由感知到动作决策一体化的类脑导航技术研究现状与未来发展

doi:10.7527/S1000-6893.2019.23280

综述

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

由感知到动作决策一体化的类脑导航技术研究现状与未来发展

杨闯¹, 刘建业^1,2,3, 熊智^1,2,3, 赖际舟^1,2,3, 熊骏¹

1. 南京航空航天大学自动化学院导航研究中心, 南京 211106;
2. 先进飞行器导航、控制与健康管理工业和信息化部重点实验室, 南京 211106;
3. 卫星通信与导航江苏高校协同创新中心, 南京 210016

收稿日期:2019-07-09 修回日期:2019-08-03 出版日期:2020-01-15 发布日期:2019-09-27
通讯作者: 刘建业 E-mail:ljyac@nuaa.edu.cn
基金资助:
国家自然科学基金（61873125，61673208，61703208，61533008，61533009，61973160）；江苏省自然科学基金（BK2018 1291）；中央高校基本科研业务费专项资金（NP2018108，NZ2019007）；江苏省六大人才高峰项目基金（2015-XXRJ-005）

Brain-inspired navigation technology integrating perception and action decision: A review and outlook

YANG Chuang¹, LIU Jianye^1,2,3, XIONG Zhi^1,2,3, LAI Jizhou^1,2,3, XIONG Jun¹

1. Navigation Research Center, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. Key Laboratory of Navigation, Control and Health-Management Technologies of Advanced Aerocraft, Ministry of Industry and Information Technology, Nanjing 211106, China;
3. Satellite Communication and Navigation Collaborative Innovation Center, Nanjing 210016, China

Received:2019-07-09 Revised:2019-08-03 Online:2020-01-15 Published:2019-09-27
Supported by:
National Natural Science Foundation of China (61873125, 61673208, 61703208, 61533008, 61533009, 61973160); Natural Science Foundation of Jiangsu Province (BK20181291); Fundamental Research Funds for the Central Universities (NP2018108, NZ2019007); Jiangsu Provincial Six Talent Peaks (2015-XXRJ-005)

摘要/Abstract

摘要： 随着脑与神经科学以及人工智能技术的持续发展，昆虫和哺乳动物大脑导航机理启发下的感知/认知/路径规划/动作决策一体化类脑导航技术得到了较大发展，可以实现由原始感知信息输入到导航动作决策的直接输出，呈现出接近动物端到端面向目标导航的智能行为，具有提高密集型无人机集群导航鲁棒性、准确性、实时响应动作、自主智能性以及计算效率的潜力。阐述了昆虫和哺乳动物大脑导航机理及其互补对称关系，以及昆虫和哺乳动物大脑导航机理启发的端到端类脑导航技术内涵；论述了类脑导航技术研究进展，包括类脑环境感知、类脑空间认知、面向目标类脑导航；分析了类脑导航向智能化、神经形态系统以及群体导航发展的新趋势；最后讨论了类脑导航技术应用于无人机密集集群系统时存在的挑战。

关键词: 类脑导航, 感知与动作决策一体化, 大脑导航, 神经形态系统, 类脑集群导航, 无人机密集集群, 人工智能

Abstract: With the sustained development of brain and neuroscience as well as artificial intelligence, brain-like navigation technology inspired by insect & mammal has been greatly developed, integrating the abilities of perception, cognition, path planning and action decision-making. The brain-inspired navigation can directly produce action decision-making of navigation based on the perception input from raw sensory cues, with emerging intelligence similar to the end-to-end character of goal-directed navigation of animal, which can potentially improve the performance of robustness, accuracy, real-time response to action decision-making, autonomy & intelligence, and computing efficiency of the dense UAV swarm navigation. In this paper, we first make a brief discussion of the neural basis of insect & mammal navigation, the complementary symmetry between insect swarm navigation and mammal navigation, and the concept of brain-like navigation technology inspired by insect & mammal. After that, we emphatically review the state of the art of the brain-inspired end-to-end navigation, including brain-inspired perception, spatial cognition, and goal-directed navigation. Then we describe the new trends of brain-inspired navigation towards intelligence, neuromorphic system and swarm navigation. Finally, we analyse the challenges of applying brain-inspired navigation technology to dense UAV swarm.

