基于多尺度空間表征的生物啟發(fā)目標(biāo)指引導(dǎo)航模型

李偉龍; 吳德偉; 盧虎; 杜佳; 周陽(yáng)

doi:10.11999/JEIT160892

基于多尺度空間表征的生物啟發(fā)目標(biāo)指引導(dǎo)航模型

doi: 10.11999/JEIT160892

1.
(空軍工程大學(xué)信息與導(dǎo)航學(xué)院西安 710077) ②(西安通信學(xué)院西安 710106)

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61273048, 61473308, 61603409)

計(jì)量
- 文章訪問(wèn)數(shù): 1256
- HTML全文瀏覽量: 148
- PDF下載量: 231
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-09-02
- 修回日期: 2017-01-22
- 刊出日期: 2017-06-19

Bio-inspired Goal-directed Navigation Model Based on Multi-scale Spatial Representation

1.
(Information and Navigation College, Air Force Engineering University, Xi'an 710077, China)

Funds:

The National Natural Science Foundation of China (61273048, 61473308, 61603409)

摘要

摘要: 為實(shí)現(xiàn)運(yùn)行體空間認(rèn)知和自主導(dǎo)航，借鑒生物導(dǎo)航機(jī)理，該文提出基于多尺度空間表征的生物啟發(fā)目標(biāo)指引導(dǎo)航模型。首先構(gòu)建不同尺度位置細(xì)胞圖編碼空間環(huán)境，采用高斯模型模擬位置細(xì)胞放電率，并將其作為Q學(xué)習(xí)的狀態(tài)輸入，然后采用模擬退火方法完成行為選擇，通過(guò)多次探索學(xué)習(xí)使運(yùn)行體能夠正確規(guī)劃出一條從起始點(diǎn)到目標(biāo)點(diǎn)的最短路徑。仿真結(jié)果表明，該方法用于目標(biāo)指引導(dǎo)航是可行的，相對(duì)于單尺度位置細(xì)胞空間認(rèn)知模型，該方法不但符合多尺度空間表征的生物學(xué)依據(jù)，而且學(xué)習(xí)速度更快。在存在障礙物的環(huán)境中，能夠順利完成目標(biāo)指引導(dǎo)航任務(wù)，并且當(dāng)障礙物發(fā)生變化時(shí)具有較好的適應(yīng)性。
- 類(lèi)腦導(dǎo)航 /
- 空間認(rèn)知 /
- 位置細(xì)胞 /
- 多尺度表征 /
- Q學(xué)習(xí)
Abstract: In order to achieve spatial cognition and autonomous navigation, enlightened by the mechanism for biological navigation, a bio-inspired goal-directed navigation model based on a multi-scale spatial representation is proposed. First, a place cell map with different scales is constructed for encoding the space environment. Second, the firing rate of place cells in each layer is calculated by the Gaussian function as the input of Q-learning process. Third, the annealing strategy is used to choose a reasonable action. After training and learning, the robot can succeed to plan an optimal route from the starting point to the goal point. Simulation results show that, the proposed method is feasible for goal-directed navigation. Compared with the spatial cognitive model of single scale place cells, the proposed method not only meets the multi-scale spatial representation nature of place cells in hippocampus, but also has a faster learning speed. Additionally, it has good performance on completing the goal- oriented navigation in the presence of obstacles, and can adapt to the change of obstacles in the environment.
- Brain-based navigation /
- Spatial cognition /
- Place cells /
- Multi-scale representation /
- Q-learning

HTML全文

參考文獻(xiàn)(27)

ALEJANDRA B, GONZALO T, MARTIN L, et al. Learning spatial localization: From rat studies to computational models of the hippocampus[J]. Spatial Cognition and Computation: An Interdisciplinary Journal, 2015, 15: 27-59. doi: 10.1080/ 13875868.2014.961602.

FABIAN C and BURGESS N. The Cognitive architecture of spatial navigation: Hippocampal and striatal contributions[J]. Neuron, 2015, 88(1): 64-77. doi: 10.1016/j.neuron.2015.09. 021.

RAYMOND P K and EDMUND T R. A computational theory of hippocampal function, and tests of the theory: New developments[J]. Neuroscience and Biobehavioral Reviews, 2015, 48(1): 92-147. doi: 10.1016/j.neubiorev.2014.11.009.

TOLMAN E C. Cognitive maps in rats and men[J]. Psychological Review, 1948, 55(1): 189-208. doi: 10.1037/ h0061626.

OKEEFE J and DOSLROVSKV J. The hippocampus as a spatial map[J]. Brain Research, 1971, 34(1): 171-175. doi: 10.1016/0006-8993(71)90358-1.

OKEEFE J and BURGESS N. Geometric determinants of the place fields of hippocampal neurons[J]. Nature, 1996, 381(6581): 425-428. doi: 10.1038/381425a0.

