定位细胞认知机理启发的机器人导航研究综述

doi:10.3901/JME.2019.23.001

机械工程学报 ›› 2019, Vol. 55 ›› Issue (23): 1-12.doi: 10.3901/JME.2019.23.001

• 机构学及机器人 • 下一篇

扫码分享

定位细胞认知机理启发的机器人导航研究综述

丛明^1,2, 邹强¹, 刘冬^1,2, 杜宇³

1. 大连理工大学机械工程学院大连 116024;
2. 大连理工江苏研究院有限公司常州 213164;
3. 大连大华中天科技有限公司大连 116023

收稿日期:2019-01-31 修回日期:2019-08-19 出版日期:2019-12-05 发布日期:2020-02-18
通讯作者: 刘冬(通信作者),男,1985年出生,博士,副教授,硕士研究生导师。主要研究方向为智能机器人与系统,智能控制,机器人机构学。E-mail:liud@dlut.edu.cn
作者简介:丛明,男,1963年出生,博士,教授,博士研究生导师。主要研究方向为机构与机器人学,智能控制,工业机器人技术与应用,仿生机器人及控制。E-mail:congm@dlut.edu.cn;邹强,男,1991年出生,博士研究生。主要研究方向为智能机器人与系统,移动机器人智能控制。E-mail:zq0819@mail.dlut.edu.cn;杜宇,女,1981年出生,博士。主要研究方向为机器人认知控制,机器人机构学,人机交互等。E-mail:dutduyu@foxmail.com
基金资助:
国家自然科学基金（61503057）、辽宁省自然科学基金联合基金（20180520017）和常州市科技支撑计划（CE20185009）资助项目。

Review of Robot Navigation Inspired by the Localization Cells' Cognitive Mechanism

CONG Ming^1,2, ZOU Qiang¹, LIU Dong^1,2, DU Yu³

1. School of Mechanical Engineering, Dalian University of Technology, Dalian 116024;
2. Dalian University of Technology Jiangsu Research Institute Co., Ltd., Changzhou 213164;
3. Dalian Dahuazhongtian Technology Co., Ltd., Dalian 116023

Received:2019-01-31 Revised:2019-08-19 Online:2019-12-05 Published:2020-02-18

摘要/Abstract

摘要： 快速准确完成目标导航是哺乳动物赖以生存的一个重要能力，海马体和内嗅皮层是实现其空间认知及导航能力的主要脑区，网格细胞和位置细胞等多细胞的协同作用可以为大脑提供一套综合定位系统，实现了哺乳动物更高水平的认知功能。综述了哺乳动物海马相关定位细胞在机器人自主导航领域的最新研究进展，重点介绍了定位细胞认知机理启发的机器人环境建模、地图构建及行为规划与控制等领域的研究成果。最后对定位细胞启发机器人应用存在的问题进行分析和讨论，并对未来发展方向做了展望。

关键词: 定位细胞, 环境建模, 地图构建, 行为规划

Abstract: Fast and accurate target navigation is an important ability for the mammals, and the hippocampus and entorhinal cortex are the main regions of brain to realize the spatial cognition and navigation ability. The coorperation of grid cells, place cells and other related cells provides the brain an integrated positioning system, which realizes that mammals can perform higher-level cognitive functions. The latest research in the field of robot autonomous navigation with mammals' localization cells were reviewed, especially focus on the localization cells' cognitive mechanism inspired robotic environment modelling, map building and behavior planning and controlling. At last, the deficiencies of current research and the future trend of autonomous robot navigation are analyzed and discussed.

Key words: localization cells, environment modelling, map building, behavior planning

中图分类号:

TP242

丛明, 邹强, 刘冬, 杜宇. 定位细胞认知机理启发的机器人导航研究综述[J]. 机械工程学报, 2019, 55(23): 1-12.

CONG Ming, ZOU Qiang, LIU Dong, DU Yu. Review of Robot Navigation Inspired by the Localization Cells' Cognitive Mechanism[J]. Journal of Mechanical Engineering, 2019, 55(23): 1-12.

