Course

Unit 1

Perception Systems in Autonomous Driving: Introduction to Autonomous Driving Perception – Overview of autonomous driving, Importance of perception systems, Key sensors: Cameras, LIDAR, RADAR, Ultrasonic Introduction to Multi-Sensor Data Fusion (MSDF) Algorithms – Applications in autonomous vehicles, Overview of Simultaneous Localization and Mapping (SLAM) – Visual SLAM and LIDAR-based SLAM, – Free Space Detection and Identification – Algorithms for free space detection, Applications in navigation and path planning.

Unit 2

Control Systems for Autonomous Driving: Introduction to vehicle dynamics, Longitudinal and lateral control, Modeling vehicle dynamics – Control Algorithms. Applications in autonomous vehicles – Introduction to AI-based control, Machine learning and reinforcement learning for control, Case studies and applications – Integrated Control Systems – Combining traditional and AI-based control methods, Challenges and solutions. Advanced Control Techniques Future trends in vehicle control.

Unit 3

Data-Driven Development for Autonomous: Data Collection and Management – Synchronizing data collection from multiple sensors, Event-based data collection, Data ingestion and storage – Data Processing and Analytics – Pre-processing techniques, Data analysis for autonomous driving, Virtualization in Autonomous Vehicle Development – Role of virtualization, Tools and techniques, Benefits and challenges – Case Studies and Future Directions

Text Books / References

Reference (s)

1. Shaoshan Liu, Liyun Li, and Jie Tang, Machine Learning for Autonomous Vehicles, Springer, 2022.
2. Sebastian Thrun, Wolfram Burgard, and Dieter Fox, Probabilistic Robotics, MIT press, 2006.
3. Rajesh Rajamani, Vehicle Dynamics and Control, Springer, 2012.
4. Steven L. Brunton and J. Nathan Kutz, Data-Driven Science and Engineering, Cambridge University Press, 2019.

Course Objectives

• To introduce advanced perception algorithms, multi-sensor data fusion techniques for autonomous vehicle navigation and environment.
• To provide knowledge on master vehicle dynamics control through PI-PID and AI-based methods for longitudinal and lateral vehicle control.
• To develop proficiency in data-driven development practices for autonomous vehicle systems.

Course Outcomes:

• CO01: implement data fusion and path planning algorithms for autonomous vehicles.
• CO02: implement vehicle dynamics modeling and control using PI-PID, AI-based methods
• CO03: development data-driven systems, data collection to CI/CD
• CO04: create systems for real-world challenges in autonomous driving

CO-PO Mapping

Skills Acquired: Perception algorithms, Optimization of Autonomous systems, Multi-Sensor Data fusion