Sensor Fusion

Sensors: Learn how lidar and radar work.

• Kalman Filter:
  Use probability distributions to fuse lidar and radar data together.
• C++ Tutorial:
  Review the key C++ concepts for implementing the Term 2 projects.
• Kalman Filter in C++:
  Build high performance filters.
• Project: Pedestrian Tracking
  

Fuse sanitized lidar and radar data together to track a pedestrian.

• Unscented Kalman Filter:
  Fuse sensor nonlinear measurements.
• Project: Pedestrian Tracking

Fuse real-world lidar and radar data together to track a pedestrian.

Localization

• Motion: Study
  how motion and probability affect your belief about where you are in the world.
• Markov Localization:
  Use a Bayesian filter to localize the vehicle.
• Bayesian Filter:
  Implement a Bayesian filter for localization.
• Egomotion:
  Estimate the position of the car over time given different sensor data.
• Sampling for Localization:
  Use a particle filter to localize the vehicle.
• Particle Filter:
  Implement a particle filter in C++.
• Project: Kidnapped Vehicle

Implement a particle filter to take real-world data and localize a lost vehicle.

Control

• Stability:
  Investigate the properties of stable and unstable systems.
• Open-Loop Control:
  Implement a controller in which the actuation is independent of the controller output.
• Closed-Loop Control:
  Implement a controller in which the actuation is dependent on the controller output.
• PID Controller:
  Implement a Proportional-Integral-Derivative controller.
• Linear Quadratic
  Regulator: Optimize the PID controller using a quadratic system of equations.
• Project: Lane-Keeping

Implement a controller to overcome disturbances and keep a simulated vehicle in its path.

• Vehicle control
  Kinematic and dynamic vehicle models.
• Model predictive control
  Frame the control problem as an optimization problem over time horizons.
• Project: Model predictive control

Drive the vehicle around the track even with the additional latency between commands!