参考文献

[1] MATHIS R, YULIA S, GREGOR S. A robotic architecture for action selection and behavioral organization inspired by human cognition[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, October 7-12, 2012, Vilamoura, Portugal. New York:IEEE, 2012:2457-2464.
[2] MORRIS R G M, GARRUD P, RAWLINS J N P, et al. Place navigation impaired in rats with hippocampal lesions[J]. Nature, 1982, 297(5868):681-683.
[3] TOURETZKY D S. The role of the hippocampus in solving the Morris water maze[J]. Neural Computation, 2014, 10(1):73-111.
[4] STEELE R J, MORRIS R G M. Delay-dependent impairment of a matching-to-place task with chronic and intrahippocampal infusion of the NMDA-antagonist D-AP5[J]. Hippocampus, 1999, 9(2):118-136.
[5] PEARCE J M, ROBERTS A D L, GOOD M. Hippocampal lesions disrupt navigation based on cognitive maps but not heading vectors[J]. Nature, 1998, 396(6706):75-77.
[6] STEFFEMACH H,WITTER M,MOSER M,et al. Spatial memory in the rat requires the dorsolateral band of the entorhinal cortex[J]. Neuron, 2005, 45(2):301-313.
[7] 于乃功,李倜,方略. 海马空间认知机理及其在仿生机器人导航中的应用[J]. 生物工程前沿, 2015, 4(1):1-14. YU Naigong, LI Ti, FANG Lue. The hippocampus spatial cognitive mechanism and its application in the biomimetic robot navigation[J]. Biotechnology Frontier, 2015, 4(1):1-14.
[8] 于平,徐晖,尹文娟,等. 网格细胞在空间记忆中的作用[J]. 心理科学进展, 2009, 17(6):1228-1233. YU Ping, XU Hui, YIN Wenjuan, et al. The roles of grid cells in spatial memory[J]. Advances in Psychological Science, 2009, 17(6):1228-1233.
[9] O'KEEFE J, DOSTROVSKY J. The hippocampus as a spatial map:Preliminary evidence from unit activity in the freely-moving rat[J]. Brain Research, 1971, 34(1):171-175.
[10] WAGATSUMA H, YAMAGUCHI Y. Neural dynamics of the cognitive map in the hippocampus[J]. Cognitive Neurodynamics, 2007, 1(2):119-141.
[11] O'KEEFE J, NADEL L. The hippocampus as a cognitive map[M]. New York:Clarendon Press, 1978.
[12] 李伟龙,吴德伟,周阳,等. 基于生物位置细胞放电机理的空间位置表征方法[J]. 电子与信息学报, 2016, 38(8):2040-2046. LI Weilong, WU Dewei, ZHOU Yang, et al. A method of spatial place representation based on biological place cells firing[J]. Journal of Electronics and Information Technology, 2016, 38(8):2040-2046.
[13] TAUBE J S, MULLER R U, JR R J. Head-direction cells recorded from the postsubiculum in freely moving rats. II. Effects of environmental manipulations[J]. Journal of Neuroscience, 1990, 10(2):436-447.
[14] O'KEEFE J,BURGESS N. Geometric determinants of the place fields of hippocampal neurons[J]. Nature, 1996, 381(6581):425-428.
[15] HAFTING T, FYHN M, MOLDEN S, et al. Microstructure of a spatial map in the entorhinal cortex[J]. Nature, 2005, 436(7052):801-806.
[16] BUZSAKI G, MOSER E. Memory, navigation and theta rhythm in the hippocampal-entorhinal system[J]. Nature Neuroscience, 2013, 16(2):130-138.
[17] WYETH G, MILFORD M. Spatial cognition for robots-robot navigation from biological inspiration[J]. IEEE Robotics and Automation Magazine, 2009, 16(3):24-32.
[18] Nobel Media AB. The Nobel prize in physiology or medicine 2014[EB/OL].[2019.04.02]. https://www.nobelprize.org/prizes/medicine/2014/summary/.
[19] 左艳芳,罗非,崔彩莲. 海马位置细胞对空间信息的处理[J]. 生理科学进展, 2006, 37(1):6-10. ZUO Yanfang, LUO Fei, CUI Cailian. Processing of spatial information by hippocampal place cells[J]. Process in Physiological Sciences, 2006, 37(1):6-10.
