Towards vision-based safe landing for an autonomous helicopter

Autonomous landing is a challenging problem for aerial robots. An autonomous landing manoeuver depends largely on two capabilities: the decision of where to land and the generation of control signals to guide the vehicle to a safe landing. We focus on the rst capability here by presenting a strategy and an underlying fast algorithm as the computer vision basis to make a safe landing decision. The experimental results obtained from real test ights on a helicopter testbed demonstrate the robustness of the approach under widely di erent light, altitude and background texture conditions, as well as its feasibility for limited-performance embedded computers.