Page 43 - Read Online
P. 43
Sellers et al. Intell Robot 2022;2(4):33354 I http://dx.doi.org/10.20517/ir.2022.21 Page 349
Figure 11. Illustration of the path created from the other models [44] . (A) It depicts the path created by Asl and Taghirad model by the green
lines (redrawn by Asl and Taghirad, 2019 [44] ). (B) It represents the proposed method point order and traversed path. The point order is
illustrated by the violet arrows, while the orange path represents the robot path. Safety-aware roads are depicted by the blue dashed lines.
The waypoints are illustrated by the violet circles.
Figure 12. Illustration of the path created from the compared models [45] . (A) It depicts the path created by Zhuang et al.’s model by the
green lines (redrawn from Zhuang et al., 2021 [45] ). (B) It represents the proposed method point order and traversed path. The point order
is illustrated by the violet arrows, while the orange path represents the robot path. Safety-aware roads are depicted by the blue dashed
lines. The waypoints are illustrated by the violet circles.
Itisclearthatthewaypointorderandpathsobtainedbyeachmodelarecreatedinanobstacle-freeenvironment,
as illustrated in Figure 10A. The length created by the Zhang’s model was 240.84 m, while the proposed model
produced a shorter trajectory of 219.99 m. This is due to the founded waypoint orders in the environment. In
Zhang’s comparison study, the proposed model establishes more nodes, and the overall path is expanded by
1.09%, but the proposed model generates a solution 6.1% faster than the compared model. Zhang’s proposed
model has to utilize a node selection algorithm to establish its shortest path, while the proposed model does
not. Due to this feature, the compared model was evaluated before this crucial step and discovered that the
nodes established were vastly greater than the proposed model, as seen in Table 2. Considering this factor, the
proposed model can surpass and outperform Zhang’s model. Asl and Taghirad aimed to solve the multi-goal