BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments

Description

Introduction:

BotanicGarden is a high-quality robot navigation dataset collected in unstructured natural environments, specifically, in a luxuriant botanic garden of more than 48000m2. It contains comprehensive sensors, including Gray and RGB stereo cameras, spinning and MEMS 3D LiDARs, and low-cost and industrial-grade IMUs, all of which are well calibrated and hardware-synchronized. An all-terrain wheeled robot is employed for data collection, traversing through thick woods, riversides, narrow trails, bridges, and grasslands, which are scarce in previous resources. This yields 33 short and long sequences, forming 17.1km trajectories in total. Excitedly, both highly-accurate ego-motions and 3D map ground truth are provided, along with fine-annotated vision semantics. We firmly believe that our dataset can advance robot navigation and sensor fusion research to a higher level.

Website:

https://github.com/robot-pesg/BotanicGarden

Citation:

Y. Liu et al., "BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments," IEEE Robotics and Automation Letters, vol. 9, no. 3, pp. 2798-2805, March 2024, doi: 10.1109/LRA.2024.3359548.

Including:

• LIO rosbag (LiDAR, IMU, Wheel)
  • 1005_00_LIO.bag
  • 1005_01_LIO.bag
  • 1005_07_LIO.bag
  • 1006_01_LIO.bag
  • 1008_03_LIO.bag
  • 1018_00_LIO.bag
  • 1018_13_LIO.bag
• VLIO rosbag (CAM, LiDAR, IMU, Wheel)
  • 1005_00_VLIO.bag
  • 1005_01_VLIO.bag
  • 1005_07_VLIO.bag
  • 1006_01_VLIO.bag
  • 1008_03_VLIO.bag
  • 1018_00_VLIO.bag
  • 1018_13_VLIO.bag
• GT-pose-qnew (Ground Truth Trajectory)
  • gt_1005_00_qnew.bag
  • gt_1005_01_qnew.bag
  • gt_1005_07_qnew.bag
  • gt_1006_01_qnew.bag
  • gt_1008_03_qnew.bag
  • gt_1018_00_qnew.bag
  • gt_1018_13_qnew.bag
• Calibration Params
  • camera_intrinsics (.yaml)
  • imu_intrinsics (.yaml)
  • extrinsics (.yaml)
• Application Form (Requesting more Sequences, Annotations, and Ground Truth Map)
  • BGarden-Application-Form-Sequence-And-Semantics.docx
  • BGarden-Application-Form-GTMap.docx

Funding:

This work was supported by National Key R&D Program of China under Grant 2018YFB1305005.

Updates:

• V1:
  • Initial version.
• V2:
  • Ground truth poses correction of quaternion from "wxyz" to "xyzw" order.
  • Application form correction.

Contact:

• Yuanzhi Liu (lyzrose@sjtu.edu.cn) for data request and technical support.
• Wei Tao (taowei@sjtu.edu.cn) for joining our project or team.

Files

Additional details