Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

The Readiness-Efficiency Coupling: Synergy of High Preparatory and Reduced Execution Fractal Complexity in Motor Learning.

Journal of motor behavior·2026
Same author

Reviewing digital collaborative interactions with multimodal hyperscanning through an ever-growing database.

Frontiers in neuroergonomics·2026
Same author

Oscillatory and gaze signatures of socio-emotional speech processing, visuo-spatial cognition, and their interaction in a near-realistic dual-task MEG study.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Response Inhibition in Autistic Adults: A Functional Near-Infrared Spectroscopy Study in Virtual Reality.

Brain and behavior·2026
Same author

General practitioners' antibiotic prescribing decisions in the Northern Dutch-German cross-border region: a discrete choice experiment.

BMC primary care·2025
Same author

Shielding the Mind With Flow: Attention Allocation and Auditory Event-Related Potentials Under Varying Mental Workload.

The European journal of neuroscience·2025

相关实验视频

Updated: Jul 5, 2025

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K

结合脑计算机接口与深度强化学习用于机器人训练:在模拟环境中的可行性研究.

Mathias Vukelić1, Michael Bui1, Anna Vorreuther2

  • 1Applied Neurocognitive Systems, Fraunhofer Institute for Industrial Engineering (IAO), Stuttgart, Germany.

Frontiers in neuroergonomics
|January 18, 2024
PubMed
概括

带有深度强化学习 (RL) 的脑计算机接口 (BCI) 加快了机器人训练. 干式EEG系统有效地评估机器人的行为,使BCI-deep RL能够匹配明确的人类反性能.

关键词:
大脑-计算机接口接口深度强化学习的学习.电脑脑电图 (EEG) 是一种电脑电图.错误监控 错误监控 错误监控 错误监控 错误监控与事件相关的潜力 (ERP)机器学习是机器学习.机器人技术 机器人工程 机器人工程

更多相关视频

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
06:11

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

393

相关实验视频

Last Updated: Jul 5, 2025

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
06:11

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

393

科学领域:

  • 机器人技术 机器人技术 机器人技术
  • 神经科学是一个神经科学.
  • 机器学习 机器学习

背景情况:

  • 深度强化学习 (RL) 在机器人训练中扎着稀少的奖励.
  • 为自主机器人学习设计有效的奖励功能是一项挑战.
  • 大脑-计算机接口 (BCI) 为隐含的人类反提供了一个替代方案.

研究的目的:

  • 为了研究BCI驱动的机器人训练深度RL的可行性.
  • 为了比较EEG系统 (湿与干) 在机器人任务中的错误分类.
  • 为了评估基于BCI的深度RL的表现与明确的人类反.

主要方法:

  • 利用基于3D物理的模拟环境进行机器人训练.
  • 湿基和干基电脑学 (EEG) 系统用于错误检测的比较.
  • 使用机器学习模型,包括卷积神经网络,用于EEG信号分析.
  • 训练有素的深度RL代理人使用隐式BCI反和明确的人类反.

主要成果:

  • 高质量的干式EEG系统提供了强大的和快速的机器人行为评估.
  • 复杂的机器学习模型准确地从EEG数据中分类感知到的错误.
  • 基于BCI的深度RL在模拟中显著加速机器人学习.
  • BCI-deep RL的性能可与人类显式反方法相提并论.

结论:

  • 干式EEG系统与机器学习相结合,为机器人行为评估提供了一种可行的方法.
  • 基于BCI的隐性深度RL是机器人训练的有效替代品,当没有明确的反时.
  • 这种方法通过启用直观的机器人学习来增强人机交互.