BJERKNES T, LANGSTON R, KRUGE I, et al. Coherence among head direction cells before eye opening in rat pups[J]. Current Biology, 2015, 25(1): 103-108. doi: 10.1016/j.cub. 2014.11.009.

GIOCOMO L M, STENSOLA T, BONNEVIE T, et al. Topography of head direction cells in medial entorhinal cortex[J]. Current Biology, 2014, 24(3): 252-262. doi: 10.1016 /j.cub.2013.12.002.

HAFTING T, FYHN M, MOLDEN S, et al. Microstructure of a spatial map in the entorhinal cortex[J]. Nature, 2005, 436(7052): 801-806. doi: 10.1038/nature03721.

DANIEL B, CASWELL B, DANIEL M, et al. Using grid cells for navigation[J]. Neuron, 2015, 87(3): 507-520. doi: 10.1016/ j.neuron.2015.07.006.

SOLSTAD T, BOCCARA C N, KROPFF E, et al. Representation of geometric borders in the entorhinal cortex[J]. Science, 2009, 322(5909): 1865-1868. doi: 10.1126/ science.1166466.

EMILIO K, JAMES E C, MOSER M B, et al. Speed cells in the medial entorhinal cortex[J]. Nature, 2015, 523(7561): 419-424. doi: 10.1038/nature14622.

TAVARES R M, MENDELSOHN A, GROSSMAN Y, et al. A map for social navigation in the human brain[J]. Neuron, 2015, 87(1): 231-243. doi: 10.1016/j.neuron.2015.06.011.

IOANNIS K, KONSTANTINOS C, ANTONIOS G, et al. Robot navigation via spatial and temporal coherent semantic maps[J]. Engineering Applications of Artificial Intelligence, 2016, 48(1): 173-187. doi: 10.1016/j.engappai.2015.11.004.

曾毅, 劉成林, 譚鐵牛. 類(lèi)腦智能研究的回顧與展望[J]. 計(jì)算機(jī)學(xué)報(bào), 2016, 39(1): 212-222. doi: 10.11897/SP.J.1016.2016. 00212.

ZENG Yi, LIU Chenglin, and TAN Tieniu. Retrospect and outlook of brain-inspired intelligence research[J]. Chinese Journal of Computer, 2016, 39(1): 212-222. doi: 10.11897/SP. J.1016.2016.00212.

李偉龍, 吳德偉, 周陽(yáng), 等. 基于生物位置細(xì)胞放電機(jī)理的空間位置表征方法[J]. 電子與信息學(xué)報(bào), 2016, 38(8): 2040-2046. doi: 10.11999/JEIT151331.

LI Weilong, WU Dewei, Zhou Yang, et al. A method of spatial place representation based on biological place cells firing[J]. Journal of Electronics Information Technology, 2016, 38(8): 2040-2046. doi: 10.11999/JEIT151331.

SPIERS H J and BARRY C. Neural systems supporting navigation[J]. Current Opinion in Behavioral Sciences, 2015, 1(1): 47-55. doi: 10.1016/j.cobeha.2014.08.005.

ERDEM U M, MILFORD M J, and HASSELMO M E. A hierarchical model of goal directed navigation selects trajectories in a visual environment[J]. Neurobiology of Learning and Memory, 2015, 117(1): 109-121. doi: 10.1016/ j.nlm.2014.07.003.

GEVA-SAGIV M, LAS L, YOVEL 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. doi: 10.1038/nrn3888.

KEINATH A T, WANG M E, WANN E G, et al. Precise spatial coding is preserved along the longitudinal hippocampal axis[J]. Hippocampus, 2014, 24(12): 1533-1548. doi: 10.1002/hipo.22333.

LONG L L, BUNCE J G, and CHROBAK J J. Theta variation and spatiotemporal scaling along the septotemporal axis of the hippocampus[J]. Frontiers in Systems Neuroscience, 2015, 37(9): 1-14. doi: 10.3389/fnsys.2015. 00037.

ROBITSEK R J, WHITE J A, and EICHENBAUM H. Place cell activation predicts subsequent memory[J]. Behavioural Brain Research, 2013, 254(4): 65-72. doi: 10.1016/j.bbr.2012. 12.034.

KONAR A, CHAKRABORTY I G, SINGH S J, et al. A deterministic improved q-learning for path planning of a mobile robot[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 43(5): 1141-1153. doi: 10.1109/ TSMCA.2012.2227719.

CUPERLIER N, QUOY M, and GAUSSIER P. Neurobiologically inspired mobile robot navigation and planning[J]. Frontiers in Neurorobotics, 2007, 1(3): 1-15. doi: 10.3389/neuro.12.003.2007.

GIOVANNI P, MATTHIJS A A, MEER V D, et al. Internally generated sequences in learning and executing goal-directed behavior[J]. Trends in Cognitive Sciences, 2014, 18(12): 647-657. doi: 10.1016/j.tics.2014.06.011.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)