[20] PREUCIL L, STEPAN P, KULICH M, et al. Towards environment modeling by autonomous mobile systems[C]//IFIP/IEEE International Conference on Information Technology for Balanced Automation Systems in Manufacturing and Services:Knowledge and Technology Integration in Production and Services:Balancing Knowledge in Product and Service Life Cycle, September 25-27, 2002, Deventer, Netherlands. New York:IEEE, 2002:509-516.
[21] CHOSET H, NAGATANI K. Topological simultaneous localization and mapping (SLAM):Toward exact localization without explicit localization[J]. IEEE Transactions on Robotics & Automation, 2002, 17(2):125-137.
[22] YAMANAKA S. Mobile robot navigation using hybrid simplified map with relationships between places and grid maps[J]. IFAC Proceedings Volumes, 2012, 45(22):616-621.
[23] ARLEO A, SMERALDI F, GERSTNER W. Cognitive navigation based on nonuniform Gabor space sampling, unsupervised growing networks, and reinforcement learning.[J]. IEEE Transactions on Neural Networks, 2004, 15(3):639-652.
[24] FRANZIUS M, SPRELELER H, WISKOTT L. Slowness and sparseness lead to place, head-direction, and spatial-view cells[J]. Plos Computational Biology, 2007, 3(8):1605-1622.
[25] OSHIRO N, KURATA K, YAMAMOTO T. A self-organizing model of place cells with grid-structured receptive fields[J]. Artificial Life & Robotics, 2007, 11(1):48-51.
[26] CHAVARRIAGA R, STRSSLIN T, SHEYNIKHOVICH D, et al. A computational model of parallel navigation systems in rodents[J]. Neuroinformatics, 2005, 3(3):223-241.
[27] GAUSSIER P, REVEL A, BANQUET J P, et al. From view cells and place cells to cognitive map learning:Processing stages of the hippocampal system[J]. Biological Cybernetics, 2002, 86(1):15-28.
[28] REDISH A D, TOURETZKY D S. Navigating with landmarks:Computing goal locations from places codes[J]. Symbolic Visual Learning, 1997, 1:325-351.
[29] REDISH A D, TOURETZKY D S. Cognitive maps beyond the hippocampus[J]. Hippocampus, 2015, 7(1):15-35.
[30] BARRERA A, WEITZENFELD A. Bio-inspired model of robot adaptive learning and mapping[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, October 9-15, 2006, Beijing, China. New York:IEEE, 2006:4750-4755.
[31] BARRERA A, WEITZENFELD A. Biologically-inspired robot spatial cognition based on rat neurophysiological studies[J]. Autonomous Robots, 2008, 25(1-2):147-169.
[32] HEBB D O. The organization of behavior a neuropsychological theory[M]. New York:Wiley, 1949.
[33] SUTTON R S, BARTO A G. Reinforcement learning:an introduction[J]. IEEE Transactions on Neural Networks, 1998, 9(5):1054-1054.
[34] 李伟龙,吴德伟,周阳,等. 基于生物位置细胞放电机理的空间位置表征方法[J]. 电子与信息学报, 2016, 38(8):2040-2046 LI Weilong, WU Dewei, ZHOU Yang, et al. A method of spatial place representation based on biological place cells firing[J]. Journal of Electronics and Information Technology, 2016, 38(8):2040-2046.
[35] 刘冬,丛明,高森,等. 融合神经元激励机制的机器人情景学习与行为控制[J]. 机器人, 2014, 36(5):576-583. LIU Dong, CONG Ming, GAO Sen, et al. Robotic episodic learning and behavior control integrated with neuron stimulation mechanism[J]. Robot, 2014, 36(5):576-583.
[36] LIU D, CONG M, DU Y. Episodic memory-based robotic planning under uncertainty[J]. IEEE Transactions on Industrial Electronics, 2016, 64(2):1762-1772.
[37] MCNAUGHTON B L, BATTAGLIA F P, JENSEN O, et al. Path integration and the neural basis of the ‘cognitive map’[J]. Nature Reviews Neuroscience, 2006, 7(8):663-678.
