The ETH‐MAV Team in the MBZ International Robotics Challenge

Abstract

This study describes the hardware and software systems of the Micro Aerial Vehicle (MAV) platforms used by the ETH Zurich team in the 2017 Mohamed Bin Zayed International Robotics Challenge (MBZIRC). The aim was to develop robust outdoor platforms with the autonomous capabilities required for the competition, by applying and integrating knowledge from various fields, including computer vision, sensor fusion, optimal control, and probabilistic robotics. This paper presents the major components and structures of the system architectures and reports on experimental findings for the MAV‐based challenges in the competition. Main highlights include securing the second place both in the individual search, pick, and place the task of Challenge 3 and the Grand Challenge, with autonomous landing executed in less than 1 min and a visual servoing success rate of over 90% for object pickups.

Team NimbRo at MBZIRC 2017: Fast landing on a moving target and treasure hunting with a team of micro aerial vehicles

“…Camera Approach ETH Zürich (Bähnemann, Pantic, et al, 2017) 752 × 480 @ 50 Hz One blob detector for platform, another detector for cross of pattern, tracker uses allocentric positional distribution over figure eight track University of Prague (Báča et al, 2017) 752 × 480 @ 50 Hz Full image adaptive threshold using altitude, circle detection, morphological operations to recognize four equally sized quadrants around the cross University of Zürich (Falanga et al, 2017) In our work, we rely solely on GPS readings-which are considered to have sufficient relative accuracy between the MAVs in an outdoor scenario-and separation of the MAV working areas.…”

Deployment of an autonomous mobile manipulator at MBZIRC

“…A special focus of this challenge lies on entirely autonomous behavior since any intervention by a human operator will directly result in significant score penalties. During the grand challenge, the UGV task is executed simultaneously with an aerial vehicle mission, which is documented in Bähnemann et al ().…”

Fully autonomous micro air vehicle flight and landing on a moving target using visual–inertial estimation and model‐predictive control

“…Their proposed odometry and control systems consider the underactuated dynamics, the actuator limitations, and the field of view constraints, to give extra robustness to abrupt variations in target motion. We would also like to highlight the work of other MBZIRC participants such as Falanga, Zanchettin, Simovic, Delmerico, and Scaramuzza (2017), Beul, Houben, Nieuwenhuisen, and Behnke (2017), and Bähnemann et al (2017), where the last two of them achieved successful landing in the competition and their work will be discussed later.…”

“…We cannot make a direct comparison with the performance of the teams who participated in the real challenge, as the final time also depends on when the target becomes visible for the first time. We can, however, compare our approach with the ones by team ETH-MAV(Bähnemann et al, 2017) and NimbRo Lidar sensor to check the distance between the MAV and the target and trigger the final stage of the landing procedure.• NimbRo team used a GPS + IMU fusion algorithm for the MAV state estimation, along with a fast trajectory planning algorithm. To detect and track the target they use two different cameras.…”