.png){kind=icon}
.png){kind=icon}
Return
A Multidevice Ground–Air Collaborative Path Planning Method With Hierarchical Architecture Based on Search-Enhanced Walrus Optimizer
.png){kind=icon}
PRE
AI
DOI：10.1109/JIOT.2026.3676741.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As the demand for multidimensional ground and air information acquisition increases on modern battlefields, ground–air cooperation has become a crucial method to enhance operational efficiency and decision-making. In the complex and changeable battlefield environment, autonomous ground vehicles (AGVs) and autonomous aerial vehicles (AAVs) can leverage their strengths to maximize exploration efficiency. The multilevel collaborative path planning method for UGV-AAV systems (MLCPP-UUs) is proposed in this article, comprising three layers: single-AAV, multi-UGV, and interactive planning. To optimize the total cost of the model, multiple strategies are used to improve the global exploration and local search of the walrus optimizer (WO). In the search-enhanced walrus optimizer (SEWO), a dynamic step size adjustment is introduced during migration based on terrain steepness to avoid blind random search and improve search space coverage. In the later iteration, a nonlinear decreasing search factor is used to accelerate the convergence speed. For high-quality solutions, the simplex method is used to complete the “secondary exploitation” by efficiently searching the neighborhood of the solution space. To evaluate the performance of SEWO, three reference terrains from real digital elevation models (DEMs) are generated with obstacle scenarios and interaction modes. The results show that the proposed algorithm can plan the collaborative paths satisfying the constraints efficiently, proving its effectiveness in the ground–air cooperative planning problem.
Keywords:
Ground–air cooperative 3-D path planning
hierarchical architecture
multidevice systems
search-enhanced walrus optimizer (SEWO)
Journal
IF:
8.9
Papers:
1.4W
Citations:
7.8W