Multi-AUV Kinematic Task Assignment based on Self-organizing Map Neural Network and Dubins Path Generator
Xin Li, Wenyang Gan, Pang Wen, Daqi Zhu
TL;DR
This work tackles joint task allocation and kinematically feasible path planning for multiple AUVs by fusing an improved Self-Organizing Map (SOM) with Dubins-path trajectory generation. It introduces an event-triggered SOM that online-adjusts task assignments using a load-balancing term and a distance metric that combines proximity with current workload, while enforcing kinematic constraints and obstacle awareness. A Dubins-path generator is extended to 3D, enabling executable trajectories under $R_{min}$ and pitch limits, with an online reallocation mechanism when path feasibility is compromised. Simulations demonstrate improved workload balance and feasible, energy-aware trajectories in both obstacle-free and obstacle-rich scenarios, including 3D environments, and indicate potential for embedded deployment on platforms like a Raspberry Pi.
Abstract
To deal with the task assignment problem of multi-AUV systems under kinematic constraints, which means steering capability constraints for underactuated AUVs or other vehicles likely, an improved task assignment algorithm is proposed combining the Dubins Path algorithm with improved SOM neural network algorithm. At first, the aimed tasks are assigned to the AUVs by improved SOM neural network method based on workload balance and neighborhood function. When there exists kinematic constraints or obstacles which may cause failure of trajectory planning, task re-assignment will be implemented by change the weights of SOM neurals, until the AUVs can have paths to reach all the targets. Then, the Dubins paths are generated in several limited cases. AUV's yaw angle is limited, which result in new assignments to the targets. Computation flow is designed so that the algorithm in MATLAB and Python can realizes the path planning to multiple targets. Finally, simulation results prove that the proposed algorithm can effectively accomplish the task assignment task for multi-AUV system.