Obstacle Avoidance of a UAV Using Fast Monocular Depth Estimation for a Wide Stereo Camera

In this study, we designed an obstacle avoidance algorithm for a quadrotor unmanned aerial vehicle (UAV) equipped with a wide field-of-view (FOV) stereo camera, utilizing a learning-based depth estimation approach. Depth estimation using monocular cameras is gaining interest as a viable alternative to large and heavy sensors, such as light detection and ranging (LiDAR) sensors. However, deep learning-based depth estimation has low accuracy unless the depth estimation is done in an environment similar to that of the training data. Therefore, we first designed a depth estimation network for a wide-FOV stereo camera using two cameras. Then, we estimated the depth image using a convolutional neural network and improved the accuracy using stereo matching. We used the estimated depth images to develop a simple behavior-arbitration-based control algorithm that steers the quadrotor away from 3-D obstacles. We conducted simulations and experiments using a real drone in an indoor and outdoor environment to validate our proposed algorithm. An analysis of the experimental results showed that the proposed method could be employed for navigation in cluttered environments.