自动驾驶功能使用意愿的影响因素分析

孙守众; 秦华; 陈琪萱; 冉令华

doi:10.3963/j.jssn.1674-4861.2025.02.013

自动驾驶功能使用意愿的影响因素分析

doi: 10.3963/j.jssn.1674-4861.2025.02.013

1.
北京建筑大学机电与车辆工程学院北京 102616
2.
中国标准化研究院北京 100191

基金项目:

国家重点研发计划项目 2023YFF0615902

北京市社会科学基金项目 19GLB029

详细信息

作者简介:
孙守众（2000—），硕士研究生. 研究方向：人因工程，人因学应用. E-mail：1926895290@qq.com

通讯作者:
秦华（1971—），博士，教授. 研究方向：人因工程、人因学应用. E-mail：qinhua@buceaedu.com

中图分类号: U491.1
计量
- 文章访问数: 23
- HTML全文浏览量: 17
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2024-09-06
- 网络出版日期: 2025-09-29

An Analysis of Factors Influencing the Willingness to Use Automated Driving Function

1.
School of Mechanical-Electronic and Vehicle Engineering, Beijing University of Civil Engineering and Architecture. Beijing 102616, China
2.
China National Institute of Standardization, Beijing 100191, China

摘要

摘要: 尽管越来越多配备自动驾驶功能（automated driving function，ADF）的车辆走向市场，但用户的实际使用率并不高。为了促进用户对车辆中自动驾驶功能的认可与应用，了解用户对ADF的使用意愿及其影响因素成为关键。先前的研究调查了在车辆中使用自动化功能的意愿，但这些研究大多受限于技术，调查的对象往往缺乏充分的使用体验。因此，有必要基于充分体验过的用户群体开展调查。研究进行了一项广泛的问卷调查，面向有过使用经验或体验的驾驶人，从人口统计学、行为模式和感受评价3类用户信息入手，探究影响使用意愿的关键因素。研究基于文献和成熟量表，构建了ADF使用意愿的调查问卷，通过线上和线下方式共收集有效问卷223份。通过相关性分析和层次回归分析构建ADF使用意愿预测模型，探究了3类用户因素对用户使用意愿的影响。研究结果表明：①当前环境下，构建的ADF使用意愿预测模型能够解释68.9%的变异；②感知安全是最大的预测因素，共解释了使用意愿36.2%的变异；③新技术倾向、感知有用性、信任、了解程度和年龄对使用意愿的影响同样显著，其中新技术倾向是行为模式信息中影响使用意愿的最大因素；④尽管用户的行为模式对自动驾驶使用意愿的影响显著，但仍然可以通过良性的驾驶体验提升使用意愿。
- 交通工程 /
- 使用意愿 /
- 层次回归模型 /
- 自动驾驶功能 /
- 行为预测
Abstract: With the accelerated launch of automated driving function (ADF) vehicles on the market, the actual usage rate of its users has shown a low trend. In order to promote the acceptance and application of ADF technology by drivers, it is crucial to analyze the key factors affecting their willingness to use it. Previous studies have examined drivers' willingness to use automation functions in vehicle. However, due to technological limitations at the time, surveyed individuals generally lacked adequate practical experience. In view of this, this study conducts an extensive questionnaire survey for fully experienced user groups. This paper explores the key factors affecting the will-ingness to use from three types of user information: demographics, behavior patterns and feeling evaluation. Based on the literature and established scale, the study devises a questionnaire concerning the willingness to use of Automated Driving Function (ADF). It collects 223 valid questionnaires via online and offline methods. The prediction model of ADF willingness to use is constructed through correlation analysis and hierarchical regression analysis, and the influence of three types of user factors on users' willingness to use is explored. The results show that : ①in the current environment, the constructed predictive model for willingness to use ADF can explain 68.9% of the variance. ②Perceived safety stands out as the predominant forecasting predictor, accounting for 36.2% of the variance in willingness to use. ③New technology orientation, perceived usefulness, trust, understanding and age also have a significant impact on the willingness to use, among which new technology orientation is the biggest factor affecting the willingness to use in behavioral pattern information.④Although the user's behavior pattern has a significant impact on the willingness to use autonomous driving function, it can still improve the willingness to use through a benign driving experience.
- traffic engineering /
- willingness to use /
- hierarchical regression model /
- autonomous driving function /
- be-havior prediction

HTML全文

图 1 研究框架示意图

Figure 1. Schematic diagram of research framework

下载: 全尺寸图片幻灯片

表 1 参试者人口统计信息

Table 1. Demographic information of participants

人口属性	参试者占比
性别	男（56%）；女（44%）
年龄/岁	≥18~25（45.4%）；＞25~35（22.5%）；＞35~45（17.1%）；＞45~55（9.5%）；>55（5.5%）
驾龄/年	≤1（24.2%）；＞1~3（34.8%）；＞3~10（17.6%）；＞10（23.4%）

