机器人如何吸引儿童?外观、动作和声音多感官特征在早期互动中的作用

doi:10.11996/JG.j.2095-302X.2026010223

图学学报 ›› 2026, Vol. 47 ›› Issue (1): 223-233.DOI: 10.11996/JG.j.2095-302X.2026010223

机器人如何吸引儿童?外观、动作和声音多感官特征在早期互动中的作用

李奕¹^,²(), 曹成才³, 宋章通⁴, 李祚奇⁵, 黎晓¹^,², 李和森¹^,²

¹ 湖北美术学院工业设计学院，湖北武汉 430205
² 湖北美术学院现代公共视觉艺术设计研究中心，湖北武汉 430205
³ 武汉工程大学艺术设计学院，湖北武汉 430205
⁴ 武汉商学院艺术学院，湖北武汉 430056
⁵ 中国地质大学(武汉)计算机学院，湖北武汉 430078

收稿日期:2025-03-24 接受日期:2025-09-02 出版日期:2026-02-28 发布日期:2026-03-16
通讯作者:李奕，E-mail：liyi@hifa.edu.cn
基金资助:
湖北省人文社会科学重点研究基地-湖北美术学院现代公共视觉艺术设计研究中心重大项目(JD-2025-01)

How do robots attract children? The role of appearance, motion, and voice as multisensory features in early-stage interactions

LI Yi¹^,²(), CAO Chengcai³, SONG Zhangtong⁴, LI Zuoqi⁵, LI Xiao¹^,², LI Hesen¹^,²

¹ School of Industrial Design, Hubei Institute of Fine Arts, Wuhan Hubei 430205, China
² Research Center for Modern Public Visual Arts and Design, Hubei Institute of Fine Arts, Wuhan Hubei 430205, China
³ School of Art and Design, Wuhan Institute of Technology, Wuhan Hubei 430205, China
⁴ School of Art, Wuhan Business University, Wuhan Hubei 430056, China
⁵ School of Computer Science, China University of Geosciences, Wuhan Hubei 430078, China

Received:2025-03-24 Accepted:2025-09-02 Published:2026-02-28 Online:2026-03-16
Supported by:
Major Projects of Key Research Institute of Humanities and Social Sciences at Universities in Hubei Province-Research Center for Modern Public Visual Arts and Design of Hubei Institute of Fine Arts(JD-2025-01)

摘要/Abstract

摘要：

随着人工智能技术的快速发展，多模态机器人在学前儿童的教育、娱乐及日常生活中扮演着日益重要的角色。现有研究多关注机器人单一感官线索对儿童感知的作用，但关于多感官整合效应仍缺乏系统性研究。为探究机器人多模态特征如何共同影响儿童的情感偏好和视觉注意力，招募318名4~6岁儿童参与1项眼动追踪实验。实验采用2(外观特征：拟人型、拟动物型)×3(声音引导：男声、女声、无)×2(手势引导：有、无)的三因素混合实验设计，以机器人外观特征(拟人型与拟动物型)和行为特征(声音、手势引导)为自变量，以儿童情感偏好和眼动指标为因变量，系统考察了多感官特征对儿童用户的影响。结果表明，在外观特征方面，拟人型机器人和拟动物型机器人在主观偏好评分上没有显著差异，但拟人型机器人吸引了更长的总注视时长、更多的注视次数和更短的首次注视时间，拟人型机器人在注意力指标上显著优于拟动物型机器人，儿童在视觉接触的初始阶段更容易被拟人型机器人所吸引，且拟人化设计在持续吸引儿童注意力方面更具优势。在行为特征方面，具有手势引导的机器人在主观偏好评分上显著高于无手势机器人，且吸引了更长的总注视时长和更多的注视次数。女声机器人在主观偏好评分上略高于男声，且两者均显著高于无声机器人。男声机器人在总注视时长上略高于女声，且两者均显著高于无声机器人。而女声和男声机器人在注视次数的差异不显著，但两者均显著高于无声机器人。具有手势引导和声音(尤其是女声)的机器人在主观评分和视觉注意力分配上表现更好，说明行为特征在增强儿童的情感偏好和互动体验中具有重要作用。此外，外观和行为特征对儿童情感偏好和视觉注意力的影响相对独立，未观察到显著交互作用。该研究揭示了机器人外观和行为特征对学前儿童情感偏好和视觉注意力的影响机制，为设计满足用户情感偏好的儿童机器人提供了科学依据。

