Proprioceptive Sensor Dataset for Quadruped Robots
These datasets are of the hydraulically actuated robot HyQ’s proprioceptive sensors. They include absolute and relative encoders, force and torque sensors, and MEMS-based and fibre optic-based inertial measurement units (IMUs). Additionally, a motion capture system recorded the ground truth data with millimetre accuracy. In the datasets HyQ was manually controlled to trot in place or move around the laboratory. The sequence includes: forward and backwards motion, side-to-side motion, zig-zags, yaw motion, and a mix of linear and yaw motion. All of the datasets are at least five minutes long. The aim of these datasets is to test state estimation using only proprioceptive sensors.
Please see instructions.pdf.
- Documentation documentation.zip (1.04 MB)
- Visualization of the raw data visualization.zip (94.79 MB)
- All of the raw data combined data.zip (2.28 GB)
- Trot in Lab 1 data trot_in_lab_1.zip (245.79 MB)
- Trot in Lab 2 data trot_in_lab_2.zip (224.41 MB)
- Trot in place data trot_in_place.zip (230.54 MB)
- All of the data, documentation, and visualization full.zip (2.37 GB)
- endurance_trot.zip (1.20 GB)
- soft_trot_in_place.zip (231.86 MB)
- rigid_trot_in_place.zip (228.56 MB)