Self-Driving Cars Specialization - Notes

Overview

Notes and assignements of Self-Driving Cars Specialization course offered by Faculty of Appied Science and Engineering of University of Toronto on Coursera.

What you will learn?

1. Understand the detailed architecture and components of a self-driving car software stack
2. Implement methods for static and dynamic object detection, localization and mapping, behaviour and maneuver planning, and vehicle control
3. Use realistic vehicle physics, complete sensor suite: camera, LIDAR, GPS/INS, wheel odometry, depth map, semantic segmentation, object bounding boxes
4. Demonstrate skills in CARLA and build programs with Python

Prerequisites

• List of prerequisites available here.

Specialization Outline

Courses	Modules	Chapters
Course1 - Introduction to Self-Driving Cars	- Module 0: Welcome to the Self-Driving Cars Specialization - Module 1: The Requirements for Autonomy - Module 2: Self-Driving Hardware and Software Architectures - Module 3: Safety Assurance for Autonomous Vehicles - Module 4: Vehicle Dynamic Modeling - Module 5: Vehicle Longitudinal Control - Module 6: Vehicle Lateral Control - Module 7: Putting it all together	- course1-w1-notes.md - course1-w2-notes.md - course1-w3-notes.md - course1-w4-notes.md - course1-w5-notes.md - course1-w6-notes.md - course1-w7-notes.md
Course2 - State Estimation and Localization for Self-Driving Cars	- Module 0: Welcome to Course 2: State Estimation and Localization for - Self-Driving Cars - Module 1: Least Squares - Module 2: State Estimation - Linear and Nonlinear Kalman Filters - Module 3: GNSS/INS Sensing for Pose Estimation - Module 4: LIDAR Sensing - Module 5: Putting It together - An Autonomous Vehicle State Estimator	- course2-w1-notes.md - course2-w2-notes.md - course2-w3-notes.md - course2-w4-notes.md - course2-w5-notes.md
Course3 - Visual Perception for Self-Driving Cars	- Module 0: Welcome to Course 3: Visual Perception for Self-Driving Cars - Module 1: Basics of 3D Computer Vision - Module 2: Visual Features - Detection, Description and Matching - Module 3: Feedforward Neural Networks - Module 4: 2D Object Detection - Module 5: Semantic Segmentation - Module 6: Putting it together - Perception of dynamic objects in the drivable region	- course3-w1-notes.md - course3-w2-notes.md - course3-w3-notes.md - course3-w4-notes.md - course3-w5-notes.md - course3-w6-notes.md
Course4 - Motion Planning for Self-Driving Cars	- Module 0: Welcome to Course 4: Motion Planning for Self-Driving Cars - Module 1: The Planning Problem - Module 2: Mapping for Planning - Module 3: Mission Planning in Driving Environments - Module 4: Dynamic Object Interactions - Module 5: Principles of Behaviour Planning - Module 6: Reactive Planning in Static Environments - Module 7: Putting it all together - Smooth Local Planning	- course4-w1-notes.md - course4-w2-notes.md - course4-w3-notes.md - course4-w4-notes.md - course4-w5-notes.md - course4-w6-notes.md - course4-w7-notes.md

Final Project & Career

You’ll learn from a highly realistic driving environment that features 3D pedestrian modelling and environmental conditions. When you complete the Specialization successfully, you’ll be able to build your own self-driving software stack and be ready to apply for jobs in the autonomous vehicle industry.

References

• Main course - Coursera
• I wrote a blog review, you can check it out here.
• I curated an awesome spreadsheet of prerequisites for the course, see here.
• All projects here!
• My Certificate :) - Good Luck, You can do it too!.

Others:

• TRAIL (Formerly WAVELab) - The Toronto Robotics and AI Laboratory
• U of T - AutoDrive Team
• WISE Lab - Waterloo Intelligent Systems Engineering Lab
  • Solutions & Projects:
    • SW: WISE Automated Driving System (ADS)
      • Stack:
        • Perception
        • Planning
        • Control
        • OS: Operating System and Middleware
        • Programming languages: C++ 17 and Python 3 with the exception of the Rule Engine, which is implemented as a NodeJS REST service.
    • HW: UW Moose (Autonomoose) - Self-Driving Research Platform
      • University of Waterloo Autonomous Driving with Autonomoose - Team (2016-2019)
      • Sensor drivers
      • Actuators
    • Sim: Wise sim
• More Automotive solutions:
  • WatCAR - The Waterloo Centre for Automotive Research
  • AVRIL - Autonomous Vehicle Research and Intelligence Lab

"Self-driving cars are the natural extension of active safety and obviously something we should do." — Elon Musk