An Improved Path Planning Algorithm for UAV Based on RRT
Jianqing Chen, Jiyan Yu
Abstract
For RRT and RRT * algorithm, the search time is long, low sampling efficiency and planning path twists and turns, someone put forward a kind of narrow two-way rapid extension of optimal sampling space random tree algorithm. In each iteration of the algorithm, two random trees are extended, and two new nodes can be generated in one iteration to accelerate the expansion speed. Then an ellipse interval sampling is constructed with the starting point and the target point as the focus, and the length of the trajectory as the long axis. The idea of continuously reducing the sampling space in the iteration makes the two random trees expand towards their respective target points under a certain probability. In the simulation experiment, the proposed algorithm is compared with RRT*, and the results show that the improved algorithm improves the convergence speed and reduces the track distance under the premise of optimizing the number of track nodes.