Project / 01 · 2026
LoneRoverReal-world robotics
Autonomous Ackermann Navigation System
A complete ROS 2 navigation stack for an Ackermann vehicle, connecting state estimation, planning, control, and safety on a real competition platform.
Research question
How can a constrained Ackermann platform move reliably through a structured environment when perception, planning, control, and safety must agree?
This page treats the project as a system and a research record, not as a list of technologies.
System
Method & contribution
Designed and integrated the navigation pipeline, including the wheel–IMU EKF, planner/controller configuration, Tube and RPP narrow-channel behavior, reverse-entry LUT tooling, and safety-limited command path.
- 设计并集成 wheel–IMU EKF 与导航状态估计
- 负责规划器、控制器配置及窄通道 / 逆向入口行为
- 维护安全限幅、陈旧数据处理与运行记录
- Separate planning from path tracking
- Use offline feasibility checks for constrained reverse entries
- Keep safety limits and stale-data behavior explicit
- Record runtime state for post-run diagnosis
Evidence
- Navigation pipeline deployed on a real Ackermann platform
- Replay and tuning records kept with the ROS 2 package
- Real Ackermann platform deployment
- ROS 2 package and launch structure
- Virtual/real vehicle replay tooling
- Navigation and tuning documentation
Performance remains sensitive to speed tuning, task timing, sensor calibration, and the handoff between open-area and narrow-channel controllers.