Autonomous Vehicle Course

Lesson 1 • SAE Autonomy Levels Explained

Defines the six levels of driving automation and their operational boundaries. Provides the classification vocabulary used throughout the entire course.

Lesson 2 • History and Evolution of Autonomous Vehicles

Traces AV development from early cruise control to modern self-driving prototypes. Establishes the technological timeline that contextualizes all subsequent chapters.

Lesson 3 • AV System Architecture Basics

Introduces the modular pipeline from perception to actuation. Students gain a mental model for how subsystems interact within a complete AV stack.

Lesson 1 • Ultrasonic and Infrared Sensors

Examines close-range sensing technologies used for parking, low-speed maneuvering, and pedestrian detection. Rounds out the full sensor suite introduced in Chapter 1.

Lesson 2 • Camera Systems and Visual Perception

Addresses monocular, stereo, and surround-view camera configurations and their calibration. Provides the visual data foundation for the deep-learning perception models in Chapter 3.

Lesson 3 • Sensor Fusion Fundamentals

Introduces probabilistic methods for combining heterogeneous sensor data into a unified environment model. Prepares students for the advanced perception algorithms in Chapter 3.

Lesson 4 • LiDAR Technology and Applications

Explains LiDAR operating principles, point-cloud generation, and range limitations. Directly supports perception module design covered in Chapter 3.

Lesson 1 • Multi-Object Tracking

Addresses data association, track initialization, and trajectory estimation across frames. Enables the AV to maintain consistent object identities over time.

Lesson 2 • Occupancy Grids and Scene Representation

Introduces probabilistic occupancy grids and dynamic scene graphs as compact environment representations. Provides the data structures consumed by motion planning in Chapter 4.

Lesson 3 • Semantic and Instance Segmentation

Teaches pixel-level scene labeling for road surfaces, lanes, and obstacles. Provides fine-grained environment understanding needed for precise path planning.

Lesson 4 • Object Detection with Deep Learning

Covers convolutional neural network architectures for 2D and 3D object detection. Directly uses sensor data from Chapter 2 to produce structured scene understanding.

Lesson 1 • Route and Mission Planning

Covers graph-based global route planning using road network data. Sets the high-level navigation goal that constrains all lower-level planning layers.

Lesson 2 • Behavioral Planning and Scenario Handling

Addresses finite state machines and rule-based systems for intersection, merge, and lane-change decisions. Translates traffic rules into executable vehicle behaviors.

Lesson 3 • Prediction of Agent Behavior

Models the future motion of pedestrians, cyclists, and other vehicles to enable proactive planning. Reduces uncertainty in the planner's decision horizon.

Lesson 4 • Local Trajectory Planning

Teaches sampling-based and optimization-based methods for generating smooth, collision-free local paths. Produces the reference trajectory consumed by the vehicle controller.

Lesson 1 • Lateral Control and Steering

Addresses pure pursuit, Stanley, and MPC-based steering controllers for path tracking. Ensures the vehicle follows the reference trajectory from the planning module.

Lesson 2 • Vehicle Dynamics Fundamentals

Reviews tire models, bicycle model kinematics, and dynamic force interactions. Provides the physics foundation required for designing accurate controllers.

Lesson 3 • Longitudinal Control Design

Covers PID and model-predictive control for speed regulation and adaptive cruise functions. Directly applies vehicle dynamics knowledge to throttle and brake actuation.

Lesson 4 • Controller Validation and Testing

Introduces hardware-in-the-loop and software-in-the-loop testing frameworks for controller verification. Connects control design to the safety validation methods in Chapter 7.

Lesson 1 • Fault Detection and Degraded Modes

Covers diagnostic monitoring, fault isolation, and graceful degradation strategies for AV subsystems. Ensures the vehicle can reach a minimal-risk condition upon failure.

Lesson 2 • Functional Safety Standards for AVs

Explains automotive functional safety frameworks, hazard analysis, and safety integrity levels. Establishes the regulatory and engineering baseline for all safety activities.

Lesson 3 • AV Cybersecurity Threat Modeling

Introduces attack surface analysis, threat enumeration, and risk prioritization for connected AV systems. Addresses the unique cyber-physical risks not present in traditional vehicles.

Lesson 4 • Secure Communication and Data Protection

Covers cryptographic protocols, secure boot, and over-the-air update security for AV platforms. Protects the integrity of sensor data and software throughout the vehicle lifecycle.

Lesson 1 • AV Simulation Platform Overview

Surveys leading simulation environments, their physics fidelity, and sensor modeling capabilities. Provides the tooling context for all simulation-based exercises in this chapter.

Lesson 2 • Continuous Integration for AV Software

Introduces automated regression testing, nightly simulation runs, and performance dashboards for AV stacks. Supports rapid iteration while maintaining safety standards.

Lesson 3 • Closed-Course and Public Road Testing

Covers structured test track protocols and phased public road deployment strategies. Bridges simulation results to real-world performance evidence.

Lesson 4 • Sim-to-Real Transfer Challenges

Addresses the domain gap between simulated and real-world sensor data and vehicle behavior. Equips students to design experiments that minimize transfer errors.

Lesson 1 • Operational Design Domain Definition

Defines the environmental, geographic, and traffic conditions within which an AV is authorized to operate. Establishes the deployment boundaries that constrain all operational decisions.

Lesson 2 • Remote Monitoring and Teleoperation

Covers real-time fleet monitoring dashboards, alert systems, and remote intervention capabilities. Enables operators to maintain oversight and assist vehicles in edge cases.

Lesson 3 • Data Management and Continuous Learning

Addresses fleet data pipelines, edge-case mining, and model retraining workflows for ongoing improvement. Closes the loop between real-world operation and software development.

Lesson 4 • Incident Response and Investigation

Establishes protocols for detecting, responding to, and investigating AV incidents and near-misses. Ensures systematic learning from failures to prevent recurrence.