In the context of robotics in general, "autonomous" refers to the ability of a robot to operate without the intervention of a human operator. And the same definition applies to autonomous driving i.e. the ability of a vehicle to drive itself without the intervention of a human.
This is an introductory course to autonomous driving. It covers different techniques and sub-systems needed to endow vehicles with autonomy. This includes the ability of a vehicle to perceive its environment, map its environment and localize itself within a map, plan its motion in its environment, execute that motion smoothly, as well as detect, model and predict behavior of other agents present in its environment.
Upon completion of the course, a student will be able to:
- Implement map-based localization using particle filtering
- Implement SLAM on simulated exteroceptive and proprioceptive data
- Explain different planning strategies for robot motion planning
- Implement a control strategy for lateral position control
- Describe challenges in behavior modelling in autonomous driving
- Understand the pros and cons of different exteroceptive sensing systems used in autonomous driving
- Understand the steps involved in employing a sensing system
Topics covered in the course
- Simultaneous localization and mapping
- Motion planning
- Sensing and perception
- Sensor fusion
- Interaction and behavior modelling
- End-to-end approaches
Course evaluation/grading is based on weekly lab assignments (delivered in the form of reports and code) and three oral exams.
Naveed Muhammad (email@example.com)