RONIN (Robust Neural Inertial Navigation)

RoNIN

The RoNIN dataset contains over 40 hours of IMU sensor data from 100 human subjects with 3D ground-truth trajectories under natural human movements. This data set provides measurements of the accelerometer, gyroscope, magnetometer, and ground track, including direction and location in 327 sequences and at a frequency of 200 Hz. A two-device data collection protocol was developed. A harness was used to attach one phone to the body for 3D tracking, allowing subjects to control the other phone to collect IMU data freely. It should be noted that the ground track can only be obtained using the 3D tracker phone attached to the harness. In addition, the body trajectory is estimated instead of the IMU. RoNIN datset contians 42.7 hours of IMU-motion data over 276 sequences in 3 buildings, and collected from 100 human subjects with three Android devices.

The dataset contains following:

1. Data 13.81 GB
seen_subjects_test_set.zip 3.15 GB
train_dataset_1.zip 4.49 GB
train_dataset_2.zip 3.18 GB
unseen_subjects_test_set.zip 2.99 GB


2. Pretrained_Models 57.05 MB
ronin_body_heading.zip 579.52 KB
ronin_lstm.zip 2.29 MB
ronin_resnet.zip 48.49 MB
ronin_tcn.zip 5.71 MB

All HDF5 files are organized as follows

HDF5 data format

1. raw:
tango:
gyro, gyro_uncalib, acce, magnet, game_rv, gravity, linacce, step, tango_pose, tango_adf_pose, rv, pressure, (optional) [wifi, gps, magnetic_rv, magnet_uncalib]
imu:
gyro, gyro_uncalib, acce, magnet, game_rv, gravity, linacce, step. rv, pressure, (optional) [wifi, gps, magnetic_rv, magnet_uncalib]


2. synced:
time, gyro, gyro_uncalib, acce, magnet, game_rv, rv, gravity, linacce, step


3. pose:
tango_pos, tango_ori, (optional) ekf_ori