.png){kind=icon}
.png){kind=icon}
Return
Swarm intelligence optimization-based task assignment for multiple autonomous underwater vehicles
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jfranklin.2025.108234.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Task assignment strategies are essential for multiple autonomous underwater vehicles (multi-AUV) to execute various tasks simultaneously. A dynamic task assignment method for multi-AUV systems is proposed to tackle the searching and attacking problem, considering the underwater weak-communication and dynamic environments. In order to overcome the difficulties of limited information interaction among AUVs in the underwater environment, a multidisciplinary cost function, including task cost, cooperative cost, and communication cost, is developed to evaluate the system performances with consideration of cooperative detection, communication packet loss and communication delay. Then, a dynamic task assignment algorithm with a token-ring mechanism is proposed, which synthesizes a bioinspired swarm intelligence optimization and a neurodynamic approach. The proposed algorithm is utilized by each AUV to obtain the allocation scheme, and then a token AUV resolves task conflicts for multi-AUV. Thus the optimal task assignment sequence can be selected dynamically in the time-varying conditions. Simulation studies in which four AUVs attack two targets considering communication limitation are conducted. The results show that the proposed method can efficiently generate the optimal assignment sequences with availability and flexibility in terms of communication constraints and moving targets.
Journal
J
IF:
4.2
Papers:
822
Citations:
0