We present a method for navigation of a small unmanned rotorcraft through an unsurveyed environment consisting of forest and urban canyons. Optical flow measurements obtained from a vision system are fused with measurements of vehicle velocity to compute estimates of range to obstacles. These estimates are used to populate a local occupancy grid which is fixed to the vehicle. This local occupancy grid allows modeling of complex environments and is suitable for use by generic trajectory planners. Results of simulations in a two-dimensional environment using a potential field obstacle avoidance routine are presented. This paper has presented an algorithm for generating a map useful for navigating a small unmanned rotor craft through a previously unknown static environment using only a monocular camera and measurements of vehicle speed. The camera's field of view is divided into bins of equal angular width. The maximum optical flow in each bin is used along with measurements of vehicle speed to compute an estimate of range to the nearest obstacle in that bin. These range measurements are used to generate an occupancy grid representation of the environment in the vicinity of the vehicle. This occupancy grid representation allows modeling of both small and large obstacles and can be used by trajectory planning algorithms to find a safe, feasible path to the goal. Simulation results show a very accurate and precise map can be generated from measurements of optical flow. Further, this map has been combined with a potential field-based obstacle avoidance and navigation algorithm to demonstrate safe flight to a goal in a complex, cluttered environment which was previously unsurveyed.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Local terrain mapping for obstacle avoidance using monocular vision


    Weitere Titelangaben:

    Lokale Gebietsabbildung zur Vermeidung von Hindernissen durch monokulares Sehen


    Beteiligte:


    Erscheinungsdatum :

    2009


    Format / Umfang :

    20 Seiten, 8 Bilder, 16 Quellen



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Local terrain mapping for obstacle avoidance using monocular vision

    Marlow, Sean Quinn / Langelaan, Jack W. | Tema Archiv | 2011


    Monocular Vision Occupancy Grid Mapping with Obstacle Avoidance on UAVs

    Balci, Emre / Watanabe, Toshinobu / Magree, Daniel P. et al. | AIAA | 2018


    Obstacle avoidance for small UAVs using monocular vision

    Lee, Jeong-Oog / Lee, Keun-Hwan / Park, Sang-Heon et al. | Emerald Group Publishing | 2011


    Obstacle avoidance for small UAVs using monocular vision

    Lee, Jeong-Oog | Online Contents | 2011


    Monocular visual mapping for obstacle avoidance on UAVs

    Magree, Daniel / Mooney, John G. / Johnson, Eric N. | IEEE | 2013