下载: 导出CSV

表 2 影响使用意愿的因素间相关性分析

Table 2. Correlation analysis of factors affecting willingness to use

变量	均值	标准差	因素1	因素2	因素3	因素4	因素5	因素6	因素7	因素8	因素9	因素10	因素11
因素1	4.605	1.422	1
因素2	4.755	1.23	0.515 ^***	1
因素3	5.153	1.017	0.547^***	0.453^**	1
因素4	4.813	1.092	0.475^***	0.296^**	0.448^***	1
因素5	4.99	1.202	0.306^*	0.326^**	0.419^***	0.369^**	1
因素6	5.214	1.353	0.495^***	0.021	0.493^***	0.455^***	0.203^**	1
因素7	4.238	1.601	0.344^**	0.237^*	0.248^*	0.262^*	0.138	0.287^**	1
因素8	3.135	1.781	0.395^***	0.267^**	0.172^*	0.125	0.300^**	0.328^**	0.139	1
因素9	3.584	2.017	0.287^*	0.167	0.322^**	0.341^**	0.388^***	0.436^***	0.122	0.114	1
因素10	1.447	0.497	0.341^**	0.138	0.112	0.152	0.080	0.148	0.461	0.430^***	0.355^**	1
因素11	2.064	1.30	0.408^***	0.170	0.204^*	0.162	0.028	0.253	0.459	0.752^***	0.288^**	-0.305^**	1
注：1.* p ≤0.05， p ≤0.005，* p ≤0.001。 2.因素1：感知安全；因素2：信任；因素3：感知有用性；因素4：感知易用性；因素5：了解程度；因素6：新技术倾向；因素7：驾驶风格；因素8：驾驶频率；因素9：学习途径；因素10：性别；因素11：年龄。

下载: 导出CSV

表 3 KMO和巴特利特检验

Table 3. KMO and Bartlett's tests

KMO取样适切性量数	巴特利特检验
KMO取样适切性量数	近似卡方	自由度	显著性
0.827	3 221.345	325	0.000

下载: 导出CSV

表 4 问卷变量与信度检验

Table 4. Questionnaire variables and reliability testing

一级变量(Cronbach’s α)	二级变量	表示	描述	因子载荷	AVE	CR
因素1（0.863）	情绪安全	EM1	使用自动驾驶功能是令人害怕的（反）		0.725
		EM2	使用自动驾驶辅功能是令人焦虑的（反）		0.840
		EM3	使用自动驾驶功能是令人放松的		0.746
		EM4	使用自动驾驶功能是令人宽慰的	0.690	0.538	0.912
	认知安全	CO1	可以预测使用自动驾驶功能时的危险		0.754
		CO2	可以控制使用自动驾驶功能时的危险		0.752
		CO3	清楚自动驾驶功能在行驶中的工作状态		0.671
		CO4	使用自动驾驶功能是安全的		0.670
因素2（0.733）	分心	DI1	担心用自动驾驶功能对驾驶任务分心（反）		0.738
	系统性能	PE1	自动驾驶功能的性能是令人满意的		0.717
	系统性能	PE2	自动驾驶功能提高了我的表现	0.702	0.508	0.740
	心智模型偏差	ME1	对自动驾驶功能的信任是适度的		0.676
因素3（0.725）		PU1	自动驾驶功能是有用的		0.743
		PU2	自动驾驶功能可以提高我的驾驶安全性	0.722	0.515	0.761
		PU3	自动驾驶功能可以使我的驾驶更容易		0.687
因素4（0.766）		PE1	自动驾驶功能是容易理解的		0.721
		PE2	学会使用自动驾驶功能是容易的	0.714	0.547	0.783
		PE3	自动驾驶功能的使用是方便的（操作流程）		0.781
因素5（0.678）		UN1	对自动驾驶功能的了解是正确的	0.767	0.558	0.716
因素5（0.678）		UN2	对自动驾驶功能的了解是完整的		0.726
因素6（0.711）		NE1	对新技术的态度是积极的	0.771	0.545	0.705
因素6（0.711）		NE2	对更新车机系统在内的智能设备系统是积极的		0.704
因素7（0.705）		DR1	手动驾驶时会以尽可能快的车速行驶（反）	0.737	0.515	0.702
因素7（0.705）		DR2	手动驾驶时会为了提升车速频繁变道（反）		0.708
因素8
因素9
因素10
因素11
注：1.因素1：感知安全；因素2：信任；因素3：感知有用性；因素4：感知易用性；因素5：了解程度；因素6：新技术倾向；因素7：驾驶风格；因素8：驾驶频率；因素9：学习途径；因素10：性别；因素11：年龄。

