RJA-Star Algorithm for UAV Path Planning Based on Improved R5DOS Model

Abstract

To improve the obstacle avoidance ability of agricultural unmanned aerial vehicles (UAV) in farmland settings, a three-dimensional space path planning model based on the R5DOS model is proposed in this paper. The direction layer of the R5DOS intersection model is improved, and the RJA-star algorithm is constructed with the improved jump point search A-star algorithm in our paper. The R5DOS model is simulated in MATLAB. The simulation results show that this model can reduce the computational complexity, computation time, the number of corners and the maximum angles of the A-star algorithm. Compared with the traditional algorithm, the model can avoid obstacles effectively and reduce the reaction times of the UAV. The final fitting results show that compared with A-star algorithm, the RJA-star algorithm reduced the total distance by 2.53%, the computation time by 97.65%, the number of nodes by 99.96% and the number of corners by 96.08% with the maximum corners reduced by approximately 63.30%. Compared with the geometric A-star algorithm, the running time of the RJA-star algorithm is reduced by 95.84%, the number of nodes is reduced by 99.95%, and the number of turns is reduced by 67.28%. In general, the experimental results confirm the effectiveness and feasibility of RJA star algorithm in three-dimensional space obstacle avoidance.

Hybrid algorithms in path planning for autonomous navigation of unmanned aerial vehicle: a comprehensive review

“…These environments are realistically simulated in terms of complexity and obstacles. There are only very few studies to present the path planning algorithms for UAVs in realistic environments such as urban [33,35,51,59,74,77,78], rural [29], and forest environments [52].…”

“…On the other hand, some combinations only apply to certain environments. Integration of A * and JPS does not care about complex and dynamic work environments where UAV mainly operate in the field [29], APF based-RRT algorithm is only appropriate in situations with known information and no moving obstructions [38], IRRT * -APF has not mentioned many different types of obstacles [42]. Additionally, for A * -D * algorithm, although it has a low cost, this algorithm has to perform many calculations and the more complex the calculation process, the more processing time it takes [31].…”

“…These methods can be combined with each other or with other algorithms to create new ones that are more effective than the original single algorithm. According to literature, the A-star technique is a useful tool, but as the size of the map increases, the computing difficulty of the typical A-star algorithm space increases exponentially, leading to a notable rise in both computational complexity and computational time [29]. In order to find solutions to these problem, A * algorithms should be integrated with others.…”

“…Besides being applied to complex environments as above, A * is also the basis for developing algorithms to plan path in 3D environments, for example, an improved A * algorithms, namely RJA-star. In [29], to enhance the Astar algorithm, the model integrates the jump point search (JPS) algorithm with the three-dimensional space algorithm. The novel algorithm help decrease the A-star algorithm's complexity in three dimensions, reduce the number of corners on the path, increase its smoothness, and optimize the A-star algorithm's path selection.…”

Path Planning of an Unmanned Surface Vessel Based on the Improved A-Star and Dynamic Window Method

“…where g(n) is the actual distance cost from the starting point to the current node, h(n) is the estimated distance cost from the current node to the target node [24], and D(n) is the hazard function that uses the Voronoi field to add hazards to the grid. The A-star algorithm only uses the path length as a heuristic function, and the planned path often approaches obstacles, which cannot effectively guide USV to navigate safely and smoothly.…”