关键词: 学龄前儿童, 机器人, 外观特征, 行为特征, 情感偏好, 视觉注意力, 多感官整合

Abstract:

With the rapid development of artificial intelligence technology, multimodal robots are playing an increasingly important role in preschool children’s education, entertainment, and daily life. Existing studies have primarily focused on the effects of single sensory cues of robots on children’s perception, while systematic research on multisensory integration effects remains limited. To explore how robots’ multimodal features jointly influence children’s emotional preferences and visual attention, 318 children aged 4-6 years were recruited to participate in an eye-tracking experiment. The experiment adopted a 2 (appearance features: humanoid vs. animal-like) × 3 (voice guidance: male voice, female voice, none) × 2 (gesture guidance: present vs. absent) mixed factorial design, with robot appearance features (humanoid vs. animal-like) and behavioral features (voice and gesture guidance) as independent variables, and children’s emotional preferences and eye-tracking indicators as dependent variables, thereby systematically examining the effects of multimodal features on child users. The results showed that, in terms of appearance features, no significant difference was observed in subjective preference ratings between humanoid and animal-like robots. However, humanoid robots attracted longer total fixation duration, more fixation counts, and shorter first-fixation latency, indicating superior attention-related performance compared with animal-like robots. Children were more readily attracted to humanoid robots during the initial stage of visual contact, and anthropomorphic design showed greater advantages in sustaining children’s attention. In terms of behavioral features, robots with gesture guidance received significantly higher subjective preference ratings than those without gestures, and also elicited longer total fixation duration and more fixation counts. Robots with female voices received slightly higher subjective preference ratings than those with male voices, and both were significantly preferred over robots without voices. Robots with male voices had slightly longer total fixation duration than those with female voices, and both significantly outperformed robots without voices. The difference in fixation counts between male- and female-voice robots was not significant, but both attracted significantly more fixations than robots without voices. Robots with gesture guidance and voice (especially female voice) performed better in subjective ratings and visual attention allocation, suggesting that behavioral features substantially enhanced children’s emotional preferences and interactive experiences. Furthermore, the effects of appearance and behavioral features on children’s emotional preferences and visual attention were relatively independent, and no significant interaction effects were observed. This study revealed the mechanisms through which robot appearance and behavioral features influenced preschool children’s emotional preferences and visual attention, thereby providing scientific evidence for designing child-oriented robots that align with users’ emotional needs.

Key words: preschool children, robot, appearance features, behavioral features, emotional preference, visual attention, multisensory integration

中图分类号:

TP242

李奕, 曹成才, 宋章通, 李祚奇, 黎晓, 李和森. 机器人如何吸引儿童?外观、动作和声音多感官特征在早期互动中的作用[J]. 图学学报, 2026, 47(1): 223-233.

LI Yi, CAO Chengcai, SONG Zhangtong, LI Zuoqi, LI Xiao, LI Hesen. How do robots attract children? The role of appearance, motion, and voice as multisensory features in early-stage interactions[J]. Journal of Graphics, 2026, 47(1): 223-233.

