SenseCobot

SenseCobot dataset has been created to evaluate stress level and cognitive load in participants involved in cobot programming tasks. This dataset integrates various physiological signals, including ElectroCardioGram (ECG), Galvanic Skin Response (GSR), body temperature, ElectroDermal Activity (EDA), ElectroEncephaloGram (EEG), Blood Volume Pulse (BVP), facial emotions, and subjective responses from NASA-TLX questionnaires. These signals have been obtained from 21 participants engaged in collaborative robotics programming tasks, organized in three phases: an introduction to learning materials, a baseline measurement task to establish reference conditions, and hands-on practice. Different wearable and non-invasive sensors have been used, such as Shimmer 3 ECG, EEG Enobio 20 channels helmet, Shimmer 3 GSR, Empatica E4 and wristband sensors. The dataset is organized into folders based on the type of collected signals, making it user-friendly and accessible for research purposes. Txt format files have been added in each folder containing detailed information about individual signals. SenseCobot dataset, aims to support research in HRC by providing high-quality, multimodal physiological data related to mental effort and stress during cobot programming. Such data can be valuable for developing more intuitive and user-friendly programming interfaces, predictive machine learning models for real-time stress monitoring, and enhancing human-robot collaboration in various applications.SenseCobot数据集专为评估参与协作机器人编程任务的受试者的压力水平与认知负荷而构建。该数据集整合了多类生理信号，包括心电图（ElectroCardioGram, ECG）、皮肤电反应（Galvanic Skin Response, GSR）、体温、皮肤电活动（ElectroDermal Activity, EDA）、脑电图（ElectroEncephaloGram, EEG）、血容量脉冲（Blood Volume Pulse, BVP）、面部表情情绪数据，以及来自NASA任务负荷指数量表（NASA-TLX）的主观反馈。这些信号采集自21名参与协作机器人编程任务的受试者，实验流程分为三个阶段：学习材料介绍环节、用于建立参考基准的基线测量任务，以及实操练习环节。研究使用了多款可穿戴及非侵入式传感器，例如Shimmer 3心电图传感器、20通道EEG Enobio头戴设备、Shimmer 3皮肤电反应传感器、Empatica E4及腕带式传感器。该数据集按采集信号的类型进行文件夹分类，便于科研人员使用与获取，适配研究需求。每个文件夹中均附带TXT格式文件，内含单条信号的详细说明信息。SenseCobot数据集旨在通过提供与协作机器人编程过程中心理负荷及压力相关的高质量多模态生理数据，支撑人机协作（Human-Robot Collaboration, HRC）领域的研究。此类数据可用于开发更直观易用的编程界面、面向实时压力监测的预测性机器学习模型，以及优化多场景下的人机协作效能。

搜集汇总

背景与挑战

背景概述

SenseCobot是一个多模态生理信号数据集，旨在评估协作机器人编程任务中参与者的压力水平和认知负荷。它整合了来自21名参与者的心电图、皮肤电反应、脑电图等多种生理信号，数据通过可穿戴传感器收集，并组织成用户友好的文件夹结构。该数据集支持人机协作研究，可用于开发直观的编程界面、实时压力监测的机器学习模型，以及增强人机协作应用。