Research on Global Path Planning of Robot Based on Ant Colony Algorithm and Gaussian Sampling

Table 13

Statistical Results of PSO, GA and S-IACO algorithms in Figure 8(c).

Ten simulation statistics
30 × 30 environment map (Figure 8(c))	Iterations
	Algorithm	1	2	3	4	5	6	7	8	9	10	Average
	PSO	45	47	47	46	45	47	48	45	45	46	46
	GA	51	50	51	49	48	53	53	47	50	51	50
	S-IACOA	39	39	40	38	42	40	41	38	42	40	40
	Path length (m)
	PSO	53.29	53.29	53.29	53.29	53.29	53.29	53.29	53.29	53.29	53.29	53.29
	GA	54.63	54.63	54.63	54.63	54.63	54.63	54.63	54.63	54.63	54.63	54.63
	S-IACOA	44.52	44.52	44.52	44.52	44.52	44.52	44.52	44.52	44.52	44.52	44.52
	Simulation time (s)
	PSO	11.31	11.42	10.97	11.05	11.30	11.28	11.12	10.96	11.59	10.74	11.17
	GA	11.94	12.38	12.41	11.58	12.02	11.21	11.68	10.37	12.22	9.98	12.75
	S-IACOA	9.61	9.84	9.82	9.57	9.75	9.79	9.87	9.61	9.69	9.72	9.70

Several experiments and statistics on the 30 × 30 environment map show that S-IACO has certain advantages in terms of the number of iterations, shortest path, and simulation time, which proves the effectiveness and reliability of S-IACO.