Key words: brain-inspired navigation, integration of perception and action decision, brain navigation, neuromorphic system, brain-inspired swarm navigation, dense UAV swarm, artificial intelligence

中图分类号:

V249.32

杨闯, 刘建业, 熊智, 赖际舟, 熊骏. 由感知到动作决策一体化的类脑导航技术研究现状与未来发展[J]. 航空学报, 2020, 41(1): 23280-023280.

YANG Chuang, LIU Jianye, XIONG Zhi, LAI Jizhou, XIONG Jun. Brain-inspired navigation technology integrating perception and action decision: A review and outlook[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(1): 23280-023280.

参考文献 72

[1]	HONKANEN A, ADDEN A, DA SILVA FREITAS J, et al. The insect central complex and the neural basis of navigational strategies[J]. Journal of Experimental Biology, 2019, 222(S1):1-15.
[2]	OMER D B, MAIMON S R, LAS L, et al. Social place-cells in the bat hippocampus[J]. Science, 2018, 359(6372):218-224.
[3]	MAYA G S, LIORA L, YOSSI Y, et al. Spatial cognition in bats and rats:From sensory acquisition to multiscale maps and navigation[J]. Nature Reviews Neuroscience, 2015, 16(2):94-108.
[4]	CHUNG S-J, PARANJAPE A A, DAMES P, et al. A survey on aerial swarm robotics[J]. IEEE Transactions on Robotics, 2018, 34(4):837-855.
[5]	熊骏, 熊智, 刘建业, 等. 一种基于置信传播和协同信息筛选的无人机编队协同导航方法[C]//2018年无人载体导航与控制技术发展及应用学术研讨峰会. 北京:中国惯性技术学会, 2018:42-46. XIONG J, XIONG Z, LIU J Y, et al. Cooperative navigation method based on belief propagation and cooperative message screening[C]//Proceedings of the Development and Application of Unmanned Vehicle Navigation and Control Technology. Beijing:Chinese Society of Inertial Technology, 2018:42-46(in Chinese).
[6]	许建新, 熊智, 陈明星, 等. 多无人机辅助定位信标的区域导航定位算法[J]. 航空学报, 2018, 39(10):322172. XU J X, XIONG Z, CHEN M X, et al. Regional navigation algorithm assisted by locations of multi uavs[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(10):322172(in Chinese).
[7]	许晓伟, 赖际舟, 吕品, 等. 多无人机协同导航技术研究现状及进展[J]. 导航定位与授时, 2017, 4(4):1-9. XU X W, LAI J Z, LV P, et al. a literature review on the research progress of the cooperative navigation technology for multiple UAVs[J]. Navigation Positioning & Timing, 2017, 4(4):1-9(in Chinese).
[8]	孙瑶洁, 熊智, 李文龙, 等. 无人机集群类脑导航系统综述[J]. 航空计算技术, 2019, 49(3):130-134. SUN Y J, XIONG Z, LI W L, et al. Research status and progress of brain-like formation navigation system[J]. Aeronautical Computing Technique, 2019, 49(3):130-134(in Chinese).
[9]	CHIALVO D R, MILLONAS M M. The biology and technology of intelligent autonomous agents[M]. Heidelberg:Springer, 1995:439-450.
[10]	BUSH D, BARRY C, MANSON D, et al. Using grid cells for navigation[J]. Neuron, 2015, 87(3):507-520.
[11]	YUAN M, TIAN B, SHIM V A, et al. An entorhinal-hippocampal model for simultaneous cognitive map building[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.
[12]	EDVARDSEN V. Navigating by decoding grid cells[D]. Norway:Norwegian University of Science and Technology, 2019:155-201.
[13]	刘建业, 杨闯, 熊智, 等. 无人机类脑吸引子神经网络导航技术[J]. 导航定位与授时, 2019, 6(5):52-60. LIU J Y, YANG C, XIONG Z, et al. Attractor neural network-based brain-inspired navigation technology for UAV[J]. Navigation Positioning & Timing, 2019, 6(5):52-60(in Chinese).
[14]	HYMAN J M, ZILLI E A, PALEY A M, et al. Working memory performance correlates with prefrontal-hippocampal theta interactions but not with prefrontal neuron firing rates[J]. Frontiers in Integrative Neuroscience, 2010, 4(2):1-13.
