Introduction to Self-Driving Cars from Coursera

Welcome to Introduction to Self-Driving Cars, the first course in University of Toronto’s Self-Driving Cars Specialization.

This course will introduce you to the terminology, design considerations and safety assessment of self-driving cars. By the end of this course, you will be able to:

- Understand commonly used hardware used for self-driving cars

- Identify the main components of the self-driving software stack

- Program vehicle modelling and control

- Analyze the safety frameworks and current industry practices for vehicle development

For the final project in this course, you will develop control code to navigate a self-driving car around a racetrack in the CARLA simulation environment. You will construct longitudinal and lateral dynamic models for a vehicle and create controllers that regulate speed and path tracking performance using Python. You’ll test the limits of your control design and learn the challenges inherent in driving at the limit of vehicle performance.

This is an advanced course, intended for learners with a background in mechanical engineering, computer and electrical engineering, or robotics. To succeed in this course, you should have programming experience in Python 3.0, familiarity with Linear Algebra (matrices, vectors, matrix multiplication, rank, Eigenvalues and vectors and inverses), Statistics (Gaussian probability distributions), Calculus and Physics (forces, moments, inertia, Newton's Laws).

You will also need certain hardware and software specifications in order to effectively run the CARLA simulator: Windows 7 64-bit (or later) or Ubuntu 16.04 (or later), Quad-core Intel or AMD processor (2.5 GHz or faster), NVIDIA GeForce 470 GTX or AMD Radeon 6870 HD series card or higher, 8 GB RAM, and OpenGL 3 or greater (for Linux computers).

What's inside

Syllabus

Module 0: Welcome to the Self-Driving Cars Specialization!

This module will introduce you to the main concepts and layout of the specialization and discusses the major advances made in the field over the last two decades, highlighting the most recent progress made by major players in terms of safety and performance metrics, where available.

Module 1: The Requirements for Autonomy

Self-driving cars present an extremely rich and inter-disciplinary problem. This module introduces the language and structure of the problem definition, defining the most salient elements of the driving task and the driving environment.

Module 2: Self-Driving Hardware and Software Architectures

System architectures for self-driving vehicles are extremely diverse, as no standardized solution has yet emerged. This module describes both the hardware and software architectures commonly used and some of the tradeoffs in terms of cost, reliability, performance and complexity that constrain autonomous vehicle design.

Module 3: Safety Assurance for Autonomous Vehicles

As the self-driving domain matures, the requirement for safety assurance on public roads become more critical to self-driving developers. You will evaluate the challenges and approaches employed to date to tackle the immense challenge of assuring the safe operation of autonomous vehicles in an uncontrolled public road driving environment.

Module 4: Vehicle Dynamic Modeling

The first task for automating an driverless vehicle is to define a model for how the vehicle moves given steering, throttle and brake commands. This module progresses through a sequence of increasing fidelity physics-based models that are used to design vehicle controllers and motion planners that adhere to the limits of vehicle capabilities.

Module 5: Vehicle Longitudinal Control

Longitudinal control of an autonomous vehicle involves tracking a speed profile along a fixed path, and can be achieved with reasonable accuracy using classic control techniques. This week, you will learn how to develop a baseline controller that is applicable for a significant subset of driving conditions, which include most non-evasive or highly-dynamic motions.

Module 6: Vehicle Lateral Control

This week, you will learn about how lateral vehicle control ensures that a fixed path through the environment is tracked accurately. You will see how to define geometry of the path following control problem and develop both a simple geometric control and a dynamic model predictive control approach.

Module 7: Putting it all together

For the last week of the course, now you will get hands on with a simulation of an autonomous vehicle that requires longitudinal and lateral vehicle control design to track a predefined path along a racetrack with a given speed profile. You are encouraged to modify the speed profile and/or path to improve their lap time, without any requirement to do so. Work and play!

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Explores self-driving technology, which is standard in the industry

Teaches safety frameworks, which helps learners evaluate the safety of self-driving cars

Develops programming skills in Python, which is a core skill for robotics

Taught by Jonathan Kelly and Steven Waslander, who are recognized for their work in robotics

Examines hardware and software architectures, which is highly relevant to self-driving cars

Requires programming experience, which may limit accessibility for some learners

Reviews summary

Driven by data: an autonomous future

According to students, 'Introduction to Self-Driving Cars' is a well received course that explores various aspects of autonomous vehicles, providing a strong foundation for those interested in the industry. Learners say the lectures are engaging and the programming assignments are challenging but instructive. The course covers topics such as safety, control systems, and hardware stacks, and provides a hands-on experience in developing and controlling a self-driving car using the CARLA simulator. Overall, it is highly recommended for anyone seeking a comprehensive introduction to the field of autonomous driving.

The programming assignments and quizzes test students' understanding of the material and require critical thinking.

"For me, I had to read on the side (books, internet searches, and Youtube) to understand each module better in order to be able to pass the quizzes and complete the programming assignments."

"the programming assignments are quite tricky and the explanations are not really godd enough to understand the framework (e.g. unprecise definition of the waypoints array, the coordinate system, etc.) without spending extra effort on this."

"The programming assignments are well thought out, and combined with the course materials, the learning was very effective."

Interviews with professionals in the autonomous vehicle industry give learners a glimpse into the real-world applications and challenges of self-driving cars.

