This study presents a technique for multi-rotor unmanned aerial vehicles (UAVs) to efficiently and safely land in dynamic environments. The aim of this method is to locate a secure potential landing zone (PLZ) and choose the best one for landing. The PLZ is initially determined with an area estimation algorithm, which returns the empty region in the image where the UAV can possibly land. The obstacle-free regions that have a higher area than the vehicle’s dimensions with tolerance are labeled as safe PLZs. In the second phase of this approach, the velocities of dynamic obstacles moving towards the PLZs are calculated, and their time to reach the zones is taken into consideration. The estimated time of arrival (ETA) of the UAV is calculated, and during the descent of the UAV, dynamic obstacle avoidance is executed. A ToF (Time of Flight) sensor is used for detecting altitude, while a depth camera is used for performing triangulation, area estimation, and computing distance to the target site. The approach, tested in real- world environments, has shown better results compared to existing work as the computation time is significantly lower, while the accuracy is competitive with deep learning counterparts.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    RHFSafeUAV: Real-Time Heuristic Framework for Safe Landing of UAVs in Dynamic Scenarios


    Contributors:


    Publication date :

    2023-06-06


    Size :

    3207134 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-Time Heuristic Framework for Safe Landing of UAVs in Dynamic Scenarios

    Singh, Jaskirat / Adwani, Neel / Kandath, Harikumar et al. | ArXiv | 2022

    Free access



    GUIDED LANDING WITH UAVS

    DE RADHA MOHAN / PATRA SUMAN | European Patent Office | 2025

    Free access

    A Real-Time and Multi-Sensor-Based Landing Area Recognition System for UAVs

    Fei Liu / Jiayao Shan / Binyu Xiong et al. | DOAJ | 2022

    Free access