[15]	STEFFEN L, REICHARD D, WEINLAND J, et al. Neuromorphic stereo vision:A survey of bio-inspired sensors and algorithms[J]. Frontiers in Neurorobotics, 2019, 13(28):1-20.
[16]	TIAN S, EBERT F, JAYARAMAN D, et al. Manipulation by feel:Touch-based control with deep predictive models[EB/OL]. (2019-03-11)[2019-07-09]. https://arxiv.org/abs/1903.04128.
[17]	HATWELL Y, STRERI A, GENTAZ E. Touching for knowing:Cognitive psychology of haptic manual perception[M]. Benjamins:John Benjamins Publishing, 2003:1-20.
[18]	FEI F, TU Z, ZHANG J, et al. Learning extreme hummingbird maneuvers on flapping wing robots[EB/OL]. (2019-02-25)[2019-07-09].https://arxiv.org/abs/1902.09626.
[19]	WU W C, SCHENATO L, WOOD R J, et al. Biomimetic sensor suite for flight control of a micromechanical flying insect:Design and experimental results[C]//IEEE International Conference on Robotics & Automation. Piscataway, NJ:IEEE Press, 2003.
[20]	SRINIVASAN M V. An image-interpolation technique for the computation of optic flow and egomotion[J]. Biological Cybernetics, 1994, 71(5):401-415.
[21]	VARGA M, ZUFFEREY J C, HEITZ G H M, et al. Evaluation of control strategies for fixed-wing drones following slow-moving ground agents[J]. Robotics & Autonomous Systems, 2015, 72:285-294.
[22]	BASIRI M, SCHILL F S, FLOREANO D, et al. Audio-based localization for swarms of micro air vehicles[C]//IEEE International Conference on Robotics & Automation. Piscataway, NJ:IEEE Press, 2014:4279-4734.
[23]	BAO X, GJORGIEVA E, SHANAHAN L K, et al. Grid-like neural representations support olfactory navigation of a two-dimensional odor space[J]. Neuron, 2019, 102(3):1-10.
[24]	BADDELEY B, GRAHAM P, PHILIPPIDES A, et al. Holistic visual encoding of ant-like routes:Navigation without waypoints[J]. Adaptive Behavior, 2011, 19(1):3-15.
[25]	CARTWRIGHT B A, COLLETT T S. Landmark maps for honeybees[J]. Biological Cybernetics, 1987, 57(1-2):85-93.
[26]	MOORE T, ZIRNSAK M. Neural mechanisms of selective visual attention[J]. Annual Review of Neuroscience, 2017, 18(1):193-222.
[27]	HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex[J]. The Journal of physiology, 1962, 160(1):106-154.
[28]	MANCINI M, COSTANTE G, VALIGI P, et al. Towards domain independence for learning-based monocular depth estimation[J]. IEEE Robotics & Automation Letters, 2017, 2(3):1-8.
[29]	ROSENBAUM D, BESSE F, VIOLA F, et al. Learning models for visual 3D localization with implicit mapping[EB/OL]. (2018-12-12)[2019-07-09]. https://arxiv.org/abs/1807.03149.
[30]	KAUFMANN E, LOQUERCIO A, RANFTL R, et al. Deep drone racing:Learning agile flight in dynamic environments[EB/OL]. (2018-10-09)[2019-07-09]. https://arxiv.org/abs/1806.08548.
[31]	PALMER S E. Modern theories of gestalt perception[J]. Mind & Language, 2010, 5(4):289-323.
[32]	MCNAUGHTON B L, BATTAGLIA F P, OLE J, et al. Path integration and the neural basis of the cognitive map[J]. Nature Reviews Neuroscience, 2006, 7(8):663-678.
[33]	TAMAS M, STAN F, KE C, et al. Bayesian integration of information in hippocampal place cells[J]. Plos One, 2015, 10(8):e0136128.
[34]	BURAK Y, FIETE I R. Accurate path integration in continuous attractor network models of grid cells[J]. PLoS Computational Biology, 2009, 5(2):1-16.
[35]	BALL D, HEATH S, WILES J, et al. OpenRatSLAM:An open source brain-based SLAM system[J]. Autonomous Robots, 2013, 34(3):149-176.
