Background

The capability of Unmanned Aerial Vehicles (UAVs) to perform landing task is essential for the autonomous operation, especially when they are outside line-of-sight. For autonomous landing, these vehicles need to know by themselves which areas are safe to be landed upon. Therefore, an intelligent landing system of UAVs using a monocular vision is proposed due to the fact that visual sensors are small, lightweight, and able to provide rich information of the UAVs’ self-motion and surroundings structure.

Bio-inspired approach for safe landing site recognition

The safe landing site can be defined as a relatively flat surface, it should not have too large inclination, and it is free of any obstacles. Therefore, a robust bio-inspired approach is suitable for this application as the motion parallax experienced by human or animals is expected to give an estimation of the surface inclination and surface flatness. Meanwhile, their motion in the world can be perceived as image motion of the environment projected on the retina or so-called optical flow.

A vision algorithm using optical flow is introduced to compute some important and useful information for landing, such as ventral flow, time-to-contact, surface flatness, and surface slope. These parameters can be used to detect obstacles, search for a safe landing spot, and perform smooth landing. The algorithm is computationally efficient and suitable for use during relatively fast maneuvers.

Publications

  • Ho, H.W. & de Croon, G.C.H.E. .Characterization of Flow Field Divergence for MAVs Vertical Control Landing. In Proceedings of the AIAA Guidance, Navigation, and Control Conference, SciTech 2016.
  • Ho, H.W., de Wagter, C., Remes, B.D.W., & de Croon, G.C.H.E. . Optical flow for self-supervised learning of obstacle appearance. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on (pp. 3098-3104). IEEE.(pdf)
  • de Croon, G.C.H.E., Ho, H.W., De Wagter, C., van Kampen, E., Remes, B.D.W. & Chu, Q.P. (2013). Optic-flow based slope estimation for autonomous landing. In International Journal of Micro Air Vehicles, 5/2013(4), 287-297.
  • de Croon, G.C.H.E., Ho, H.W., de Wagter, C., van Kampen, E., Remes, B.D.W. & Chu, Q.P. . Optic-flow based slope estimation for autonomous landing. In Proceedings of the International Micro Air Vehicle Conference and Flight Competition 2013. Toulouse, France.
  • Ho, H.W. & Chu, Q.P. . Automatic Landing System of a Quadrotor UAV Using Visual Servoing. In Proceedings of the CEAS Euro GNC conference 2013. Delft, The Netherlands.

 

Leave a Reply