A Bioinspired Neural Model Based Extended Kalman Filter for Robot SLAM

Table 3

The root mean square error of the SLAM task in the second experiment.

The algorithms for the SLAM task	The root mean square error
			Angle/rad
The S-EKF based method	0.4064	0.3922	0.0921
The F-EKF based method	0.3083	0.3316	0.0496
The B-EKF based method	0.1132	0.0918	0.0204