Sensor Fusion for Robotics
ECE 411/511

The course discusses sensing techniques and methods of data fusion for robotics applications. Topics include active and passive sensors, data filtering, deterministic and probabilistic data fusion methods.

    1. Fundamentals
      1. Introduction
      2. Review of probability
      3. Maximum likelihood estimation
      4. Maximum a posteriori estimation
      5. Complementary filter
      6. Image recognition
      7. Pose estimation using GPS and IMU
      8. Object tracking
    2. Modeling
      1. Coordinates and transformations
      2. Velocity-based motion model
      3. Odometry-based motion model
      4. Sensor models
      5. Radar
    3. Bayesian Filtering
      1. Bayes filter
      2. Discrete and histogram filters
      3. Grid localization
      4. Occupancy grid mapping
      5. Maximum a posteriori occupancy grid mapping
      6. Kalman filter
      7. Extended Kalman filter
      8. Information filter
      9. Particle filter and Monte Carlo localization
    4. Graph SLAM
      1. Graph SLAM
      2. Linear least squares
      3. Nonlinear least squares