pb2025_sentry_nav

深圳北理莫斯科大学 北极熊战队 2025 赛季哨兵导航仿真/实车包

BiliBili: 谁说在家不能调车！？更适合新手宝宝的 RM 导航仿真

https://github.com/user-attachments/assets/d9e778e0-fa43-40c2-96c2-e71eaf7737d4

https://github.com/user-attachments/assets/ae4c19a0-4c73-46a0-95bd-909734da2a42

1. Overview

本项目基于 NAV2 导航框架 并参考学习了 autonomous_exploration_development_environment 的设计。

• 关于坐标变换：

  本项目大幅优化了坐标变换逻辑，考虑雷达原点 lidar_odom 与 底盘原点 odom 之间的隐式变换。

  mid360 倾斜侧放在底盘上，使用 point_lio 里程计，small_gicp 重定位，loam_interface 会将 point_lio 输出的 /cloud_registered 从 lidar_odom 系转换到 odom 系，sensor_scan_generation 将 odom 系的点云转换到 front_mid360 系，并发布变换 odom -> chassis。

  

• 关于路径规划：

  使用 NAV2 默认的 Global Planner 作为全局路径规划器，pb_omni_pid_pursuit_controller 作为路径跟踪器。

• namespace：

  为了后续拓展多机器人，本项目引入 namespace 的设计，与 ROS 相关的 node, topic, action 等都加入了 namespace 前缀。如需查看 tf tree，请使用命令 ros2 run rqt_tf_tree rqt_tf_tree --ros-args -r /tf:=tf -r /tf_static:=tf_static -r __ns:=/red_standard_robot1

• LiDAR:

  Livox mid360 倾斜侧放在底盘上。

  注：仿真环境中，实际上 point pattern 为 velodyne 样式的机械式扫描。此外，由于仿真器中输出的 PointCloud 缺少部分 field，导致 point_lio 无法正常估计状态，故仿真器输出的点云经过 ign_sim_pointcloud_tool 处理添加 time field。

• 文件结构

    .
    ├── fake_vel_transform                  # 虚拟速度参考坐标系，以应对云台扫描模式自旋，详见子仓库 README
    ├── ign_sim_pointcloud_tool             # 仿真器点云处理工具
    ├── livox_ros_driver2                   # Livox 驱动
    ├── loam_interface                      # point_lio 等里程计算法接口
    ├── pb_teleop_twist_joy                 # 手柄控制
    ├── pb2025_nav_bringup                  # 启动文件
    ├── pb2025_sentry_nav                   # 本仓库功能包描述文件
    ├── pb_omni_pid_pursuit_controller      # 路径跟踪控制器
    ├── point_lio                           # 里程计
    ├── pointcloud_to_laserscan             # 将 terrain_map 转换为 laserScan 类型以表示障碍物（仅 SLAM 模式启动）
    ├── sensor_scan_generation              # 点云相关坐标变换
    ├── small_gicp_relocalization           # 重定位
    └── terrain_analysis                    # 分割出非地面障碍物点云
    

2. Quick Start

2.1 Option 1: Docker

2.1.1 Setup Environment

• Docker

• 允许 Docker Container 访问宿主机 X11 显示

    xhost +local:docker
    

2.1.2 Create Container

docker run -it --rm --name pb2025_sentry_nav \
  --network host \
  -e "DISPLAY=$DISPLAY" \
  -v /tmp/.X11-unix:/tmp/.X11-unix \
  -v /dev:/dev \
  ghcr.io/smbu-polarbear-robotics-team/pb2025_sentry_nav:1.3.0

2.2 Option 2: Build From Source

2.2.1 Setup Environment

• Ubuntu 22.04
• ROS: Humble
• 配套仿真包（Option）：rmu_gazebo_simulator
• Install small_icp:

    sudo apt install -y libeigen3-dev libomp-dev

    git clone https://github.com/koide3/small_gicp.git
    cd small_gicp
    mkdir build && cd build
    cmake .. -DCMAKE_BUILD_TYPE=Release && make -j
    sudo make install
    

2.2.2 Create Workspace

mkdir -p ~/ros_ws
cd ~/ros_ws

git clone --recursive https://github.com/SMBU-PolarBear-Robotics-Team/pb2025_sentry_nav.git src/pb2025_sentry_nav

下载先验点云:

