Module 10 · Phase 4: Localization and autonomy
Visual-Inertial SLAM & LiDAR-Inertial Integration
The hands-on side of VIO and LIO: IMU noise parameters, camera–IMU and LiDAR–IMU extrinsics, time offsets, initialization and recovery.
This overview is open. 6 of 6 guides are written; the others show Coming soon until they are complete and tested.
Questions this module answers
- How do I configure an IMU for VIO and obtain its noise parameters?
- How do I diagnose an incorrect camera–IMU calibration or a timestamp offset?
- How do I validate LiDAR–IMU calibration?
- How do I compare VIO and LIO performance?
What it covers
- IMU noise and bias, preintegration
- Feature tracking and visual odometry
- LiDAR deskewing and odometry
- Estimator initialization
- Tracking failure and recovery
Guides and design decisions
A. Engineering Guides (5)
B. Design & Selection (1)
Diagnostics, tools and challenges
C. Troubleshooting (2)
- Visual tracking is lostThe visual system reports lost tracking or reinitializes.
- Localization fails due to timestamp offsetsThe estimator diverges only when the robot rotates quickly.
E. Design challenges (1)
- Challenge 4: UAV GNSS-Denied NavigationCamera, LiDAR and IMU on a UAV: compute, calibration, VIO/LIO, estimation, flight-controller integration and failure handling.
Practical deliverables
- VIO/LIO configuration checklists
- Debugging workflows
Read first: existing FixTheRobot lessons and labs
This module builds on these instead of repeating them.
- Visual-Inertial Odometry SLAM · Lesson
- Visual-Inertial SLAM SLAM · Lesson
- Diagnose Camera–IMU Synchronization Errors SLAM · Lab