Vision-Based Navigation Frame Mapping and Path Planning for Micro Air Vehicles
Huili Yu, Randy Beard, Jeffrey Byrne · 2009
Path planning and obstacle avoidance for Micro Air Vehicles (MAVs) involve planning a feasible path from an initial state to a goal state while avoiding obstacles in the environment. This paper presents a vision-based navigation frame multi-resolution mapping and path planning technique for MAVs using a forward-looking onboard camera. A depth map representing time to collision and bearing to obstacles is obtained by computer vision algorithms. To account for measurement uncertainties introduced by the camera, a multiresolution map in the navigation frame of the MAV is created using an occupancy grid. The map is represented by log-polar mapping that is more compatible with time to collision estimates and also reflects the pixel quantization uncertainty of vision. The log polar representation gives finer resolution to areas close to the MAV and coarser resolution to areas far from the MAV. We employ the RRT algorithm to find a collision-free path in the navigation frame. The experimental results show that the proposed technique is successful in solving path planning and multiple obstacles avoidance problems for MAVs.