[38] NAVRATILOVA Z, GIOCOMO L M, FELLOUW J M, et al. Phase precession and variable spatial scaling in a periodic attractor map model of medial entorhinal grid cells with realistic after-spike dynamics[J]. Hippocampus, 2012, 22(4):772-789.
[39] MILFORD M J, WYETH G F, PRASSER D. RatSLAM:a hippocampal model for simultaneous localization and mapping[C]//IEEE International Conference on Robotics and Automation, April 26-May 1, 2004, New Orleans, USA. New York:IEEE, 2004:403-408.
[40] GUANELLA A, VERSCHURE P F. A model of grid cells based on a path integration mechanism[C]//International Conference on Artificial Neural Networks, September 10-14, 2006, Athens, Greece. Berlin:Springer, 2006:740-749.
[41] MILFORD M, SCHULZ R, PRASSER D, et al. Learning spatial concepts from RatSLAM representations[J]. Robotics and Autonomous Systems,2007,55(5):403-410.
[42] WYETH G, MILFORD M. Spatial cognition for robots:Robot navigation from biological inspiration[J]. IEEE Robotics & Automation Magazine, 2009, 16(3):24-32.
[43] MILFORD M J, WILES J, WYETH G F. Solving navigational uncertainty using grid cells on robots[J]. PLoS Computational Biology, 2010, 6(11):1-14.
[44] TEJERA G, LLOFRIU M, BARRERA A, et al. A spatial cognition model integrating grid cells and place cells[C]//International Joint Conference on Neural Networks, July 12-17, 2015, Killarney, Ireland. New York:IEEE, 2015:1-8.
[45] GONZALO T, MARTIN L, ALEJANDRA B, et al. Bio-inspired robotics:A spatial cognition model integrating place cells, grid cells and head direction cells[J]. Journal of Intelligent & Robotic Systems, 2018, 91(1):85-99.
[46] 陈孟元. 鼠类脑细胞导航机理的移动机器人仿生SLAM综述[J]. 智能系统学报, 2018, 13(1):107-117. CHEN Mengyuan. Overview of mobile robot bionic slam based on navigation mechanism of mouse brain cells[J]. CAAI Transactions on Intelligent Systems, 2018, 13(1):107-117.
[47] TOLMAN, EDWARD C. Cognitive maps in rats and men[J]. Psychological Review, 1948, 55(4):189-208.
[48] CUPERLIER N, QUOY M, GAUSSIER P. Neurobiologically inspired mobile robot navigation and planning[J]. Front. Neurorobotics, 2007, 1:1-15.
[49] 朱青,王如彬. 基于智力探索的认知地图建模[C]//全国神经动力学学术会议, 3月28-31日, 2012,上海, 中国. 北京:中国力学学会, 2012:55-70. ZHU Qing, WANG Rubin. A model of cognitive map based on mental exploration[C]//National Conference on Neurodynamics, March 28-31, 2012, Shanghai, China. Beijing:The Chinese Society of Theoretical and Applied Mechanics, 2012:55-70.
[50] 周阳,吴德伟,邰能建,等. UCAV地形空间环境感知中位置细胞构建方法[J]. 空军工程大学学报, 2014, 15(1):62-66. ZHOU Yang, WU Dewei, TAI Nengjian, et al. A method of constructing place cells in UCAV terrain space environment perception[J]. Journal of Air Force Engineering University, 2014, 15(1):62-66.
[51] HAFNER V V. Robots as tools for modelling navigation skills-a neural cognitive map approach[J]. Springer Tracts in Advanced Robotics, 2012, 38:315-324.
[52] ERDEM U M, HASSELMO M E. A biologically inspired hierarchical goal directed navigation model[J]. Journal of Physiology Paris, 2014, 108(1):28-37.
[53] JAUFFRET A, CUPERLIER N, GAUSSIER P. Multimodal integration of visual place cells and grid cells for navigation tasks of a real robot[C]//International Conference on Simulation of Adaptive Behavior, August 27-30, 2012, Odense, Denmark. Berlin:Springer, 2012:136-145.
[54] ARLEO A. Spatial learning and navigation in neuro-mimetic systems:Modeling the rat hippocampus[D]. Milan:University of Milano, 2000.