图/表 9

参考文献 63

[1]	BELPAEME T, KENNEDY J, RAMACHANDRAN A, et al. Social robots for education: a review[J]. Science Robotics, 2018, 3(21): eaat5954. DOI URL
[2]	BARTNECK C, BELPAEME T, EYSSEL F, et al. Human-robot interaction: an introduction[M]. Cambridge: Cambridge University Press, 2024: 12-18.
[3]	CHIEN S E, CHEN Y S, CHEN Y C, et al. Exploring the developmental aspects of the uncanny valley effect on children’s preferences for robot appearance[J]. International Journal of Human-Computer Interaction, 2025, 41(10): 6366-6376. DOI URL
[4]	ZHANG F R, BROZ F, DERTIEN E, et al. Understanding design preferences for robots for pain management: a co-design study[C]// 2022 17th ACM/IEEE International Conference on Human-Robot Interaction. New York: IEEE Press, 2022: 1124-1129.
[5]	MANNER M D. Identifying differences in social responsiveness among preschoolers interacting with or watching social robots[C]// The 27th International Joint Conference on Artificial Intelligence. New York: ACM, 2018: 5777-5778.
[6]	LEE J, AOKI H, STEFANOV D, et al. A study on the relationship between robotic movement with animacy and visual attention of young children[C]// 2016 25th IEEE International Symposium on Robot and Human Interactive Communication. New York: IEEE Press, 2016: 682-687.
[7]	ANDRÉ V, JOST C, HAUSBERGER M, et al. Ethorobotics applied to human behaviour: can animated objects influence children's behaviour in cognitive tasks?[J]. Animal Behaviour, 2014, 96: 69-77. DOI URL
[8]	王艳群, 杨俞玲, 张仁杰, 等. 基于眼动实验的ASD儿童陪伴机器人造型设计评价研究[J]. 包装工程, 2022, 43(20): 121-131.
	WANG Y Q, YANG Y L, ZHANG R J, et al. Research on modeling design evaluation of ASD children accompanying robot based on eye-movement experiment[J]. Packaging Engineering, 2022, 43(20): 121-131 (in Chinese).
[9]	KE F F, LIU R H, SOKOLIKJ Z, et al. Using eye-tracking in education: review of empirical research and technology[J]. Educational Technology Research and Development, 2024, 72(3): 1383-1418. DOI
[10]	ZAJONC R B, MARKUS H. Affective and cognitive factors in preferences[J]. Journal of Consumer Research, 1982, 9(2): 123-131. DOI URL
[11]	KAWASAKI M, YAMAGUCHI Y. Individual visual working memory capacities and related brain oscillatory activities are modulated by color preferences[J]. Frontiers in Human Neuroscience, 2012, 6: 318. DOI PMID
[12]	FONG T, NOURBAKHSH I, DAUTENHAHN K. A survey of socially interactive robots[J]. Robotics and Autonomous Systems, 2003, 42(3/4): 143-166. DOI URL
[13]	TUNG F W. Child perception of humanoid robot appearance and behavior[J]. International Journal of Human-Computer Interaction, 2016, 32(6): 493-502. DOI URL
[14]	VAN STRATEN C L, PETER J, KÜHNE R. Child-robot relationship formation: a narrative review of empirical research[J]. International Journal of Social Robotics, 2020, 12(2): 325-344. DOI PMID
[15]	OROS M, NIKOLIĆ M, BOROVAC B, et al. Children’s preference of appearance and parents’ attitudes towards assistive robots[C]// 2014 IEEE-RAS International Conference on Humanoid Robots. New York: IEEE Press, 2014: 360-365.
[16]	WOODS S. Exploring the design space of robots: children’s perspectives[J]. Interacting with Computers, 2006, 18(6): 1390-1418. DOI URL
[17]	CORBETTA M, SHULMAN G L. Control of goal-directed and stimulus-driven attention in the brain[J]. Nature Reviews Neuroscience, 2002, 3(3): 201-215. DOI PMID
[18]	LIU Y S, LI F, TANG L H, et al. Detection of humanoid robot design preferences using EEG and eye tracker[C]// 2019 International Conference on Cyberworlds. New York: IEEE Press, 2019: 219-224.
[19]	LI M M, GUO F, REN Z G, et al. A visual and neural evaluation of the affective impression on humanoid robot appearances in free viewing[J]. International Journal of Industrial Ergonomics, 2022, 88: 103159. DOI URL
[20]	LIBERMAN-PINCU E, ORON-GILAD T. Impacting the perception of socially assistive robots- evaluating the effect of visual qualities among children[C]// 2021 30th IEEE International Conference on Robot & Human Interactive Communication. New York: IEEE Press, 2021: 612-618.
