Unmanned aerial vehicle obstacle avoidance method

Abstract

The invention discloses an unmanned aerial vehicle obstacle avoidance method, which comprises the steps of planning an initial flight path for an unmanned aerial vehicle; detecting position and speed information of an obstacle within a certain distance of the unmanned aerial vehicle by using a sensor in the flying process of the unmanned aerial vehicle; calculating whether collision occurs or not in flight according to the initial path by adopting a collision detection algorithm; working out a collision avoidance path by using a policy iteration algorithm according to a collision region information predicted by the collision detection algorithm and a destination of the unmanned aerial vehicle; correcting the collision avoidance path by using a backtracking method, and preventing the unmanned aerial vehicle from being caught in a local obstacle trap; and performing differential flattening processing on the corrected collision avoidance path according to dynamic performance characteristics of the unmanned aerial vehicle. According to the method provided by the invention, flight envelope restriction requirements of the unmanned aerial vehicle in reality are met, a common problem of local obstacle traps in the path planning algorithm is effectively avoided, and multiple obstacles can be avoided in real time under the premise of meeting the dynamic performance.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to an obstacle avoidance method for unmanned aerial vehicles. Background technique [0002] Compared with manned aircraft, UAVs have significant advantages in military and civilian fields, and have been widely used in aerial photography, environmental monitoring, forest fire prevention and other fields, and the cost is low. In order to promote UAVs to enter a broader application field and share the flight space with manned aircraft, how to ensure the safety of UAVs in the air has become a difficult problem that needs to be solved. At present, scholars at home and abroad have successively proposed patents and documents on UAV obstacle avoidance methods, such as: [0003] Document 1 (A.G.Shem, T.A.Mazzuchi, and S.Sarkani, "Addressing uncertainty in UAV navigation decision-making," IEEE Transactions on Aerospace and Electronic Systems, vol.44, no.1, pp.295-313, 2008.)...

AI Technical Summary

Problems solved by technology

This method has the disadvantages of a large amount of calculation and does not take into account the limitations of the UAV's dynamic performance.

[0010] To sum up, the existing documents and patents related to UAV obstacle avoidance methods proposed by existing experts are limited to locating obstacles, lack of consideration of UAV dynamic constraints and flight envelope requirements, and cannot realize practically no UAV. Human-Machine Autonomous Obstacle Avoidance

Images