[55] STROSSLIN T, SHEYNIKHOVICH D, CHAVARRIAGA R, et al. Robust self-localisation and navigation based on hippocampal place cells[J]. Neural Networks, 2005, 18(9):1125-1140.
[56] YUAN M, TIAN B, SHIM V A, et al. An entorhinal-hippocampal model for simultaneous cognitive map building[C]//Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25-29, 2015, Austin, USA. Palo Alto:AAAI Press, 2015:586-592.
[57] JAUFFRET A, CUPERLIER N, GAUSSIER P. From grid cells and visual place cells to multimodal place cell:A new robotic architecture[J]. Frontiers in Neurorobotics, 2015, 9(1):1-23.
[58] 于乃功,苑云鹤,李倜,等. 一种基于海马认知机理的仿生机器人认知地图构建方法[J]. 自动化学报, 2018, 44(1):52-73. YU Naigong, FAN Yunhe, LI Ti, et al. A cognitive map building algorithm by means of cognitive mechanism of hippocampus[J]. Acta Automatica Sinica, 2018, 44(1):52-73.
[59] GIOVANNANGELI C, GAUSSIER P, DESILLES G. Robust mapless outdoor vision-based navigation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, October 9-15, 2006, Beijing, China. New York:IEEE, 2006:3293-3300.
[60] GIOVANNANGELI C, GAUSSIER P. Autonomous vision-based navigation:Goal-oriented action planning by transient states prediction, cognitive map building, and sensory-motor learning[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, September 22-26, 2008, Nice, France. New York:IEEE, 2008:676-683.
[61] HIREL J, GAUSSIER P, QUOY M, et al. The hippocampo-cortical loop:Spatio-temporal learning and goal-oriented planning in navigation[J]. Neural Networks, 2013, 43(7):8-21.
[62] WEILLER D, LAER L, ENGEL A K, et al. Unsupervised learning of reflexive and action-based affordances to model adaptive navigational behavior[J]. Frontiers in Neurorobotics, 2010, 4(2):1-15.
[63] YAN W J, WEBER C, WERMTER S. Learning indoor robot navigation using visual and sensorimotor map information[J]. Frontiers in Neurorobotics, 2013, 7(15):1-14.
[64] KRICHMAR J L, NITZ D A, GALLY J A, et al. Characterizing functional hippocampal pathways in a brain-based device as it solves a spatial memory task[J]. Proceedings of the National Academy of Sciences of the United States of America, 2005, 102(6):2111-2116.
[65] SAMU D, EROS P, UJFALUSSY B. Robust path integration in the entorhinal grid cell system with hippocampal feed-back[J]. Biological Cybernetics, 2009, 101(1):19-34.
[66] MILFORD M J, WYETH G F. Mapping a suburb with a single camera using a biologically inspired SLAM system[J]. IEEE Transactions on Robotics, 2008, 24(5):1038-1053.
[67] TIAN B, SHIM V A, YUAN M, et al. RGB-D based cognitive map building and navigation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, November 3-7, 2013, Tokyo, Japan. New York:IEEE, 2013:1562-1567.
[68] 邹强,丛明,刘冬,等. 基于生物认知的移动机器人路径规划方法[J]. 机器人, 2018, 40(6):894-902. ZOU Qiang, CONG Ming, LIU Dong, et al. Path planning of mobile robots based on biological cognition[J]. Robot, 2018, 40(6):894-902.
[69] MITTELSTAEDT M L, MITTELSTAEDT H. Homing by path integration in a mammal[J]. Naturwissenschaften, 1980, 67(11):566-567.
[70] OSHIRO N, KURATA K, YAMAMOTO T. A self-organizing model of place cells with grid-structured receptive fields[J]. Artificial Life and Robotics, 2007, 11(1):48-51.
[71] MILFORD M, WYETH G. Persistent navigation and mapping using a biologically inspired SLAM system[J]. International Journal of Robotics Research, 2009, 29(9):1131-1153.
