Unmanned aerial vehicle autonomous obstacle avoidance system and method based on deep reinforcement learning

Abstract

The invention discloses an unmanned aerial vehicle autonomous obstacle avoidance system and method based on deep reinforcement learning, through a novel system architecture, training and decision making are separated, training time consumption can be greatly reduced, and aircraft decision making timeliness is improved. According to the autonomous obstacle avoidance method, a deep reinforcement learning model based on strategy iteration is adopted, original RGB images shot by a monocular camera of an unmanned aerial vehicle are taken as training data, other 3D information such as complex point cloud is not needed, the original RGB images are trained through a complete convolutional neural network to obtain depth image information, and the autonomous obstacle avoidance efficiency is improved. And the image is analyzed and predicted through a reinforcement learning method based on strategy iteration, the flight action of the unmanned aerial vehicle at the next moment is pre-judged in advance, and autonomous obstacle avoidance is realized. Compared with an existing typical value iteration-based method, the obstacle avoidance method provided by the invention is more efficient in training time consumption and lower in time consumption, can realize flexible and autonomous obstacle avoidance, and is suitable for autonomous obstacle avoidance scenes with high requirements, such as automatic inspection of a transformer substation and cruise of an unmanned aerial vehicle.

Description

technical field [0001] The invention relates to an unmanned aerial vehicle obstacle avoidance system and method, in particular to an unmanned aerial vehicle autonomous obstacle avoidance system and method based on deep reinforcement learning; it belongs to the technical field of unmanned aerial vehicle flight control. Background technique [0002] Obstacle avoidance is one of the core issues of UAVs. Its goal is to allow UAVs to autonomously explore the unknown environment to avoid collisions with other objects, so as to obtain a flight path that can avoid threats and reach the target safely. The traditional obstacle avoidance technology detects traversable spaces and obstacles, and then performs path planning. The data information used is captured by RGB-D cameras, light detection, ranging sensors (LIDAR), and even sonar. These traditional obstacle avoidance technologies can be well adapted to the autonomous obstacle avoidance of ground robots, but it is difficult to apply ...

AI Technical Summary

Problems solved by technology

Although these works can scale the trained networks to the real world, they still require a lot of computing resources to generate huge datasets and train them

Images