| 引用本文: | 章程,朱志亮,张子墨,查金吾,付庆庆,冯海贝,李清坤,岳康,马翠霞,王宏安.人机共驾场景中驾驶权接管技术研究综述.软件学报,2026,37(3):1290-1315 |
| |
|
| |
|
|
| 本文已被：浏览 1272次 下载 803次 |
码上扫一扫！ |
|
|
| 人机共驾场景中驾驶权接管技术研究综述 |
|
章程1,2, 朱志亮1,3, 张子墨1,2, 查金吾2, 付庆庆3, 冯海贝1,2, 李清坤1, 岳康1, 马翠霞1,2, 王宏安1,2
|
|
1.中国科学院 软件研究所 人机交互技术与智能信息处理实验室, 北京 100190;2.中国科学院大学 计算机科学与技术学院, 北京 100049;3.华东交通大学 信息与软件工程学院, 江西 南昌 330013
|
|
| 摘要: |
| 智能驾驶技术的快速发展使人机共驾成为平衡自动化能力与人类驾驶权责的重要范式. 实现控制权在人与机器之间的安全、平滑、高效转移的驾驶权接管技术, 成为该领域面临的核心挑战与技术瓶颈之一. 通过从理论框架、技术挑战和交互机制这3个维度系统梳理相关研究, 揭示目前驾驶权接管技术在实时决策和个性化适配方面的局限性, 可以深入剖析当前进展, 明确未来研究方向. 首先, 基于多学科交叉视角, 阐述驾驶权接管的理论基础, 提出基于场景特征的接管分类框架, 分析环境复杂度与驾驶员状态等因素的作用机理, 系统比较唤醒策略与控制算法, 指出当前技术在复杂场景适应性和个性化设计方面的不足. 其次, 探讨人机信任对驾驶权接管的影响机制, 从信任动态建模与多模态交互两个维度, 提出基于信任校准的接管策略优化方法. 最后, 展望大模型与跨模态认知技术融合的发展趋势, 为未来人机无缝协同驾驶提供研究方向. |
| 关键词: 人机共驾 人机信任 驾驶接管 |
| DOI：10.13328/j.cnki.jos.007561 |
| 分类号: |
| 基金项目:重庆市技术创新与应用发展专项重大项目(CSTB2023TAD-STX0027); 科技创新2030—“新一代人工智能”重大项目(2022ZD0117904); 中国科学院重点部署青年人才项目(RCJJ-145-24-14); 北京市自然科学基金(4254109); 重庆市工业和信息化领域“揭榜挂帅”项目(SEKJP001ZJY) |
|
| Survey on Driving Control Takeover Techniques in Human-machine Shared Driving Scenario |
|
ZHANG Cheng1,2, ZHU Zhi-Liang1,3, ZHANG Zi-Mo1,2, ZHA Jin-Wu2, FU Qing-Qing3, FENG Hai-Bei1,2, LI Qing-Kun1, YUE Kang1, MA Cui-Xia1,2, WANG Hong-An1,2
|
|
1.Human-computer Interaction Technology and Intelligent Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China;2.School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China;3.School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China
|
| Abstract: |
| The rapid development of intelligent driving technology has made human-machine collaborative co-driving a key paradigm for balancing automation capabilities with human driving rights and responsibilities. Driving authority takeover technology, which ensures the safe, smooth, and efficient transfer of control between humans and machines, has become one of the core challenges and technical bottlenecks in this field. By systematically reviewing relevant research on theoretical frameworks, technical challenges, and interaction mechanisms, the limitations of driving authority takeover technology in real-time decision-making and personalized adaptation are highlighted. This enables a thorough analysis of current progress and clarifies future research directions. First, from a multidisciplinary perspective, this study elaborates on the theoretical foundation of driving authority takeover, proposes a classification framework based on scenario characteristics, and analyzes the roles of factors such as environmental complexity and driver state. In addition, the wake-up strategies and control algorithms are systematically compared, highlighting the shortcomings of current technology in adapting to complex scenarios and personalized designs. Second, the influence of human-machine trust on driving authority takeover is innovatively explored. From the two dimensions of trust dynamic modeling and multimodal interaction, a trust calibration-based optimization method for takeover strategies is proposed. Finally, the trend toward integrating large models with cross-modal cognitive technology is envisioned, providing research directions for seamless human-machine collaborative driving in the future. |
| Key words: human-machine shared driving human-machine trust driving takeover |
|
|
|
|
