S2MAT

S2MAT: Simultaneous and Self-Reinforced Mapping and Tracking in Dynamic Urban Scenarios

Project Page

Installation

1. Install Dependencies

   • ROS (Robot Operating System): Follow the official ROS installation guide for your operating system. Make sure to install the version compatible with your system.

   • CMake: Install CMake using your package manager. For example, on Ubuntu:

     sudo apt-get update
     sudo apt-get install cmake

   • PCL (Point Cloud Library): Install PCL using the following command:

     sudo apt-get install libpcl-dev

   • OpenCV: Install OpenCV using the following command:

     sudo apt-get install libopencv-dev

   • Eigen3: Install Eigen3 using the following command:

     sudo apt-get install libeigen3-dev

   • Octomap: Install Octomap using the following command:

     sudo apt-get install ros-<ros-distro>-octomap

     Replace <ros-distro> with your ROS distribution, e.g., melodic, noetic.

   • OpenMP: OpenMP is typically included with the GCC compiler. Ensure you have GCC installed:

     sudo apt-get install build-essential

   • ROS Packages: Use rosdep to install any additional ROS package dependencies:

     rosdep install --from-paths src --ignore-src -r -y

2. Clone the Repository

   Clone this repository to your local machine:

   git clone <repository-url>
   cd s2mat

3. Build the Project

   Use catkin_make to build the project:

   catkin_make DCMAKE_BUILD_TYPE=Release

TODO List

• Open source the perception code used in the real-world navigation experiment.
• Open source the simulation dataset.
• Add installation and running instructions for the code.
• Open source all code after the paper is accepted.