AI in Autonomous Vehicles Course

Introduction to the Course

The AI in Autonomous Vehicles course at General Motors provides an introduction to the complete self-driving pipeline from perception to planning to control by showing you how AI in self-driving cars ‘sees the road’ through computer vision, understands the motion through machine learning, and decides what to do through planning algorithms and control logic.

Program Objectives

• After completing this AI in Autonomous Vehicles Course, you will be able to:
• Familiarize yourself with the fundamental concepts of AI in autonomous vehicles and the use of autonomy stacks for self-driving cars.
• Understand how ADAS functions incorporate elements of machine learning, perception, and control.
• Developing perception models and testing them against scenarios to gain practical experience.
• Mastering the fundamentals of sensor fusion to effectively utilize multi-sensor information and derive reliable scene understanding.
• Understand planning and decision-making pipelines to transform perception outputs to safe actions.

What Will You Learn (Modules)

Module 1: Introduction to Robotics and Kinematics

• Overview of robotics: history, types, and real-world applications.
• Basic kinematics: motion, coordinate systems, and robot arm movements.
• Introduction to robot design: sensors, actuators, and control systems.
• Hands-on project: Build a basic robotic arm model and simulate simple movements.

Module 2: Robot Control Systems and Motion Planning

• Understanding control systems in robotics: PID controllers, feedback loops, and motion planning algorithms.
• How to control robotic movements with precision and accuracy.
• Explore motion planning algorithms for pathfinding and navigation.
• Hands-on project: Program a simple robot to follow a pre-defined path using a PID controller.

Module 3: AI in Robotics: Machine Learning and Computer Vision

• Introduction to AI in robotics: applying machine learning to improve robot behavior.
• Understanding computer vision: how robots perceive and interpret their environment.
• Using AI for object detection, recognition, and tracking in robotic systems.
• Hands-on project: Implement a simple computer vision algorithm to detect objects using a camera sensor.

Module 4: Autonomous Robots and Reinforcement Learning

• Introduction to autonomous robots: self-navigation, decision-making, and task execution.
• Exploring reinforcement learning for autonomous decision-making and robot training.
• Designing and simulating intelligent robots that learn from their environment.
• Hands-on project: Train a robot to navigate an environment using reinforcement learning algorithms.

Final Project

• Design and implement a robot capable of performing a specific task autonomously (e.g., obstacle avoidance, object sorting, or delivery).
• Integrate sensors and AI algorithms for real-time decision-making and autonomous control.
• Present the final project, including code implementation and simulation results.

Who Should Take This Course?

The following individuals might benefit greatly from this course:

• Professionals working in automotive, robotics, AI/ML, embedded systems, and ADAS development
• Students (UG/PG), pursuing engineering, data science, or computer science for self-driving cars-specific roles
• Researchers interested in perception, planning, safety, or sensor fusion in autonomy
• Career Changers in Autonomous Vehicle Industry and Automotive Artificial Intelligence
• Enthusiasts who want structured courses and projects in self-driving cars

Job Oppurtunities

Students who complete this curriculum will be sufficiently equipped for work positions such as:

• Upon completing this AI in Autonomous Vehicles course, you will be able to target:
• Autonomous Vehicle/ Robotics ML Engineer
• ADAS Engineer – Perception/Planning Support
• Computer Vision Engineer (Automotive)
• Sensor Fusion Engineer
• Autonomous Systems
• Simulation & Validation Engineer (Autonomy / ADAS)

Why Learn With Nanoschool?

At nanoscool, you will get expert, guided trainings in AI applications for psychological and behavioral analysis that will also give you practical and hands, on experiences. Some of the main benefits are:

• Expert, Led Training: Get knowledge from instructors who have a strong background in both AI and psychology.
• Practical & Hands, On Learning: Handle real, world datasets and AI tools that are being used in the field of psychology and behavioral research.
• Industry Relevance: Keep abreast of changes with a curriculum that incorporates the latest discoveries in using AI for behavioral analysis and therapy.
• Career Support: Get career counselling and job placement services that will facilitate your professional growth in AI and psychology.

Key outcomes of the course

After completing the AI in Autonomous Vehicles course, you will:

• Build a strong and practical foundation in AI in Autonomous Vehicles and Autonomous Stack Thinking.
• Understand the way self-driving cars perform perception, prediction, and decisions in actual scenarios
• Familiarization with ADAS Pipelines and the Role of AI in Driver Assistance Systems
• Gain core sensor fusion intuition to enhance the robustness of the system with the integration of various multi-sensor data
• Produce project outcomes to demonstrate in your application for an autonomous systems engineer, ADAS engineer, or other car-based artificial intelligence jobs