[21]	ADMONI H, SCASSELLATI B. Social eye gaze in human-robot interaction: a review[J]. Journal of Human-Robot Interaction, 2017, 6(1): 25-63. DOI URL
[22]	WRÓBEL A, ZGUDA P, ŹRÓBEK K, et al. ‘I prefer robot cats!’ reflections on robot animal-like morphology from an in-the-wild child-robot interaction workshop[C]// The 16th International Conference on Intelligent Human Computer Interaction. Cham: Springer, 2025: 159-170.
[23]	BARBER O, SOMOGYI E, MCBRIDE E A, et al. Exploring the role of aliveness in children's responses to a dog, biomimetic robot, and toy dog[J]. Computers in Human Behavior, 2023, 142: 107660. DOI URL
[24]	LEE D, PARK H, LEE H S. Book-Toki: a rabbit-shaped reading companion robot that enhances children’s reading concentration[C]// 2024 21st International Conference on Ubiquitous Robots. New York: IEEE Press, 2024: 520-524.
[25]	BECK A, CAÑAMERO L, HIOLLE A, et al. Interpretation of emotional body language displayed by a humanoid robot: a case study with children[J]. International Journal of Social Robotics, 2013, 5(3): 325-334. DOI URL
[26]	LI M M, GUO F, FANG C, et al. Multisensory integration effect of humanoid robot appearance and voice on users’ affective preference and visual attention[J]. Behaviour & Information Technology, 2023, 42(14): 2387-2406.
[27]	TIELMAN M, NEERINCX M, MEYER J J, et al. Adaptive emotional expression in robot-child interaction[C]// The 9th ACM/IEEE International Conference on Human-Robot Interaction. New York: IEEE Press, 2014: 407-414.
[28]	BORAU S, OTTERBRING T, LAPORTE S, et al. The most human bot: Female gendering increases humanness perceptions of bots and acceptance of AI[J]. Psychology & Marketing, 2021, 38(7): 1052-1068. DOI URL
[29]	KENDON A. Gesture: visible action as utterance[M]. New York: Cambridge University Press, 2004: 176-198.
[30]	KREJTZ I, SZARKOWSKA A, KREJTZ K, et al. Audio description as an aural guide of children's visual attention: evidence from an eye-tracking study[C]// Symposium on Eye Tracking Research and Applications. New York: ACM, 2012: 99-106.
[31]	JURKAT S, GUTKNECHT-STÖHR A C, KÄRTNER J. The socialization of visual attention: training effects of verbal attention guidance in urban German children[EB/OL]. [2025-01-23]. https://doi.org/10.1037/dev0001746.
[32]	KORY WESTLUND J M, JEONG S, PARK H W, et al. Flat vs. expressive storytelling: young children’s learning and retention of a social robot’s narrative[J]. Frontiers in Human Neuroscience, 2017, 11: 295. DOI URL
[33]	KOELEWIJN T, BRONKHORST A, THEEUWES J. Attention and the multiple stages of multisensory integration: a review of audiovisual studies[J]. Acta Psychologica, 2010, 134(3): 372-384. DOI PMID
[34]	DE BOER M J, BAŞKENT D, CORNELISSEN F W. Eyes on emotion: dynamic gaze allocation during emotion perception from speech-like stimuli[J]. Multisensory Research, 2020, 34(1): 17-47. DOI PMID
[35]	DE WIT J, BRANDSE A, KRAHMER E, et al. Varied human-like gestures for social robots: investigating the effects on children’s engagement and language learning[C]// The 15th ACM/IEEE International Conference on Human-Robot Interaction. New York: IEEE Press, 2020: 359-367.
[36]	JOUEN A L, MATSUNAKA R, HIRAKI K. Once upon a time… acquisition of second language vocabulary through robotic storytelling in classroom settings[J]. International Journal of Social Robotics, 2025, 17(6): 955-988. DOI
[37]	OVIATT S. Ten myths of multimodal interaction[J]. Communications of the ACM, 1999, 42(11): 74-81.
[38]	VANNASING P, DIONNE-DOSTIE E, TREMBLAY J, et al. Electrophysiological responses of audiovisual integration from infancy to adulthood[J]. Brain and Cognition, 2024, 178: 106180. DOI URL
[39]	KLASEN M, CHEN Y H, MATHIAK K. Multisensory emotions: perception, combination and underlying neural processes[J]. Reviews in the Neurosciences, 2012, 23(4): 381-392. DOI PMID
[40]	CORNELIO P, VELASCO C, OBRIST M. Multisensory integration as per technological advances: a review[J]. Frontiers in Neuroscience, 2021, 15: 652611. DOI URL