[36]	KANITSCHEIDER I, FIETE I. Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems[C]//Proceedings of the Advances in Neural Information Processing Systems, 2017:4529-4538.
[37]	CUEVA C J, WEI X X. Emergence of grid-like representations by training recurrent neural networks to perform spatial localization[EB/OL]. (2018-03-21)[2019-07-09]. https://arxiv.org/abs/1803.07770.
[38]	BANINO A, BARRY C, URIA B, et al. Vector-based navigation using grid-like representations in artificial agents[J]. Nature, 2018, 557(7705):429.
[39]	HWU T, KRICHMAR J, ZOU X. A complete neuromorphic solution to outdoor navigation and path planning[C]//2017 IEEE International Symposium on Circuits and Systems. Piscataway, NJ:IEEE Press, 2017:1-4.
[40]	TANG G, MICHMIZOS K P. Gridbot:An autonomous robot controlled by a spiking neural network mimicking the brain's navigational system[C]//International Conference on Neuromorphic Systems, 2018:4-11.
[41]	BURGESS N, JACKSON A, HARTLEY T, et al. Predictions derived from modelling the hippocampal role in navigation[J]. Biological Cybernetics, 2000, 83(3):301-312.
[42]	EDVARDSEN V. Goal-directed navigation based on path integration and decoding of grid cells in an artificial neural network[J]. Natural Computing, 2016, 18(1):13-27.
[43]	GOLDSCHMIDT D, MANOONPONG P, DASGUPTA S. A neurocomputational model of goal-directed navigation in insect-inspired artificial agents[J]. Frontiers in Neurorobotics, 2017, 11(20):1-17.
[44]	LAMPLE G, CHAPLOT D S. Playing FPS games with deep reinforcement learning[EB/OL]. (2018-01-29)[2019-07-09]. https://arxiv.org/abs/1609.05521v2.
[45]	MIROWSKI P, PASCANU R, VIOLA F, et al. Learning to navigate in complex environments[EB/OL]. (2017-01-13)[2019-07-09]. https://arxiv.org/abs/1611.03673v3.
[46]	ZHU Y, MOTTAGHI R, KOLVE E, et al. Target-driven visual navigation in indoor scenes using deep reinforcement learning[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE Press, 2017:3357-3364.
[47]	SAVINOV N, RAICHUK A, MARINIER R, et al. Episodic curiosity through reachability[EB/OL]. (2019-05-09)[2019-07-09]. https://arxiv.org/abs/1810.02274v5.
[48]	FINN C, RAJESWARAN A, KAKADE S, et al. Online meta-learning[EB/OL]. (2019-07-03)[2019-07-09]. https://arxiv.org/abs/1902.08438v4.
[49]	LOQUERCIO A, MAQUEDA A I, BLANCO C R D, et al. Dronet:Learning to fly by driving[J]. IEEE Robotics & Automation Letters, 2018, 3(2):1088-1095.
[50]	TOBIN J, FONG R, RAY A, et al. Domain randomization for transferring deep neural networks from simulation to the real world[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ:IEEE Press, 2017.
[51]	MIROWSKI P, GRIMES M K, MALINOWSKI M, et al. Learning to Navigate in Cities Without a Map[EB/OL]. (2019-01-10)[2019-07-09]. https://arxiv.org/abs/1804.00168v3.
[52]	MADL T, FRANKLIN S, CHEN K, et al. A computational cognitive framework of spatial memory in brains and robots[J]. Cognitive Systems Research, 2018, 47:147-172.
[53]	ARONOV D, NEVERS R, TANK D W. Mapping of a non-spatial dimension by the hippocampal-entorhinal circuit[J]. Nature, 2017, 543(7647):719.
[54]	QUIROGA R Q. Concept cells:The building blocks of declarative memory functions[J]. Nature Reviews Neuroscience, 2012, 13(8):587-597.
