基于APSODE-MS算法的无人机航迹规划

无人机航迹规划是指在环境威胁与自身约束条件下,规划一条安全可行的航迹,是实现无人机自主化飞行的关键技术之一.为实现无人机在不同城市环境下能够快速规划一条安全可靠的航迹,提出一种基于自适应粒子群差分进化-最小捕捉(APSODE-MS)算法的无人机航迹规划方法.首先,建立城市环境航迹规划数学模型,以航程距离、威胁约束、违背约束代价3者的加权和作为目标函数;其次,在PSO算法中引入自适应非线性惯性权重,根据粒子偏离全局最优解的程度分配不同的搜索模式,结合动态差分进化(DE)算法加快粒子的收敛速度,引入改进的正态扰动提高跳出停滞与早熟现象的能力;最后,筛选关键航迹点,并采用最小捕捉轨迹(MS)算法对航迹进行光滑处理.仿真结果表明,所提出的APSODE-MS航迹规划方法能够在不同城市仿真环境下较好地完成规划任务,并能获得更优的航路,从而验证算法的有效性和鲁棒性.

UAV trajectory planning based on APSODE-MS algorithm

Unmanned aerial vehicle (UAV) trajectory planning is to plan a safe and feasible track under the environmental threats and self-constraints. It is one of the key technologies to realize the autonomous flight of an UAV. In order to quickly plan a safe and reliable UAV path in the complex urban environment, this paper presents a hybrid adaptive particle optimization with differential evolution and minimum snap (APSODE-MS) for the UAV path planning in the city. Firstly, this paper establishes a mathematical model for urban environmental trajectory planning, and the weighted sum of flight distance, threat constraint, and violation constraint cost is taken as the objective function. Secondly, the adaptive nonlinear inertia weight is introduced into the PSO algorithm, and different search modes are assigned according to the degree of deviation of the particles from the global optimal solution. The dynamic DE algorithm is used to accelerate the convergence rate of the particles, and the improved normal perturbation is introduced to improve the ability to break out of stagnation and precocity. Finally, the key track points are screened, and the minimum snap(MS) algorithm is used to smooth the track. The simulation results show that the proposed APSODE-MS path planning method can complete the planning task well and obtain a better path in different city simulation environments, thus verifying the effectiveness and robustness of the algorithm.