MAV Datasets for Autonomous Navigation

This web page presents datasets for autonomous navigation of MAVs collected on-board our Micro Aerial Vehicle (MAV). The datasets contain stereo images, IMU , Px4flow, RGB-D camera, ultrasonic ,lidar measurements, and accurate ground-truth of motion capture system Vicon indoors and Ublox RTK outdoors.

MAV Platform


Sensor List

Product model of all sensors used in our datasets are listed:

Sensor Product Model Collection frequency
Optical flow Px4flow v1.3.1 20
Stereo camera 640×480×2 OV7725 30
IMU MPU9250 40
Ultrasonic MaxSonar MB1242 15
RGB-D Camera ASUS Xtion Pro Live 40
Lidar Hokuyo UST-20LX 40
Lidar Hokuyo UST-20LX 40
Vicon Vero 360 100
RTK GNSS receiver Ublox M8P 10


Our datasets are collected in four main scene:5m×5m×2.5m testing room with Vicon ’ Room’, 8m×12m×5m hall of office with Vicon in part of it ’ Hall’, 20m×20m open square outdoors ’ OutSquare’, and 50m2 area near the building outdoors ’ OutBuilding’.


Flight trajectories of datasets in indoor and outdoor scene are shown as following figure. where left one for indoor and right one for outdoor.



You can download our ASNDM datasets from link.

The details of datasets are shown in the table as follows.

Task Data ROS bag
SLAM data link bag link
3D Model Reconstruction data link bag link
Obstacle avoidance data link bag link
MAV State Estimation data link bag link