[41]	COSTA S, SOARES F, SANTOS C. Facial expressions and gestures to convey emotions with a humanoid robot[C]// The 5th International Conference on Social Robotics. Cham: Springer, 2013: 542-551.
[42]	TSIOURTI C, WEISS A, WAC K, et al. Multimodal integration of emotional signals from voice, body, and context: effects of (In)congruence on emotion recognition and attitudes towards robots[J]. International Journal of Social Robotics, 2019, 11(4): 555-573. DOI
[43]	ESCUDERO P, ROBBINS R A, JOHNSON S P. Sex-related preferences for real and doll faces versus real and toy objects in young infants and adults[J]. Journal of Experimental Child Psychology, 2013, 116(2): 367-379. DOI PMID
[44]	SPINNER L, CAMERON L, FERGUSON H J. Children’s and parents’ looking preferences to gender-typed objects: evidence from eye tracking[J]. Journal of Experimental Child Psychology, 2020, 199: 104892. DOI URL
[45]	FAZIO R H, OLSON M A. Implicit measures in social cognition research: their meaning and use[J]. Annual Review of Psychology, 2003, 54(1): 297-327. DOI URL
[46]	COSTA A, SCHWEICH T, CHARPIOT L, et al. Attitudes of children with autism towards robots: an exploratory study[EB/OL]. [2025-01-23]. https://arxiv.org/abs/1806.07805.
[47]	ROESLER E, MANZEY D, ONNASCH L. A meta-analysis on the effectiveness of anthropomorphism in human-robot interaction[J]. Science Robotics, 2021, 6(58): eabj5425.
[48]	ROSSINI G, MANZI F, DI DIO C, et al. Playing with robots in a nursery: a sociomaterial focus on interaction and learning[J]. European Journal of Psychology of Education, 2025, 40(1): 37. DOI
[49]	ZAJONC R B. Attitudinal effects of mere exposure[J]. Journal of Personality and Social Psychology, 1968, 9(2): 1-27.
[50]	BRAND J, MASTERSON T D, EMOND J A, et al. Measuring attentional bias to food cues in young children using a visual search task: an eye-tracking study[J]. Appetite, 2020, 148: 104610. DOI URL
[51]	SANDOVAL E B, SOSA R, CAPPUCCIO M, et al. Human-robot creative interactions: exploring creativity in artificial agents using a storytelling game[J]. Frontiers in Robotics and AI, 2022, 9: 695162. DOI URL
[52]	KANDA T, HIRANO T, EATON D, et al. Interactive robots as social partners and peer tutors for children: a field trial[J]. Human-Computer Interaction, 2004, 19(1/2): 61-84. DOI URL
[53]	ABRAMS R A, CHRIST S E. Motion onset captures attention[J]. Psychological Science, 2003, 14(5): 427-432. DOI PMID
[54]	EGETH H E, YANTIS S. Visual attention: control, representation, and time course[J]. Annual Review of Psychology, 1997, 48: 269-297. PMID
[55]	WEISS A, WURHOFER D, TSCHELIGI M. “I love this dog”—children’s emotional attachment to the robotic dog AIBO[J]. International Journal of Social Robotics, 2009, 1(3): 243-248. DOI URL
[56]	CHANG R C S, LU H P, YANG P S. Stereotypes or golden rules? Exploring likable voice traits of social robots as active aging companions for tech-savvy baby boomers in Taiwan[J]. Computers in Human Behavior, 2018, 84: 194-210. DOI URL
[57]	PRENTICE D A, CARRANZA E. What women and men should be, shouldn't be, are allowed to be, and don't have to be: the contents of prescriptive gender stereotypes[J]. Psychology of Women Quarterly, 2002, 26(4): 269-281. DOI URL
[58]	DOU X, WU C F, NIU J, et al. Effect of voice type and head-light color in social robots for different applications[J]. International Journal of Social Robotics, 2022, 14(1): 229-244. DOI
[59]	COHEN J. Statistical power analysis for the behavioral sciences[M]. 2nd ed. New York: Routledge, 1988: 559-560.
[60]	BARROUILLET P. Theories of cognitive development: from Piaget to today[J]. Developmental Review, 2015, 38: 1-12. DOI URL
[61]	GELMAN S A, MARKMAN E M. Categories and induction in young children[J]. Cognition, 1986, 23(3): 183-209. PMID
[62]	CHANDLER P, SWELLER J. Cognitive load theory and the format of instruction[J]. Cognition and Instruction, 1991, 8(4): 293-332. DOI URL
[63]	王伟伟, 宁瑨, 魏婷. 基于认知负荷的用户感知体验情感评价方法[J]. 包装工程, 2022, 43(4): 147-155.
	WANG W W, NING J, WEI T. Emotional evaluation method of user perceptual experience based on the perspective of cognitive load[J]. Packaging Engineering, 2022, 43(4): 147-155 (in Chinese).