[55]	BICANSKI A, BURGESS N. A computational model of visual recognition memory via grid cells[J]. Current Biology, 2019, 29(3):979-990.
[56]	TANG H, YAN R, TAN K C. Cognitive navigation by neuro-inspired localization, mapping, and episodic memory[J]. IEEE Transactions on Cognitive and Developmental Systems, 2018, 10(3):751-761.
[57]	FLEISCHER J G, EDELMAN G M. Brain-based devices[J]. IEEE Robotics & Automation Magazine, 2009, 16(3):33-41.
[58]	SABO C, CHISHOLM R, PETTERSON A, et al. A lightweight, inexpensive robotic system for insect vision[J]. Arthropod Structure & Development, 2017, 46(5):689-702.
[59]	HWU T, ISBELL J, OROS N, et al. A self-driving robot using deep convolutional neural networks on neuromorphic hardware[C]//2017 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE Press, 2017:635-641.
[60]	KREISER R, PIENROJ P, RENNER A, et al. Pose estimation and map formation with spiking neural networks:towards neuromorphic SLAM[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE Press, 2018:2159-2166.
[61]	PALOSSI D, CONTI F, BENINI L. An open source and open hardware deep learning-powered visual navigation engine for autonomous nano-UAVs[EB/OL]. (2019-05-10)[2019-07-09]. https://arxiv.org/abs/1905.04166.
[62]	PEI J, DENG L, SONG S, et al. Towards artificial general intelligence with hybrid Tianjic chip architecture[J]. Nature, 2019, 572(7767):106.
[63]	JIMENEZ R C, SOUSA R D, JOHNSON J H, et al. A model for foraging ants, controlled by spiking neural networks and double pheromones[EB/OL]. (2015-09-18)[2019-07-09]. https://arxiv.org/abs/1507.08467v3.
[64]	BONNET F, MILLS R, SZOPEK M, et al. Robots mediating interactions between animals for interspecies collective behaviors[J]. Science, 2019, 4(28):eaau7897.
[65]	DUVELLE É, JEFFERY K J. Social spaces:Place cells represent the locations of others[J]. Current Biology, 2018, 28(6):271-273.
[66]	GEVA-SAGIV M, ROMANI S, LAS L, et al. Hippocampal global remapping for different sensory modalities in flying bats[J]. Nature Neuroscience, 2016, 19(7):952.
[67]	WOHLGEMUTH M W, CHAO I, MOSS C F. 3D Hippocampal place field dynamics in free-flying echolocating bats[J]. Frontiers in Cellular Neuroscience, 2018, 12(270):1-16.
[68]	NGUYEN T T, NGUYEN N D, NAHAVANDI S. Deep reinforcement learning for multi-agent systems:A review of challenges, solutions and applications[EB/OL]. (2019-02-06)[2019-07-09]. https://arxiv.org/abs/1812.11794v2.
[69]	VLADIMIR G I, DARRYN J R. Cognitive supervisor for an autonomous swarm of robots[J]. Intelligent Control and Automation, 2017, 8(01):44-65.
[70]	熊智, 刘建业. 智能自主无人机多源信息融合导航理论与类脑导航技术发展建议[C]//科技2035-导航新技术与学科发展论坛, 2019. XIONG Z, LIU J Y. Multi-source information fusion navigation theory of intelligent autonomous UAV and development suggestions of brain-like navigation technology[C]//Science and Technology 2035-Forum on New Navigation Technologies, 2019(in Chinese).
[71]	张佳龙, 闫建国, 张普. 基于反步推演法的多机编队队形重构控制研究[J]. 航空学报, 2019, 40(11):323177. ZHANG J L, YAN J G, ZHANG P. Study on multi-UAV formation forming control based on backing-stepping method[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(11):323177(in Chinese).
[72]	MILFORD M, WYETH G. Mapping a suburb with a single camera using a biologically inspired SLAM system[J]. IEEE Transactions on Robotics, 2008, 24(5):1038-1053.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