[72] MILFORD M, WYETH G, PRASSER D. Efficient goal directed navigation using RatSLAM[C]//IEEE International Conference on Robotics and Automation, April 18-22, 2005, Barcelona, Spain. New York:IEEE, 2005:1097-1102.
[73] ROJAS-CASTRO D M, REVEL A, MENARD M. Robotic and document analysis cross-fertilization:Improving place cells based robot navigation[C]//International Conference on Control, Automation, Robotics and Vision, November 13-15, 2016, Phuket, Thailand. New York:IEEE, 2016:1-6.
[74] 李伟龙,吴德伟,卢虎,等. 基于多尺度空间表征的生物启发目标指引导航模型[J]. 电子与信息学报, 2017, 39(6):1363-1370. LI Weilong, WU Dewei, LU Hu, et al. Bio-inspired goal-directed navigation model based on multi-scale spatial representation[J]. Journal of Electronics & Information Technology, 2017, 39(6):1363-1370.
[75] NUXOLL A, LAIRD J E. A cognitive model of episodic memory integrated with a general cognitive architecture[C]//International Conference on Cognitive Modelling, July 30-August 1, 2004, Pittsburgh, USA. USA:CiteSeerx, 2004:220-225.
[76] ENDO Y. Anticipatory robot control for a partially observable environment using episodic memories[C]//IEEE International Conference on Robotics and Automation, May 19-23, 2008, Pasadena, USA. New York:IEEE, 2008:2852-2859.
[77] JOCKEL S, WESTHOFF D, ZHANG J. EPIROME-a novel framework to investigate high-level episodic robot memory[C]//IEEE International Conference on Robotics and Biomimetics, December 15-18, 2008, Sanya, China, New York:IEEE, 2008:1075-1080.
[78] KUBIE J L, FENTON A A. Linear look-ahead in conjunctive cells:An entorhinal mechanism for vector-based navigation[J]. Frontiers in Neural Circuits, 2012, 6(1):203-209.
[79] HOWARD L R, JAVADI A H, YU Y C, et al. The hippocampus and entorhinal cortex encode the path and euclidean distances to goal during navigation[J]. Current Biology, 2014, 24(12):1331-1340.
[80] BARRY C, BURGESS N. Neural mechanisms of self-location[J]. Current Biology, 2014, 24(8):330-339.
[81] ZENO P J. Using an FPGA to emulate grid cell spatial cognition in a mobile robot[C]//IEEE International Conference on Development and Learning and Epigenetic Robotics, September 19-22, 2016, Paris, France. New York:IEEE, 2016:7-8.
[82] ERDEM U M, HASSELMO M. A goal-directed spatial navigation model using forward trajectory planning based on grid cells[J]. European Journal of Neuroscience, 2012, 35(6):916-931.
[83] ERDEM U M, MILFORD M J, HASSELMO M E. A hierarchical model of goal directed navigation selects trajectories in a visual environment[J]. Neurobiology of Learning & Memory, 2015, 117:109-121.
[84] 邰能建,吴德伟,戚君宜. 多尺度网格细胞路径综合方法[J]. 北京航空航天大学学报, 2013, 39(6):756-760. TAI Nengjian, WU Dewei, QI Junyi. Method to realize path integration based on multi-scaled grid cells[J]. Journal of Beijing Univesrty of Aeronautics and Astronautics, 2013, 39(6):756-760.
[85] BANINO A, BARRY C, URIA B, et al. Vector-based navigation using grid-like representations in artificial agents[J]. Nature, 2018, 557(7705):429-433.
[86] TULVING E. Elements of episodic memory[M]. Oxford:Clarendon Press, 1983.
[87] BJERKNES T L, MOSER E I, MOSER M B. Representation of geometric borders in the developing rat[J]. Neuron, 2014, 82(1):71-78.

定位细胞认知机理启发的机器人导航研究综述

Review of Robot Navigation Inspired by the Localization Cells' Cognitive Mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价