kolinguo/maplab repository overview

Container for launching and configuring maplab⁠, which is a visual-inertial SLAM supporting RGB-D+IMU mapping.
This docker image has Ubuntu 18.04, CUDA 11.3.1, ROS Melodic, OpenCV 4.4.0, librealsense⁠, realsense-ros⁠.

⁠Build & compile codebase

1. ./docker_setup.sh maplab to pull the docker image and build the container.
2. cd slam_algorithms/maplab && ./build_ros.sh to compile the packages.

⁠Running

Run ./slam_algorithms/maplab/run_maplab.sh <bag-name> to start the camera tracking. It accepts a <bag-name> argument which will record and save the rosbag as /maya-slam/slam_algorithms/rosbags/d435i_{bag-name}_{TIMESTAMP}.bag

The script will launch the launch file realsense.launch⁠. It will run maplab by calling run_realsense⁠, display the trajectory in RVIZ and also record color/depth/imu/camera pose trajectory generated by maplab as topics into a rosbag. The RealSense camera parameters can be modified in realsense-camera.yaml⁠ and realsense-imu.yaml⁠.

Remember to update the camera parameters for your RealSense camera