6275. doi: 10.3390/s24196275.

DOI:10.3390/s24196275
PMID:39409314
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11479096/
Abstract

This study explores manipulator control using reinforcement learning, specifically targeting anthropomorphic gripper-equipped robots, with the objective of enhancing the robots' ability to safely exchange diverse objects with humans during human-robot interactions (HRIs). The study integrates an adaptive HRI hand for versatile grasping and incorporates image recognition for efficient object identification and precise coordinate estimation. A tailored reinforcement-learning environment enables the robot to dynamically adapt to diverse scenarios. The effectiveness of this approach is validated through simulations and real-world applications. The HRI hand's adaptability ensures seamless interactions, while image recognition enhances cognitive capabilities. The reinforcement-learning framework enables the robot to learn and refine skills, demonstrated through successful navigation and manipulation in various scenarios. The transition from simulations to real-world applications affirms the practicality of the proposed system, showcasing its robustness and potential for integration into practical robotic platforms. This study contributes to advancing intelligent and adaptable robotic systems for safe and dynamic HRIs.

摘要

本研究探索使用强化学习进行机械臂控制，特别是针对配备拟人夹持器的机器人，旨在增强机器人在人机交互（HRI）期间与人类安全交换各种物体的能力。该研究集成了自适应 HRI 手，用于多功能抓取，并结合图像识别，实现高效的物体识别和精确坐标估计。定制的强化学习环境使机器人能够动态适应各种场景。通过仿真和实际应用验证了这种方法的有效性。HRI 手的适应性确保了无缝交互，而图像识别则增强了认知能力。强化学习框架使机器人能够学习和改进技能，在各种场景中成功导航和操作证明了这一点。从仿真到实际应用的转变证实了所提出系统的实用性，展示了其在集成到实际机器人平台中的稳健性和潜力。本研究为安全和动态 HRI 推进智能和适应性机器人系统做出了贡献。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/99cbea850103/sensors-24-06275-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/5592afa02c4e/sensors-24-06275-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/84a70bb806ee/sensors-24-06275-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/2cfa8b0b1429/sensors-24-06275-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/798e237d18ba/sensors-24-06275-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/db914327c0f1/sensors-24-06275-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/2f08cf941014/sensors-24-06275-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/ae19cc2ac5cf/sensors-24-06275-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/d8a57add5200/sensors-24-06275-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/99cbea850103/sensors-24-06275-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/5592afa02c4e/sensors-24-06275-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/84a70bb806ee/sensors-24-06275-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/2cfa8b0b1429/sensors-24-06275-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/798e237d18ba/sensors-24-06275-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/db914327c0f1/sensors-24-06275-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/2f08cf941014/sensors-24-06275-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/ae19cc2ac5cf/sensors-24-06275-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/d8a57add5200/sensors-24-06275-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22a7/11479096/99cbea850103/sensors-24-06275-g009.jpg

相似文献

1
Human-to-Robot Handover Based on Reinforcement Learning.基于强化学习的人机交互。
Sensors (Basel). 2024 Sep 27;24(19):6275. doi: 10.3390/s24196275.
2
Research on deep reinforcement learning basketball robot shooting skills improvement based on end to end architecture and multi-modal perception.基于端到端架构和多模态感知的深度强化学习篮球机器人投篮技术改进研究
Front Neurorobot. 2023 Oct 13;17:1274543. doi: 10.3389/fnbot.2023.1274543. eCollection 2023.
3
Grasping learning, optimization, and knowledge transfer in the robotics field.掌握机器人技术领域的学习、优化和知识转移。
Sci Rep. 2022 Mar 16;12(1):4481. doi: 10.1038/s41598-022-08276-z.
4
GadgetArm-Automatic Grasp Generation and Manipulation of 4-DOF Robot Arm for Arbitrary Objects Through Reinforcement Learning.GadgetArm：通过强化学习实现四自由度机器人手臂对任意物体的自动抓取生成与操作
Sensors (Basel). 2020 Oct 30;20(21):6183. doi: 10.3390/s20216183.
5
Handover Control for Human-Robot and Robot-Robot Collaboration.人机协作与机器人协作中的交接控制。
Front Robot AI. 2021 May 7;8:672995. doi: 10.3389/frobt.2021.672995. eCollection 2021.
6
The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning.农业机器人的强化学习智能路径规划系统。
Sensors (Basel). 2022 Jun 7;22(12):4316. doi: 10.3390/s22124316.
7
Human-Robot Interaction Using Learning from Demonstrations and a Wearable Glove with Multiple Sensors.使用示教学习和带有多个传感器的可穿戴手套进行人机交互。
Sensors (Basel). 2023 Dec 12;23(24):9780. doi: 10.3390/s23249780.
8
Human-robot collaborative task planning using anticipatory brain responses.使用预期脑反应进行人机协作任务规划。
PLoS One. 2023 Jul 11;18(7):e0287958. doi: 10.1371/journal.pone.0287958. eCollection 2023.
9
Bio-robots automatic navigation with graded electric reward stimulation based on Reinforcement Learning.基于强化学习的具有分级电奖励刺激的生物机器人自动导航。
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:6901-4. doi: 10.1109/EMBC.2013.6611144.
10
Adaptive Variable Stiffness Particle Phalange for Robust and Durable Robotic Grasping.用于稳健且持久机器人抓取的自适应可变刚度颗粒指骨
Soft Robot. 2020 Dec;7(6):743-757. doi: 10.1089/soro.2019.0089. Epub 2020 Apr 22.

本文引用的文献

1
Trends of Human-Robot Collaboration in Industry Contexts: Handover, Learning, and Metrics.工业环境下人机协作的发展趋势：交接、学习和度量。
Sensors (Basel). 2021 Jun 15;21(12):4113. doi: 10.3390/s21124113.