由感知到动作决策一体化的类脑导航技术研究现状与未来发展

Brain-inspired navigation technology integrating perception and action decision: A review and outlook

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 72

相关文章 15

编辑推荐

Metrics

本文评价

[1]	惠俊鹏, 汪韧, 俞启东. 基于强化学习的再入飞行器“新质”走廊在线生成技术[J]. 航空学报, 2022, 43(9): 325960-325960.
[2]	王皓, 陈根良. 机器人型装备在航空装配中的应用现状与研究展望[J]. 航空学报, 2022, 43(5): 626128-626128.
[3]	胡庆雷, 邵小东, 杨昊旸, 段超. 航天器多约束姿态规划与控制:进展与展望[J]. 航空学报, 2022, 43(10): 527351-527351.
[4]	蔡国飙, 张百一, 贺碧蛟, 翁惠焱, 刘立辉. 真空羽流智能化计算[J]. 航空学报, 2022, 43(10): 527352-527352.
[5]	孙智孝, 杨晟琦, 朴海音, 白成超, 葛俊. 未来智能空战发展综述[J]. 航空学报, 2021, 42(8): 525799-525799.
[6]	黄旭星, 李爽, 杨彬, 孙盼, 刘学文, 刘新彦. 人工智能在航天器制导与控制中的应用综述[J]. 航空学报, 2021, 42(4): 524201-524201.
[7]	张伟伟, 寇家庆, 刘溢浪. 智能赋能流体力学展望[J]. 航空学报, 2021, 42(4): 524689-524689.
[8]	丁国如, 孙佳琛, 王海超, 焦雨涛. 复杂电磁环境下频谱智能管控技术探讨[J]. 航空学报, 2021, 42(4): 524750-524750.
[9]	李霓, 布树辉, 尚柏林, 李永波, 汤志荔, 张伟伟. 飞行器智能设计愿景与关键问题[J]. 航空学报, 2021, 42(4): 524752-524752.
[10]	陈志杰, 汤锦辉, 王冲, 程季锃, 曹珊, 邵欣. 人工智能赋能空域系统,提升空域分层治理能力[J]. 航空学报, 2021, 42(4): 525018-525018.
[11]	祝学军, 赵长见, 梁卓, 谭清科. OODA智能赋能技术发展思考[J]. 航空学报, 2021, 42(4): 524332-524332.
[12]	袁利, 王淑一. 航天器控制系统智能健康管理技术发展综述[J]. 航空学报, 2021, 42(4): 525044-525044.
[13]	卢新来, 杜子亮, 许赟. 航空人工智能概念与应用发展综述[J]. 航空学报, 2021, 42(4): 525150-525150.
[14]	董一群, 艾剑良. 自主空战技术中的机动决策:进展与展望[J]. 航空学报, 2020, 41(S2): 724264-724264.
[15]	隋少春, 许艾明, 黎小华, 刘顺涛, 黄伟. 面向航空智能制造的DT与AI融合应用[J]. 航空学报, 2020, 41(7): 624173-624173.