指标	含义
主观量表	对机器人外观的主观评分，分值与满意度呈正相关
总注视时长	视线在兴趣区内所有注视点的注视时间总和，主要反映信息加工的偏向，持续注视时间越长，表明该兴趣区对被试的吸引力或复杂性越高，积极情绪则常导致更长注视
注视次数	一次注视为一个注视点，注视次数是在兴趣区内注视点的总数量，能反映吸引力或难度，注视次数越多，表明该兴趣区对被试的吸引力越强
首次进入时间	从观看样本开始到视线第一次注视到兴趣区的时长，首次注视前时间越短，表明该兴趣区越易被注意到，且越易引起关注
平均瞳孔直径	瞳孔的放大与情感效价呈非线性关系，而与情感唤醒度呈线性关系，即唤醒度越高，瞳孔直径越大

指标	含义
主观量表	对机器人外观的主观评分，分值与满意度呈正相关
总注视时长	视线在兴趣区内所有注视点的注视时间总和，主要反映信息加工的偏向，持续注视时间越长，表明该兴趣区对被试的吸引力或复杂性越高，积极情绪则常导致更长注视
注视次数	一次注视为一个注视点，注视次数是在兴趣区内注视点的总数量，能反映吸引力或难度，注视次数越多，表明该兴趣区对被试的吸引力越强
首次进入时间	从观看样本开始到视线第一次注视到兴趣区的时长，首次注视前时间越短，表明该兴趣区越易被注意到，且越易引起关注
平均瞳孔直径	瞳孔的放大与情感效价呈非线性关系，而与情感唤醒度呈线性关系，即唤醒度越高，瞳孔直径越大

变异来源	III类平方和	自由度	均方	F	P	η²p
修正模型	18.545	11.000	1.686	2.131	0.017
截距	11 506.501	1.000	11 506.501	14 543.404	0
声音	6.912	2.000	3.456	4.368	0.013	0.013 7
动作	8.287	1.000	8.287	10.475	0.001	0.016 6
外观	0.574	1.000	0.574	0.726	0.395	0.001 2
外观×动作	0.058	1.000	0.058	0.073	0.787	0.000 1
动作×声音	0.055	2.000	0.027	0.035	0.966	0.000 1
外观×声音	0.876	2.000	0.438	0.554	0.575	0.001 8
外观×动作×声音	1.508	2.000	0.754	0.953	0.386	0.003 0

变异来源	III类平方和	自由度	均方	F	P	η²p
修正模型	18.545	11.000	1.686	2.131	0.017
截距	11 506.501	1.000	11 506.501	14 543.404	0
声音	6.912	2.000	3.456	4.368	0.013	0.013 7
动作	8.287	1.000	8.287	10.475	0.001	0.016 6
外观	0.574	1.000	0.574	0.726	0.395	0.001 2
外观×动作	0.058	1.000	0.058	0.073	0.787	0.000 1
动作×声音	0.055	2.000	0.027	0.035	0.966	0.000 1
外观×声音	0.876	2.000	0.438	0.554	0.575	0.001 8
外观×动作×声音	1.508	2.000	0.754	0.953	0.386	0.003 0

指标	拟人型	拟动物型	T	P	η²p
总注视时长/ms	11 513.92	10 194.31	2.981	0.003	0.014 3
注视次数/次	22.99	19.40	4.388	0	0.030 9
首次进入时间/ms	16 11.96	2 324.57	-2.264	0.024	0.008 1
平均瞳孔直径/mm	4.84	4.89	-1.191	0.234	0.002 2