先验点云用于 point_lio 和 small_gicp，由于点云文件体积较大，故不存储在 git 中，请前往 FlowUs 下载。

当前 point_lio with prior_pcd 在大场景的效果并不好，比不带先验点云更容易飘，待 Debug 优化

2.2.3 Build

rosdep install -r --from-paths src --ignore-src --rosdistro $ROS_DISTRO -y

colcon build --symlink-install --cmake-args -DCMAKE_BUILD_TYPE=Release

[!NOTE] 推荐使用 –symlink-install 选项来构建你的工作空间，因为 pb2025_sentry_nav 广泛使用了 launch.py 文件和 YAML 文件。这个构建参数会为那些非编译的源文件使用符号链接，这意味着当你调整参数文件时，不需要反复重建，只需要重新启动即可。

2.3 Running

可使用以下命令启动，在 RViz 中使用 Nav2 Goal 插件发布目标点。

2.3.1 仿真

单机器人：

导航模式：

ros2 launch pb2025_nav_bringup rm_navigation_simulation_launch.py \
world:=rmuc_2025 \
slam:=False

建图模式：

ros2 launch pb2025_nav_bringup rm_navigation_simulation_launch.py \
slam:=True

保存栅格地图：ros2 run nav2_map_server map_saver_cli -f <YOUR_MAP_NAME> --ros-args -r __ns:=/red_standard_robot1

多机器人 (实验性功能) :

当前指定的初始位姿实际上是无效的。TODO: 加入 map -> odom 的变换和初始化

ros2 launch pb2025_nav_bringup rm_multi_navigation_simulation_launch.py \
world:=rmul_2024 \
robots:=" \
red_standard_robot1={x: 0.0, y: 0.0, yaw: 0.0}; \
blue_standard_robot1={x: 5.6, y: 1.4, yaw: 3.14}; \
"

2.3.2 实车

建图模式：

ros2 launch pb2025_nav_bringup rm_navigation_reality_launch.py \
slam:=True \
use_robot_state_pub:=True

保存栅格地图：ros2 run nav2_map_server map_saver_cli -f <YOUR_MAP_NAME> --ros-args -r __ns:=/red_standard_robot1

导航模式：

注意修改 world 参数为实际地图的名称

ros2 launch pb2025_nav_bringup rm_navigation_reality_launch.py \
world:=<YOUR_WORLD_NAME> \
slam:=False \
use_robot_state_pub:=True

2.4 Launch Arguments

启动参数在仿真和实车中大部分是通用的。以下是所有启动参数表格的图例。

[!TIP] 关于本项目更多细节与实车部署指南，请前往 Wiki

2.5 手柄控制

默认情况下，PS4 手柄控制已开启。键位映射关系详见 nav2_params.yaml 中的 teleop_twist_joy_node 部分。

Contributing Guidelines

Thank you for your interest in contributing to pb2025_sentry_nav. Whether it’s a bug report, new feature, correction, or additional documentation, we greatly value feedback and contributions from our community.

Please read through this document before submitting any issues or pull requests to ensure we have all the necessary information to effectively respond to your bug report or contribution.

Reporting Bugs/Feature Requests

We welcome you to use the GitHub issue tracker to report bugs or suggest features.

When filing an issue, please check existing open, or recently closed, issues to make sure somebody else hasn’t already reported the issue. Please try to include as much information as you can. Details like these are incredibly useful:

• A reproducible test case or series of steps
• The version of our code being used
• Any modifications you’ve made relevant to the bug
• Anything unusual about your environment or deployment

Contributing via Pull Requests

To send us a pull request, please:

1. Fork the repository.
2. Modify the source; please focus on the specific change you are contributing. If you also reformat all the code, it will be hard for us to focus on your change.
3. Ensure local tests pass. (colcon test and pre-commit run (requires you to install pre-commit by pip3 install pre-commit)
4. Commit to your fork using clear commit messages.
5. Send a pull request, answering any default questions in the pull request interface.
6. Pay attention to any automated CI failures reported in the pull request, and stay involved in the conversation.

GitHub provides additional documentation on forking a repository and creating a pull request.

Finding contributions to work on

Looking at the existing issues is a great way to find something to contribute on. As this project, by default, uses the default GitHub issue labels (enhancement/bug/duplicate/help wanted/invalid/question/wontfix), looking at any ‘help wanted’ issues is a great place to start.

Licensing

Any contribution that you make to this repository will be under the Apache 2 License, as dictated by that license:

5. Submission of Contributions. Unless You explicitly state otherwise,
   any Contribution intentionally submitted for inclusion in the Work
   by You to the Licensor shall be under the terms and conditions of
   this License, without any additional terms or conditions.
   Notwithstanding the above, nothing herein shall supersede or modify
   the terms of any separate license agreement you may have executed
   with Licensor regarding such Contributions.