[1]李德毅,王留召,杜煜,等.空间智能：驾驶态势中的活地图[J].智能系统学报,2026,21(2):498-509.[doi:10.11992/tis.202601022]
LI Deyi,WANG Liuzhao,DU Yu,et al.Spatial intelligence: a living map in driving situation[J].CAAI Transactions on Intelligent Systems,2026,21(2):498-509.[doi:10.11992/tis.202601022]
点击复制
LI Deyi,WANG Liuzhao,DU Yu,et al.Spatial intelligence: a living map in driving situation[J].CAAI Transactions on Intelligent Systems,2026,21(2):498-509.[doi:10.11992/tis.202601022]
空间智能：驾驶态势中的活地图
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第2期
页码:
498-509
栏目:
学术论文—智能系统
出版日期:
2026-03-05
- Title:
- Spatial intelligence: a living map in driving situation
- Keywords:
- spatial intelligence; living map; right of way; driving situation map; moving with the vehicle; variable-resolution grid; logarithmic polar coordinates; Bayesian filtering; hierarchical memory; autonomous driving
- 分类号:
- TP18
- 摘要:
- 本文研究随车而动的驾驶员眼中的活地图在无人驾驶过程中的实时生成技术，即驾驶空间智能。在线生成并持续更新车辆当前路权的地理空间表征，乃是机器驾驶脑中驾驶决策的基础数据，对无人驾驶车辆的认知工程实现具有基础性意义。以变粒度对数极坐标栅格为统一形式化语言，给出活地图系统生成框架；能从传统意义的静态地图问题提升为随车而动的地理空间的状态估计问题，并被持续更新与估计；能承载多源异构的道路传感器感知与先验知识的融合，以贝叶斯滤波为核心机制维护其后验分布；用瞬时记忆—工作记忆—长时记忆维持地图的连续性，并用实时规划实现驾驶活地图的认知闭环。如果路上没有任何其他移动障碍物，活地图就可以让车在不同路段以不同速度从出发地自主驾驶到达目的地。
- Abstract:
- This paper examines the real-time generation technology of the live map from the driver’s perspective, who follows the car during the process of autonomous driving, known as driving space intelligence. Online generation and continuous updating of the geospatial representation of the vehicle’s current road right is the basic data of driving decision-making in the machine driver’s mind, which is of fundamental significance to the realization of cognitive engineering of unmanned vehicles. Taking a variable granularity logarithmic polar grid as a unified formal language, the generation framework of the active map system is given. It can be upgraded from the traditional static map problem to the state estimation problem of the geographical space that moves with the car, and it can be continuously updated and estimated; It can carry the fusion of multi-source heterogeneous road sensor perception and prior knowledge, and maintain posterior distribution with Bayesian filtering as the core mechanism; Instantaneous memory-working memory-long-term memory is used to maintain the continuity of the map, and real-time planning is used to realize the cognitive closed loop of the driving map. If there are no other moving obstacles on the road, the mobile map can enable the car to drive from the starting point to the destination at varying speeds on different sections.
- 参考文献/References:
-
[1] ASRAT K T, CHO H J. A comprehensive survey on high-definition map generation and maintenance[J]. ISPRS international journal of geo-information, 2024, 13(7): 232
[2] 李德毅, 张天雷, 韩威, 等. 认知机器的结构和激活[J]. 智能系统学报, 2024, 19(6): 1604-1613 LI Deyi, ZHANG Tianlei, HAN Wei, et al. Structure and activation of cognitive machines[J]. CAAI transactions on intelligent systems, 2024, 19(6): 1604-1613
[3] LI Qi, WANG Yue, WANG Yilun, et al. HDMapNet: an online HD map construction and evaluation framework[EB/OL]. (2021-07-13)[2026-01-18]. https://arxiv.org/abs/2107.06307.
[4] 李德毅. 认知物理学导引[J]. 智能系统学报, 2024, 19(3): 493 LI Deyi. Introduction to cognitive physics[J]. CAAI transactions on intelligent systems, 2024, 19(3): 493
[5] 李德毅, 殷嘉伦, 张天雷, 等. 机器认知四要素说[J]. 中国基础科学, 2023, 25(3): 1-10,22 LI Deyi, YIN Jialun, ZHANG Tianlei, et al. Four most basic elements in machine cognition[J]. China basic science, 2023, 25(3): 1-10,22
[6] LI Deyi, LIU Changyu, GAN Wenyan. A new cognitive model: Cloud model[J]. International journal of intelligent systems, 2009, 24(3): 357-375
[7] ATKINSON R C, SHIFFRIN R M. Human memory: a proposed system and its control processes[M]//SPENCE K W, SPENCE J T, eds. Psychology of Learning and Motivation. New York: Academic Press, 1968: 89-195.
