Fig 1.
Core process diagram of the RRT algorithm.
Fig 2.
Step of re-selecting parent node.
Fig 3.
Re-wiring phase.
Fig 4.
Schematic diagram of high confidence sampling strategy.
Fig 5.
Schematic diagram of low confidence sampling strategy.
Fig 6.
The path generated by the RRT* algorithm.
Fig 7.
Path after cubic B-spline curve optimization.
Table 1.
Performance comparison table of different object detection algorithms.
Fig 8.
Comparison of evaluation metrics between YOLOv11n and PC-YOLO.
Fig 9.
YOLOv11n detection result image.
Fig 10.
PC-YOLO detection result image.
Table 2.
AUBO I5 robotic arm standard DH parameter table.
Fig 11.
Schematic diagram of obstacle distribution in three simulation scenarios.
Table 3.
Effect of noise coefficient on path planning indicators at confidence 0.6.
Table 4.
Effect of noise coefficient on path planning indicators at confidence 0.7.
Table 5.
Effect of noise coefficient on path planning indicators at confidence 0.8.
Table 6.
Effect of noise coefficient on path planning indicators at confidence 0.9.
Table 7.
Comparison of different path planning algorithms.
Fig 12.
RRT* path planning.
Fig 13.
Bi-RRT path planning.
Fig 14.
APF-RRT* path planning.
Fig 15.
VM-RRT* path planning.
Fig 16.
Comparison of metric distributions between RRT* and VM-RRT* (Scene 1).
Fig 17.
Comparison of metric distributions between RRT* and VM-RRT* (Scene 2).
Fig 18.
Comparison of metric distributions between RRT* and VM-RRT* (Scene 3).
Fig 19.
Comparison of three-Axis velocity curves for robotic arms under different smoothing strategies.
Fig 20.
Comparison of three-Axis acceleration curves for robotic arms under different smoothing strategies.
Fig 21.
Simulation diagram of the movement process of the robotic arm.