SLAM Datasets

Datasets from the ShanghaiTech Automation and Robotics Center (STAR Center) for research on Simultaneous Localization And Mapping (SLAM).

• 

  MARS Dataset

  Three indoor datasets with the MARS Mapping Robot.
  • Sensors:
    9x RGB camera (5MP, 10Hz)
    2x 32beam Velodyne LiDAR
    1x IMU
  • Duration: 704sec
  • Distance: 177m
  • Size: 120GB
  • Scene: Indoor Lab
  • Format: ROS 1 Bag
  • Ground truth: Tracking System, ground truth map
  • Paper: Chen et al. Advanced mapping robot and high-resolution dataset, Robotics and Autonomous Systems, Elsevier, 2020
• 

  VINS-RGBD

  Three datasets collected with an Intel RealSense camera (Handheld, wheeled & tracked robot).
  • Sensor: RGBD: IntelRealsense D435i with IMU
  • Duration: 585 sec
  • Distance: 50 m
  • Size: 16GB
  • Scene: Indoor Lab
  • Format: ROS 1 Bag
  • Ground truth: Tracking System
  • Paper: Shan et al. RGBD-Inertial Trajectory Estimation and Mapping for Ground Robots, Sensors, MDPI, 2019