[8] BADDELEY A D, HITCH G. Working memory[M]//BOWER G H, ed. Psychology of Learning and Motivation. New York: Academic Press, 1974: 47-89.
[9] SAND?Y S S, HEGDE J, SCHJ?LBERG I, et al. Polar map: a digital representation of closed structures for underwater robotic inspection[J]. Aquacultural engineering, 2020, 89: 102039
[10] GENG Junyi, LANGELAAN J W. A quasi polar local occupancy grid approach for vision-based obstacle avoidance[C]//AIAA Guidance, Navigation, and Control Conference. Grapevine: AIAA, 2017: 1-25.
[11] QIU Wenzhao, Pang Shanmin, Zhang Hao, et al. HeightMapNet: explicit height modeling for end-to-end HD map learning[EB/OL]. (2021-07-13)[2026-01-18]. https://arxiv.org/abs/2107.06307.
[12] FOX D, BURGARD W, THRUN S. Markov localization for mobile robots in dynamic environments[J]. Journal of artificial intelligence research, 1999, 11: 391-427
[13] KALMAN R E. A new approach to linear filtering and prediction problems[J]. Journal of basic engineering, 1960, 82(1): 35-45
[14] ASGHARIVASKASI A, ATANASOV N. Active Bayesian multi-class mapping from range and semantic segmentation observations[C]//2021 IEEE International Conference on Robotics and Automation. Xi’an: IEEE, 2021: 1-7.
[15] MORAVEC H, ELFES A. High resolution maps from wide angle sonar[C]//Proceedings of 1985 IEEE International Conference on Robotics and Automation. St. Louis: IEEE, 2003: 116-121.
[16] ELFES A. Using occupancy grids for mobile robot perception and navigation[J]. Computer, 1989, 22(6): 46-57
[17] NARAYANA M, KOLLING A, NARDELLI L, et al. Lifelong update of semantic maps in dynamic environments[EB/OL]. (2020-10-17)[2026-01-18]. https://arxiv.org/abs/2010.08846.
[18] THRUN S, BURGARD W, FOX D. Probabilistic robotics[M]. Cambridge, Mass.: MIT Press, 2006.
[19] DOUCET A, FREITAS N, GORDON N. Sequential Monte Carlo methods in practice[M]. New York: Springer, 2001.
[20] 李德毅, 刘常昱. 论正态云模型的普适性[J]. 中国工程科学, 2004, 6(8): 28-34 LI Deyi, LIU Changyu. Study on the universality of the normal cloud model[J]. Strategic study of CAE, 2004, 6(8): 28-34
[21] SANFELIU A, FU K S. A distance measure between attributed relational graphs for pattern recognition[J]. IEEE transactions on systems, man, and cybernetics, 1983, 13(3): 353-362
备注/Memo
收稿日期:2026-1-18。
作者简介:李德毅，中国工程院院士，中国人工智能学会名誉理事长，中国指挥与控制学会名誉理事长，中国人工智能学会会士，军事科学院研究员，吴文俊人工智能科学技术奖最高成就奖获得者，我国不确定性人工智能领域的主要开拓者、无人驾驶的积极引领者和 人工智能产学研发展的重要推动者。 E-mail：lidy@cae.cn。;王留召，研究员，北京测绘学会常务理事，主要研究方向为数字摄影测量、移动测量。先后获得河南省科技进步一等奖、测绘科技进步一等奖、国家科技进步二等奖、首届青年测绘地理信息科技创新人才奖。E-mail：wanglz@casm.ac.cn。;殷嘉伦，助理研究员，博士后，主要研究方向为自动驾驶、不确定性决策。E-mail：yinjialun@tsari.tsinghua.edu.cn。
通讯作者:殷嘉伦. E-mail：yinjialun@tsari.tsinghua.edu.cn
更新日期/Last Update:
1900-01-01