Sensor Fusion and State Estimation

Lessons (16)

1. M3-T1Probability and uncertainty in roboticsLesson
2. M3-T2Gaussian distributions and covarianceLesson
3. M3-T3Bayesian estimationLesson
4. M3-T4Kalman FilterLesson
5. M3-T5Extended Kalman FilterLesson
6. M3-T6Error-State Kalman FilterLesson
7. M3-T7IMU noise and bias modellingLesson
8. M3-T8IMU preintegrationLesson
9. M3-T9Camera-IMU fusionLesson
10. M3-T10LiDAR-IMU fusionLesson
11. M3-T11Multi-sensor fusion architecturesLesson
12. M3-T12Observability and consistencyLesson
13. M3-T13Innovation monitoringLesson
14. M3-T14Normalized Innovation SquaredLesson
15. M3-T15Normalized Estimation Error SquaredLesson
16. M3-T16Sensor fault detection and isolationLesson

Practical laboratories (6)

1. M3-L1Implement a Kalman Filter in PythonGuided lab
2. M3-L2Implement an EKFInteractive simulation
3. M3-L3Fuse IMU and visual odometryInteractive simulation
4. M3-L4Implement a basic IMU-LiDAR estimation pipelineInteractive simulation
5. M3-L5Analyze covariance and driftInteractive simulation
6. M3-L6Detect faulty sensor measurementsInteractive simulation

Used in capstones

• Capstone 1: Vision-Aided Autonomous UAV
• Capstone 2: LiDAR-Inertial GNSS-Denied UAV
• Capstone 4: Complete GNSS-Denied Autonomous UAV