Monocular vision-based autonomous navigation system on a toy quadcopter in unknown environments

Abstract

In this paper, we present an monocular visionbased autonomous navigation system for a commercial quadcoptor. The quadcoptor communicates with a ground-based laptop via wireless connection. The video stream of the front camera on the drone and the navigation data measured onboard are sent to the ground station and then processed by a vision-based SLAM system. In order to handle motion blur and frame lost in the received video, our SLAM system consists of a improved robust feature tracking scheme and a relocalisation module which achieves fast recovery from tracking failure. An Extended Kalman filter (EKF) is designed for sensor fusion. Thanks to the proposed EKF, accurate 3D positions and velocities can be estimated as well as the scaling factor of the monocular SLAM. Using a motion capture system with millimeter-level precision, we also identify the system models of the quadcoptor and design the PID controller accordingly. We demonstrate that the quadcoptor can navigate along pre-defined paths in an unknown indoor environment with our system using its front camera and onboard sensors only after some simple manual initialization procedures.

General Moving Object Localization from a Single Flying Camera

“…This approach uses feature extraction from images to perform navigation and depth extraction. Huang et al [34] proposed an accurate autonomous indoor navigation system for a quad copter with a monocular vision. They used information from multiple sensors from the drone as well as a vision-based Simultaneous Localization and Mapping (SLAM) system and Extended Kalman Filter (EKF) to achieve robust and accurate 3D position and velocity estimation.…”

Multi-sensor fusion approach based on nonlinear H∞ filter with interval type 2 fuzzy adaptive parameters tuning for unmanned vehicle localization

“…Second, a single camera provides 2D information only; thus, scale estimation is required to estimate the 3D pose. 8 Henceforward, the current research challenge is related to the development of the advanced robust nonlinear filtering approaches for multi-sensor fusion approach. This approach is based on nonlinear HN filter and fuzzy adaptive parameters tuning for resolving the autonomous unmanned vehicle localization based on inertial measurements, GPS and monocular-vision data fusion.…”

“…Second, a single camera provides 2D information only; thus, scale estimation is required to estimate the 3D pose. 8…”

NavREn-Rl: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images

“…In this paper we explore a single-camera-based autonomous navigation and obstacle avoidance for MAVs in real environments. Traditional systems employ handcrafted sensing and control algorithms to allow navigation and has led to significant progress in this field [5], [6]. Recently, the success of deep neural networks have enticed researchers to study neuromorphic models of autonomous navigation [7]- [9].…”