Micro-Aerial Vehicles (MAVs) have gained significant attention lately due to their size advantage. However, there is a drawback of MAVs — its limited payload and size don't allow adding extensive sensors. That explains why incorporating computer vision is of great significance to MAVs. One of the problems that computer-vision-driven MAVs need to overcome is obstacle avoidance, which is very important for autonomie vehicles especially for aerial vehicles as they are more vulnerable to collision compared to ground vehicles. Over the last ten years, several obstacle detection algorithms have been developed to create collision-free maneuver for MAVs. Most of them have promising results inside virtual environment; however, they fail miserably during actual flight tests. In this project, we will investigate the real-life issues affecting obstacle avoidance for MAVs and carry out the project on a physical drone. We take into consideration the limitations of the platform and derive our own obstacle avoidance algorithm by combining several existing ones. Effectiveness of the algorithm will be demonstrated through experimental results on the physical drone.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Basic Micro-Aerial Vehicles (MAVs) obstacles avoidance using monocular computer vision


    Contributors:


    Publication date :

    2014-12-01


    Size :

    338266 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MONOCULAR VISION-BASED OBSTACLE DETECTION/AVOIDANCE FOR UNMANNED AERIAL VEHICLES

    Al-Kaff, Abdulla / Meng, Qinggang / Martín, David et al. | British Library Conference Proceedings | 2016




    Monocular Vision-based Obstacle Avoidance Scheme for Micro Aerial Vehicle Navigation

    Karlsson, Samuel / Kanellakis, Christoforos / Mansouri, Sina Sharif et al. | IEEE | 2021


    Computer Vision for MAVs

    López, Antonio M. / Imiya, Atsushi / Pajdla, Tomas et al. | Wiley | 2017