Neural Behavior Chain Learning of Mobile Robot Actions

Table 4

Selected set of mobile robot positions from experiments and predicted values from neural network learning process.

𝜌	15	25	35	45	55	65
𝜃	160	140	120	100	80	60
Real values of coefficients 𝑘𝑖
𝑘1	6	4	3	1	−1	−3
𝑘2	0	1	3	5	6	8
𝑘3	0	1	0	0	0	0
𝑘4	0	1	0	0	0	0
Real values of (𝑑, 𝛼)
𝑑	0	12	18	30	36	48
𝛼	150	135	120	100	80	60
Values of coefficients 𝑘𝑖 gained from neural network learning process
𝑘1	6.66	5.09	3.05	1.00	−0.68	−2.70
𝑘2	−0.06	2.10	3.34	4.68	4.92	5.71
𝑘3	−0.14	0.09	0.02	0.04	−0.22	−0.32
𝑘4	0.00	−0.34	−0.07	0.48	1.55	2.14
𝑑NN and 𝛼NN gained from neural network learning process
𝑑NN	0.37	10.57	19.65	30.99	38.83	47.09
𝛼NN	149.95	129.83	119.99	100.04	79.46	59.12