Multi-UAV trajectory planning using gradient-based sequence minimal optimization

Abstract

Multi-UAV system is widely used in surveillance, search and rescue, and industrial inspection. Multi-UAV trajectory planning is crucial for the multi-UAV system, but multi-UAV trajectory planning often needs to consider many constraints, such as trajectory smoothness, obstacle collisions, mutual collisions, dynamic limits, time-consuming, and trajectory length. It is a challenge to balance these constraints while considering computational performance. This paper proposes a novel multi-UAV trajectory planning method to solve the challenge. This method uses time segmentation instead of traditional waypoint segmentation to establish a trajectory optimization model based on the unified time interval, which simplifies the calculation of cost functions. At the same time, virtual segments are introduced to adapt to the trajectory length of different UAVs to reduce the total arrival time. Nonlinear constraints are cast into cost functions and a gradient-based sequential minimal optimization (GB-SMO) algorithm is proposed to minimize the cost function, which decouples the constraint of the mutual collisions in each iteration to save the planning time. Experiments are performed on a multi-UAV system to prove the effectiveness of the proposed method. Results show that this method has good performance in obstacle-rich environments and is efficient for a large number of UAVs.