Research On Mission Planning Technology Of Multiple Unmanned Mobile Platforms

Mission planning is to make plans for the efficient completion of tasks to maximize the benefits of global tasks.Mission planning can be divided into task allocation and path planning,which is widely used in civil and military fields.Due to the characteristics of multi location and diversity of current tasks,single unmanned mobile platform can not complete such tasks independently.Many unmanned mobile platforms can accomplish such tasks efficiently through cooperation,and have the characteristics of strong robustness and high reliability.Therefore,this paper studies the mission planning of multiple unmanned mobile platforms.Based on the analysis of existing mission planning technologies,this paper focuses on the task allocation and path planning technologies of multiple unmanned mobile platforms.Firstly,aiming at the problem that the efficiency of task assignment decreases with the increase of task size,a discrete particle swarm optimization algorithm based on evolutionary learning is proposed.The algorithm realizes the mapping between the particle position and the feasible solution of the problem through the sequential coding of particles,improves the evolution mode of particles,introduces the influence of the same generation of population particles into the formula of particle position update,guarantees the diversity of population,and enhances the global search ability of the algorithm.At the same time,in the process of learning from the optimal value,the algorithm introduces the intermediate individual acceptance probability,improves the ability to jump out of the local optimal value,speeds up the convergence speed of the algorithm,and improves the efficiency of task allocation.Secondly,a dynamic path planning algorithm based on neighborhood disturbance is proposed to solve the problem of poor real-time path planning for multiple unmanned mobile platforms.The algorithm improves the way of state generation,uses five neighborhood disturbance mechanisms to reduce the randomness of new state generation,and records the current optimal state to guide the algorithm to search the optimal direction and improve the real-time performance of path planning.In addition,due to the lack of executors in the dynamic environment,the auction mechanism is introduced in the algorithm to realize the negotiation of the emergency tasks on the unmanned mobile platform,complete the re planning of the original allocation scheme and path,and improve the overall mission planning efficiency.In this paper,the MATLAB platform is used to build a multi unmanned mobile platform mission planning system,and the above results are simulated and tested.Simulation results show that,compared with the existing algorithms,the algorithm proposed in this paper can significantly improve the efficiency and real-time performance of mission planning for multiple unmanned mobile platforms,and achieve the expected purpose.