下载: 导出CSV

表 5 层次回归分析

Table 5. Hierarchical Regression Analysis

步骤	预测变量	第1步β	t	第2步β	t	第3步β	t	SE	R²	ΔR²
1	性别	-0.053	-0.67					0.192	0.065	0.065^*
	年龄	-0.266	-3.452^*					0.073
2	性别			-0.028	-0.336			0.211	0.400	0.335^***
	年龄			-0.184	-2.086^*			0.087
	驾驶频率			0.074	1.176			0.105
	学习途径			0.126	1.644			0.088
	驾驶风格			-0.113	-1.405			0.063
	新技术倾向			0.305	4.279^***			0.082
	了解程度			0.190	2.716^*			0.097
3	性别					0.047	0.724	0.161	0.689	0.289^***
	年龄					-0.149	-1.849^*	0.061
	驾驶频率					0.073	1.256	0.079
	学习途径					0.097	1.482	0.060
	驾驶风格					-0.073	-1.182^***	0.081
	新技术倾向					0.296	3.465	0.064
	了解程度					0.164	2.110^*	0.072
	感知安全					0.362	4.088^***	0.092
	信任					0.188	1.844^*	0.106
	感知有用性					0.235	2.768^**	0.083
	感知易用性					0.112	1.414	0.075
注：^p ≤0.05，^* p ≤0.005，^*** p ≤0.001。

下载: 导出CSV

表 6 回归模型结果

Table 6. Regression model results

因素	B	β	t	p	VIF
常量	0.414	0	0.646	0	0
年龄	-0.111	-0.117	-1.524	0.030	1.077
新技术倾向	0.228	0.288	3.342	0.001	1.221
了解程度	0.151	0.192	2.425	0.010	1.012
感知安全	0.291	0.388	4.782	0.001	1.146
信任	0.097	0.136	1.723	0.032	1.221
感知有用性	0.190	0.173	2.292	0.015	1.505

下载: 导出CSV

表 7 感知安全子因素与使用意愿相关性分析

Table 7. Correlation analysis between perceived safety sub factors and willingness to use

相关性	使用意愿	情绪安全	认知安全	分心（反）
相关性	1	0.492**	0.333**	0.629**
双尾检验		< 0.001	< 0.001	< 0.001
案例数		223	223	223
注：**. 在0.01级别（双尾），相关性显著。

下载: 导出CSV

参考文献(29)

