Page 106 - Read Online

Mai et al. Intell Robot 2023;3(4):466-84 I http://dx.doi.org/10.20517/ir.2023.37 Page 13 of 19

Figure 6. The influences of on path length, fitness values, and mean convergence generation.

Table 4. The values of the experimental parameters
Symbol Description Value
m Number of ants 10
n Number of iterations 500
Q Pheromone intensity 100
Pheromone incentive factor 1
Expected heuristic factor 8
Pheromone evaporation rate 0.2
The maximum value of pheromone 0.9
The minimum value of pheromone 0.03
p The weight of the global optimal fitness value 1

nates (50, 42, 0.6). The maximum single moving distance of the UAV in the horizontal plane is two grids, and
the maximum moving distance in the vertical direction is one grid. To ensure that the height of the UAV is
within the safe range, the height constraint is set to 50 m < h < 2 km.

In order to illustrate the superiority of the method in this paper, the well-known improved ACO approaches:
AS and MMAS, the improved ACO by Chen et al., and the DSACO in this paper are introduced for simulation
and comparison research.

Figures 9-11 show the path planning simulation diagrams of four different algorithms in simple, medium,
complex, and complex environments, respectively. Through comparison, it is found that despite no apparent
differencebetweenthepathsobtainedbythefour algorithmsin simplemountainenvironments, DSACO seeks
theshortestpathcomparedtootherapproachesinmediumcomplexandcomplexmountainenvironmentsdue