Direct tuning of inertia sensors of a navigation system using the neural network approach

Figures & data

Figure 1. Reference frames for the 2D (a) and 3D (b) problems.

Figure 2. Orientation error (a) and 2D trail on a map (b) during a 150 s simulation.

Figure 3. Optimal correction of orientation (a) and positioning (b) during a 150 s simulation.

Figure 4. 2D trail on a map (a) and displacement components (b) when sensitivity errors are increased 10 times.

Figure 5. Identification on data containing 2% error in final positioning, orientation (a) and velocity correction (b).

Figure 6. Example of optimal reconstruction of acceleration (a) and 3D path (b).

Figure 7. Non-optimal velocities (a) and 3D path reconstruction during 60 s measurement (b).

Figure 8. Missed velocity (a) and 3D path reconstruction over a 300 s measurement (b).

Figure 9. Optimal velocity reconstruction (a) and 3D path on a 300 s measurement (b).

Table 1. The exact and estimated correction parameters presented in Figure 2–9.

Reference figures	nDIM	Tot time	Exact parameter	Estimated parameter max% error	Max% error in distance
2(a), 2(b), 3(a) and 3(b)	2	150	0.30	0.0%	0.0%
4(a) and (b)	2	150	3.00	0.0%	0.0%
5(a) and (b)	2	150	0.30	13.6%	57.9%
6(a) and (b)	3	60	0.20	6.3%	0.1%
7(a) and (b)	3	60	0.20	42.5%	29.7%
8(a) and (b)	3	300	0.20	More that 100%	50.4%
9(a) and (b)	3	300	0.20	2.75%	2.3%