机器人如何吸引儿童?外观、动作和声音多感官特征在早期互动中的作用

How do robots attract children? The role of appearance, motion, and voice as multisensory features in early-stage interactions

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 63

相关文章 15

编辑推荐

Metrics

本文评价

指标	有动作	无动作	T	P	η²p
总注视时长/ms	11 853.42	98 61.07	4.542	0	0.034 3
注视次数/次	22.97	19.44	4.318	0	0.031 4
首次进入时间/ms	1 843.69	2 092.06	-0.786	0.432	0.0010
平均瞳孔直径/mm	4.88	4.85	0.733	0.464	0.000 9

指标	男声	女声	无声	F	P	η²p
总注视时长/ms	12 222.78	11 537.48	8 805.27	23.675	0	0.072 9
注视次数/次	23.60	22.33	17.67	20.184	0	0.063 2
首次进入时间/ms	2 021.16	2 121.62	1 765.12	0.450	0.638	0.001 6
平均瞳孔直径/mm	4.87	4.83	4.88	0.538	0.584	0.001 7

[1]	王海涵. 基于YOLOv8-OSRA的钢拱塔表观病害多目标检测方法[J]. 图学学报, 2025, 46(6): 1327-1336.
[2]	夏明海, 罗自荣, 殷谦, 卢钟岳, 蒋涛. 基于CFD的仿鱼机器人多模式游动机理研究[J]. 图学学报, 2025, 46(5): 1105-1112.
[3]	孙浩, 谢滔, 何龙, 郭文忠, 虞永方, 吴其军, 王建伟, 东辉. 多模态文本视觉大模型机器人地形感知算法研究[J]. 图学学报, 2025, 46(3): 558-567.
[4]	李赛赛, 孙博文, 李迪嘉, 潘文娟. 认知机制视域下的机器人手术系统界面设计迭代优化[J]. 图学学报, 2025, 46(2): 469-478.
[5]	贾明超, 冯斌, 吴鹏, 张坤, 桑胜举. 一种融合改进A*算法与改进动态窗口法的文旅服务机器人路径规划[J]. 图学学报, 2024, 45(3): 505-515.
[6]	丁建川, 肖金桐, 赵可新, 贾冬青, 崔炳德, 杨鑫. 基于脉冲神经网络的复杂场景导航避障算法[J]. 图学学报, 2023, 44(6): 1121-1129.
[7]	张伟康, 孙浩, 陈鑫凯, 李叙兵, 姚立纲, 东辉. 基于改进YOLOv5的智能除草机器人蔬菜苗田杂草检测研究[J]. 图学学报, 2023, 44(2): 346-356.
[8]	王秋惠, 王雅馨. 医院消杀机器人作业安全与交互设计策略[J]. 图学学报, 2022, 43(1): 172-180.
[9]	马欢, 冀晶晶, 刘佳豪, 刘雨婷. 面向机器人自主分割的肉品识别分类系统实现[J]. 图学学报, 2021, 42(6): 924-930.
[10]	王秋惠, 姚景一. 下肢外骨骼康复机器人人因工程研究进展[J]. 图学学报, 2021, 42(5): 712-718.
[11]	王豪，郭斌，郝少阳，张秋韵，於志文 . 基于深度学习的个性化对话内容生成方法[J]. 图学学报, 2020, 41(2): 210-216.
[12]	张肇轩 1，王诚斌 1，杨鑫 1，朴星霖 2，王鹏杰 3，尹宝才 1 . 基于模板替换的室内场景建模方法研究[J]. 图学学报, 2020, 41(2): 270-276.
[13]	方伟 1,2，黄增强 3，徐建斌 4，黄羿 1,5，马新强 1,5 . 基于 Spark 的分布式机器人强化学习训练框架[J]. 图学学报, 2019, 40(5): 852-857.
[14]	王秋惠，杨悦 . 基于 QFD 与 RAHP 的餐馆服务机器人人因工程设计[J]. 图学学报, 2019, 40(4): 739-745.
[15]	孙瑞，张文胜. 基于改进蚁群算法的移动机器人平滑路径规划[J]. 图学学报, 2019, 40(2): 344-350.