文档介绍：Visual-Inertial SLAM for a Small Helicopter in Large Outdoor
Environments
Markus W. Achtelik, Simon Lynen, Stephan Weiss, Laurent Kneip, Margarita Chli, Roland Siegwart
Abstract— In this video, we present our latest results towards
fully autonomous flights with a small helicopter. Using a
monocular camera as the only exteroceptive sensor, we fuse
inertial measurements to achieve a self-calibrating power-on-
and-go system, able to perform autonomous flights in previously
unknown, large, outdoor spaces. Our framework achieves
Simultaneous Localization And Mapping (SLAM) with previ-
ously unseen robustness in onboard aerial navigation for small
platforms with natural restrictions on weight putational
power. We demonstrate essful operation in flights with
altitude between -70 m, trajectories with 350 m length, as Fig. 1: Fusing information from the downward-looking camera and an IMU,
well as dynamic maneuvers with track speed of 2 m/s. All flights the MAV performs SLAM in a disaster area
shown are performed autonomously using vision in the loop,
with only high-level waypoints given as directions. limiting the capability for aggressive maneuvers and the
flight duration and, as a consequence, autonomy.
I. INTRODUCTION A minimal sensor prising a camera and an
Inertial Measurement Unit (IMU) is very suitable for MAV
The research towards autonomous Micro Aerial Vehicles
navigation, but imposes great research challenges. Fusing
(MAVs) has been increasingly active over the past few
inertial and visual cues can be very beneficial as they
years, resulting to great progress in the field. We have seen
plementary information, aiding the robustness
impressive flights with aggressive maneuvers [1], but these
of the estimation processes. However, plexity of the
rely on external tracking systems (. Vicon) limiting their
system grows vastly with each extra sensor; one has to take
feasibility to lab-controlled environments. Ego-motion and
into ac