[1]	PARK J, HONG E P, LE H T. Adopting autonomous vehicles: the moderating effects of demographic variables[J]. Journal of Retailing and Consumer Services, 2021, 63(11): 102687.
[2]	MARA M, MEYER K. Acceptance of autonomous vehicles: an overview of user-specific, car-specific and contextual determinants[J]. User Experience Design in the Era of Automated Driving, 2022, 980(1): 51-83.
[3]	DEGUZMAN C A, DONMEZ B. Knowledge of and trust in advanced driver assistance systems[J]. Accident Analysis & Prevention, 2021, 156(7): 106121.
[4]	KAYE S A, SOMORAY K, RODWELL D, et al. Users' acceptance of private automated vehicles: a systematic review and meta-analysis[J]. Journal of Safety Research, 2021, 79(12): 352-367.
[5]	LOUW T, MADIGAN R, LEE Y M, et al. Drivers' intentions to use different functionalities of conditionally automated cars: a survey study of 18, 631 drivers from 17 countries[J]. International Journal of Environmental Research and Public Health, 2021, 18(22): 12054. doi: 10.3390/ijerph182212054
[6]	NORDHOFF S, LOUW T, INNAMAA S, et al. Using the UTAUT2 model to explain public acceptance of conditionally automated(L3)cars: a questionnaire study among 9, 118 car drivers from eight European countries[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2020, 74 (10): 280-297.
[7]	徐亮, 陆洋, 孙造诣, 等. 基于自动驾驶汽车接受度的个性化用户研究[J]. 包装工程, 2023, 44(20): 42-58. XU L, LU Y, SUN Z Y, et al. Research on personalized users based on the acceptance of autonomous vehicle[J]. Packaging Engineering, 2023, 44(20): 42-58. (in Chinese)
[8]	鄢云珠, 傅忠宁, 岳金田. 车辆怠速起停系统使用意愿结构方程模型及影响因素分析[J]. 交通信息与安全, 2023, 41 (6): 161-170. doi: 10.3963/j.jssn.1674-4861.2023.06.018 YAN Y Z, FU Z N, YUE J T. An analysis of the influence factors on using intention of vehicle idle start-stop system with a structural equation model[J]. Journal of Transport Information and Safety, 2023, 41(6): 161-170. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.06.018
[9]	HEWITT C, POLITIS I, AMANATIDIS T, et al. Assessing public perception of self-driving cars: the autonomous vehicle acceptance model[C]. 24^th Intelligent User Interfaces. New York: Association for Computing Machinery, 2019.
[10]	FEYS M, ROMBAUT E, VANHAVERBEKE L. Does a test ride influence attitude towards autonomous vehicles? a field experiment with pretest and posttest measurement[J]. Sustainability, 2021, 13(10): 5387. doi: 10.3390/su13105387
[11]	WANG S, LI Z, WANG Y, et al. Evidence of automated vehicle safety's influence on people's acceptance of the automated driving technology[J]. Accident Analysis & Prevention, 2024, 195(2): 107381.
[12]	SENER I N, ZMUD J, WILLIAMS T. Measures of baseline intent to use automated vehicles: a case study of Texas cities[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2019, 62(4): 66-77.
[13]	GREENWOOD P M, BALDWIN C L. Preferred sources of information, knowledge, and acceptance of automated vehicle systems: effects of gender and age[J]. Frontiers in Psychology, 2022, 13(5): 806552.
[14]	MA Z, ZHANG Y. Drivers trust, acceptance, and takeover behaviors in fully automated vehicles: effects of automated driving styles and driver's driving styles[J]. Accident Analysis & Prevention, 2021, 159(9): 106238.
[15]	YOUSSEF P, PLANT K L, WATERSON B. Narrow passage interactions: a UK-based exploratory survey study to identify factors affecting driver decision-making[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2024, 100(1): 402-418.
[16]	XU Z, ZHANG K, MIN H, et al. What drives people to accept automated vehicles? findings from a field experiment[J]. Transportation Research Part C: Emerging Technologies, 2018, 95(11): 320-334.
[17]	王云泽, 李英杰, 唐立. 交通运输从业者对自动驾驶接受度建模与分析[J]. 交通运输工程与信息学报, 2023, 21(2): 42-54. WANG Y Z, LI Y J, TANG L. Modeling and analysis of acceptance of autonomous driving by transportation practitioners[J]. Journal of Transportation Engineering and Information, 2023, 21(2): 42-54. (in Chinese)
[18]	CAO J, LIN L, ZHANG J, et al. The development and validation of the perceived safety of intelligent connected vehicles scale[J]. Accident Analysis & Prevention, 2021, 154(5): 106092.
[19]	ZHANG T, TAO D, QU X, et al. The roles of initial trust and perceived risk in public's acceptance of automated vehicles[J]. Transportation Research Part C: Emerging Technologies, 2019, 98(1): 207-220.
[20]	REAGAN I J, KIDD D G, CICCHINO J B. Driver acceptance of adaptive cruise control and active lane keeping in five production vehicles[C]. 61^th Human Factors and Ergonomics Society Annual Meeting, Los Angeles: SAGE Publications, 2017.
[21]	NORDHOFF S, STAPLE J, HE X, et al. Perceived safety and trust in SAE level 2 partially automated cars: results from an online questionnaire[J]. Plos one, 2021, 16(12): 260953.
[22]	DAVIS F D, BAGOZZI R P, WARSHAW P R. User acceptance of computer technology: a comparison of two theoretical models[J]. Management Science, 1989, 35(8): 982-1003. doi: 10.1287/mnsc.35.8.982
[23]	SUN X F. Developing and validating a model for assessing autonomous vehicles acceptance[J]. International Journal of Human-Computer Interaction, 2024, 40(18): 5503-5516. doi: 10.1080/10447318.2023.2238343
[24]	HUANG T. Psychological factors affecting potential users'intention to use autonomous vehicles[J]. Plos one, 2023, 18(3): 282915.
[25]	LI X, RONG J, LI Z, et al. Modeling drivers' acceptance of augmented reality head-up display in connected environment[J]. Displays, 2022, 75(12): 102307.
[26]	李慧慧, 胡启洲, 雷爱国, 等. 基于计划行为理论的驾驶人未礼让行为研究[J]. 交通运输工程与信息学报, 2020, 18 (4): 110-119. LI H H, HU Q Z, LEI A G, et al. Driver's noncomity behavior based on planned behavior theory[J]. Journal of Transportation Engineering and Information, 2020, 18(4): 110-119. (in Chinese)
[27]	LEE Y M, MADIGAN R, LOUW T, et al. Does users' experience and evaluation of level 3 automated driving functions predict willingness to use: results from an on-road study[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2023, 99(11): 473-484.
[28]	KAYE S A, NANDAVAR S, YASMIN S, et al. Consumer knowledge and acceptance of advanced driver assistance systems[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2022, 90(10): 300-311.
[29]	QU W, SUN H, GE Y. The effects of trait anxiety and the big five personality traits on self-driving car acceptance[J]. Transportation, 2021, 48(5): 2663-2679. doi: 10.1007/s11116-020-10143-7