面向家庭办公场景的具身智能机器人触觉交互需求与行为反馈设计研究

何旭 ,  虞文琦 ,  巢鹏飞 ,  林师潼

信息科学与工程研究 ›› 2026, Vol. 7 ›› Issue (10) : 31 -33.

PDF (1033KB)
信息科学与工程研究 ›› 2026, Vol. 7 ›› Issue (10) : 31 -33. DOI: 10.12349/iser.v7i10.11962

面向家庭办公场景的具身智能机器人触觉交互需求与行为反馈设计研究

作者信息 +

Tactile Interaction Needs and Behavioral Feedback Design for Embodied Intelligent Robots in Home Office Scenarios

Author information +
文章历史 +
PDF (1056K)

摘要

随着具身智能机器人逐渐进入家庭与办公等非结构化环境,机器人交互正由屏幕、按钮等传统界面扩展到身体动作与物理接触.触觉不仅承担压力、振动、温度和摩擦等信息采集功能,也影响机器人对抓取风险、物体状态及人与机器接触关系的判断.针对现有研究重感知性能、轻行为表达的问题,本文以EIR触觉感知Agent为研究对象,从具身智能与工业设计交叉视角构建“场景需求-触觉判断-行为意图-外显反馈”的设计框架,并提出确认型、警示型、修正型、退让型和失败型五类行为反馈.研究强调以动作速度、夹持力度、轨迹、停顿与退让等身体行为表达机器人内部状态,形成“行为即界面”的具身交互方式.该方法将工业设计由外观与传统界面进一步延伸到感知、行为和人机关系设计,为家庭办公机器人的触觉交互与安全协作提供设计参考.

Abstract

As embodied intelligent robots increasingly enter unstructured environments such as homes and offices, robot interaction is expanding beyond traditional interfaces like screens and buttons to include physical movements and tactile contact. Touch not only enables the collection of information such as pressure, vibration, temperature, and friction, but also influences a robot's judgment regarding grasping risks, object states, and human-robot contact dynamics. Addressing the current research gap-overemphasis on perception performance at the expense of behavioral expression-this study takes the EIR tactile perception agent as the subject, establishing a design framework from the intersection of embodied intelligence and industrial design: "scenario needs-tactile judgment-behavioral intent-external feedback." Five types of behavioral feedback are proposed: confirmation, warning, correction, yielding, and failure. The study emphasizes expressing internal robotic states through physical behaviors such as movement speed, gripping force, trajectory, pauses, and withdrawal, thus forming an embodied interaction model where "behavior becomes the interface." This approach extends industrial design beyond aesthetics and conventional interfaces to encompass perception, behavior, and human-robot relationship design, offering valuable insights for tactile interaction and safe collaboration in home office robots.

关键词

具身智能 / 工业设计 / 触觉交互 / 行为反馈 / 人机交互 / 智能机器人

Key words

embodied intelligence / industrial design / tactile interaction / behavioral feedback / human-robot interaction / intelligent robots

引用本文

引用格式 ▾
何旭,虞文琦,巢鹏飞,林师潼. 面向家庭办公场景的具身智能机器人触觉交互需求与行为反馈设计研究[J]. 信息科学与工程研究, 2026, 7(10): 31-33 DOI:10.12349/iser.v7i10.11962

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

XU J, CHEN W, QIAN H, et al. ThinTact: Thin vision-based tactile sensor by lensless imaging[J]. IEEE Transactions on Robotics, 2025, 41: 1139-1154.

[2]

ZHAO Z, LI W, LI Y, et al. Embedding high-resolution touch across robotic hands enables adaptive human-like grasping[J]. Nature Machine Intelligence, 2025.

[3]

HIGUERA C, SHARMA A, BODDULURI C K, et al. Sparsh: Self-supervised touch representations for vision-based tactile sensing[C]// Proceedings of the 8th Conference on Robot Learning. Proceedings of Machine Learning Research, 2025, 270: 885-915.

[4]

ZHUANG Y, WANG S, SHE D, et al. Octopi: Object property reasoning with large tactile-language models[C]// Robotics: Science and Systems. 2024.

[5]

HUANG J, WANG S, LIN F, et al. Tactile-VLA: Unlocking vision-language-action model's physical knowledge for tactile generalization[EB/OL]. arXiv:2507.09160, 2025.

[6]

KANITKAR S, JIANG H, YUAN W. PoseIt: A visual-tactile dataset of holding poses for grasp stability analysis[C]// IEEE/RSJ International Conference on Intelligent Robots and Systems. 2022.

[7]

LIMA B M R, DANYAMRAJU V N S S, DE OLIVEIRA T E A, et al. A multimodal tactile dataset for dynamic texture classification[J]. Data in Brief, 2023, 50: 109590.

[8]

ZHAO J, MA Y, WANG L, et al. Transferable tactile transformers for representation learning across diverse sensors and tasks[C]//Proceedings of the 8th Conference on Robot Learning. Proceedings of Machine Learning Research, 2025, 270.

基金资助

市级大学生创新训练项目“EIR触觉感知agent开发设计”(csz2607001)

AI Summary AI Mindmap
PDF (1033KB)

13

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