AI in Autonomous Vehicles

The program delves into the AI and robotics techniques that empower autonomous vehicles, including computer vision, object detection, sensor fusion from LIDAR and radar, and motion planning algorithms. This hands-on course also covers real-world challenges like obstacle avoidance, lane detection, and decision-making for AVs.

• Learn the core AI technologies that enable self-driving vehicles.
• Master sensor fusion, perception, and motion planning for AVs.
• Understand computer vision techniques for road and object detection.
• Implement real-time decision-making with reinforcement learning.
• Gain hands-on experience in building an AI-driven autonomous vehicle system.

1. Introduction to Autonomous Vehicles and AI
   • Overview of Autonomous Vehicle Levels (SAE Levels 0-5)
   • Role of AI in Autonomous Driving
   • Use Cases and Applications (Self-Driving Cars, Drones, Delivery Robots)
2. Sensors and Perception in Autonomous Vehicles
   • Types of Sensors: LIDAR, Radar, Cameras, Ultrasonics
   • Sensor Fusion for Accurate Environment Perception
   • AI for Perception: Object Detection, Lane Detection, and Segmentation
3. Computer Vision in Autonomous Driving
   • Basics of Computer Vision for Autonomous Vehicles
   • Deep Learning Techniques for Object Detection (YOLO, SSD)
   • Real-Time Image Processing for Vehicle Cameras
4. Localization and Mapping
   • Simultaneous Localization and Mapping (SLAM)
   • GPS, IMU, and Dead Reckoning for Vehicle Localization
   • AI Techniques for Accurate Mapping (Visual SLAM, Particle Filters)
5. Path Planning and Motion Control
   • Path Planning Algorithms (Dijkstra, A*, RRT)
   • AI-Based Path Planning: Reinforcement Learning for Autonomous Navigation
   • Motion Control Techniques (PID, MPC) for Smooth Driving
6. Deep Learning for Autonomous Vehicles
   • Neural Networks for Perception and Decision-Making
   • Convolutional Neural Networks (CNNs) for Image Processing
   • Recurrent Neural Networks (RNNs) for Sequential Data (Sensor Data)
7. Reinforcement Learning in Autonomous Driving
   • Fundamentals of Reinforcement Learning (Q-Learning, Policy Gradient)
   • Applying RL to Decision-Making in Autonomous Vehicles
   • Case Studies: Self-Learning Driving Agents
8. Vehicle-to-Everything (V2X) Communication
   • Communication between Vehicles (V2V), Infrastructure (V2I), and Networks (V2N)
   • AI for Optimizing V2X Communication
   • Safety and Traffic Management through AI-Driven V2X Systems
9. Autonomous Vehicle Software Architecture
   • Overview of Autonomous Driving Stacks (Apollo, Autoware)
   • ROS (Robot Operating System) for Autonomous Vehicles
   • AI Integration into Autonomous Vehicle Software Pipelines
10. Simulation and Testing of Autonomous Vehicles
    • Virtual Environments for Testing Autonomous Vehicles (CARLA, AirSim)
    • AI for Simulation-Based Testing and Validation
    • Reinforcement Learning for Simulated Driving Scenarios
11. Safety, Ethics, and Regulations in Autonomous Driving
    • AI for Safety-Critical Systems in Autonomous Vehicles
    • Ethical Considerations in AI-Driven Decision Making
    • Legal and Regulatory Framework for Autonomous Vehicles