基于位置细胞的空间表征及位置估计模型

Spatial Representation and Location Estimation Model Based on Place Cells

为开发具有生物启发式空间表征和自主定位能力的导航新方法,提出一种基于位置细胞的空间表征及位置估计模型.该模型通过径向基函数神经网络实现网格细胞到位置细胞的转换,生成自运动感知下的位置细胞.同时,通过环境感知和相似性度量生成视觉感知下的位置细胞.最后,采用信息加权的方式对前两种位置细胞进行融合,生成多信息感知下的位置细胞,以此表征已探索的空间.当运行体在已表征空间中运行时,基于重心估计原理对群体位置细胞放电活动进行处理,实现自主定位.仿真分析结果表明,所提模型能够实现已探索空间的内部表征,生成的位置细胞具有生物位置细胞的放电特性,且多信息感知下的空间表征在某一感知方式存在误差时仍表现出好的位置估计性能.

To develop a new navigation method with bio-inspired spatial representation and autonomous positioning ability,a model of spatial representation and location estimation based on place cells is presented in this paper.In the proposed model,the place cells of self-motion perception are generated through the transformation from grid cells to place cells based on radial basis function(RBF)neural network.Simultaneously,the place cells of visual perception are generated through environment perception and similar measure.Finally,the above two kinds of place cells are fused by information weighting,and the place cells of multi-information perception are generated to represent the explored space.When the vehicle runs in the represented space,it can realize autonomous positioning by processing the firing activity of population place cells based on gravity center estimation principle.Simulation results indicate the proposed model can represent the explored space,and the firing characteristic of the generated place cells is similar to that of biological place cells.Besides,when there is an error in one of the perception modes,the spatial representation of multi-information perception can also give the good location estimation performance.