"It does cover many topics in broad strokes, so while the course description may say it takes about 40 hours to complete this course, expect to spend at least double"

"It also gives you a modest intro to the Carla simulator."

"The interviews of various professionals in the AV industry were very interesting."

The course is organized in a logical manner, providing a clear progression of topics and concepts.

"The possibility to get such a smooth introduction to the dynamic modeling and controlling topics together with the programming task on a realistic problem is very important for further learning and understanding."

The final project involves developing and controlling a self-driving car in a simulated environment, providing hands-on experience.

"Most of the course was easy to follow and easy to understand."

"I liked this course and learned a great deal about the in and outs of self-driving cars."

"The final project with Carla simulator is actually pretty good."

The course lacks active support, making it challenging to resolve technical issues or receive guidance.

"For this course on the forums is non existent and expecting students to jump into CARLA and write a simulation loop is quite a leap."

"Especially when debugging CARLA is next to impossible since putting a breakpoint inturn breaks the connection to the server."

"The course requires way more smaller steps before throwing the student in the deep end."

Some of the course materials and software may be outdated, requiring additional effort to complete assignments.

"The negative is that the lectures are extremely short."

"Worked problems aren´t covered in the lectures or the readings, and insight into the topic seems to have been omitted."

"Python has progressed, but the notes for installation seem to be static."

The course assumes students have a basic understanding of college-level math, physics, engineering, and Python programming.

"This course assumes you have more than a basic understanding of college-level math, physics and engineering (at least you have to know the classical control theory) and Python/familiarity with using a command line environment."

"Especially to complete the final exam, a lot of effort has to be spend to get to know environment."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Introduction to Self-Driving Cars with these activities:

Review the mathematics behind self-driving cars

Show steps

Strengthen your foundational knowledge in mathematics by reviewing concepts relevant to self-driving cars. This will improve your comprehension of the course material.

Browse courses on Linear Algebra

Show steps

Review linear algebra concepts
Refresh calculus skills
Review probability and statistics

Form study groups

Show steps

Collaborate with classmates to review course material, solve problems, and share insights. This peer-to-peer learning will enhance your understanding.

Show steps

Identify classmates with similar interests
Schedule regular study sessions
Review lecture notes and assignments together

Control engineering exercises

Show steps

Sharpen your control engineering skills by solving practice problems. These drills will strengthen your understanding of the fundamental concepts.

Browse courses on Control Theory

Show steps

Analyze system dynamics
Design controllers
Simulate control systems

Five other activities

Expand to see all activities and additional details

Show all eight activities

Tutorials on deep learning for self-driving cars

Show steps

Stay up to date with the latest advancements in deep learning for self-driving cars by following guided tutorials. This will broaden your skillset and enhance your knowledge.

Browse courses on Machine Learning

Show steps

Learn the basics of deep learning
Apply deep learning to self-driving cars
Implement deep learning algorithms

Attend industry conferences

Show steps

Connect with other professionals in the self-driving car industry to learn about the latest trends and exchange ideas.

Show steps

Research industry conferences
Register for attendance
Network with attendees

Build a self-driving car simulator

Show steps

Implement a simulator to test and refine your self-driving car algorithms. This hands-on experience will reinforce the concepts learned in the course.

Show steps

Choose a simulation platform
Design the simulator environment
Implement the physics engine
Add sensors and actuators
Test the simulator

Create a blog post about a self-driving car topic

Show steps

Solidify your understanding by synthesizing your knowledge into a blog post. This will help you articulate your thoughts and enhance your communication skills.

Show steps

Choose a specific topic
Research and gather information
Write and edit the blog post
Publish and promote the blog post

Participate in self-driving car competitions

Show steps

Test your knowledge and skills by participating in self-driving car competitions. This real-world experience will push you to solve complex problems and refine your abilities.

Show steps

Identify relevant competitions
Form a team or join an existing one
Design and develop a self-driving car
Compete in the competition

Career center

Learners who complete Introduction to Self-Driving Cars will develop knowledge and skills that may be useful to these careers:

Automotive Engineer

Automotive Engineers design, develop, and test vehicles. They work on a variety of aspects of vehicles, including engines, transmissions, and safety systems. This course may be useful for Automotive Engineers who want to work on self-driving cars, which are a new and rapidly developing area of automotive engineering.

See salaries and explore the career path for Automotive Engineer

Software Engineer

Software Engineers design, develop, and maintain software systems. They work on a variety of software applications, including operating systems, web applications, and mobile applications. This course may be useful for Software Engineers who want to work on self-driving cars, which are software-intensive systems.

See salaries and explore the career path for Software Engineer

Mechanical Engineer

Mechanical Engineers design, develop, and maintain mechanical systems. They work on a variety of mechanical systems, including engines, transmissions, and robots. This course may be useful for Mechanical Engineers who want to work on self-driving cars, which are mechanical systems that require a high level of engineering expertise.

See salaries and explore the career path for Mechanical Engineer

Control Systems Engineer

Control Systems Engineers design and implement control systems, which are used to regulate the behavior of dynamic systems. They work in a variety of industries, including automotive, aerospace, and manufacturing. This course may be useful for Control Systems Engineers who want to work on self-driving cars, which are dynamic systems that require precise control.

See salaries and explore the career path for Control Systems Engineer

Electrical Engineer

Electrical Engineers design, develop, and maintain electrical systems. They work on a variety of electrical systems, including power systems, control systems, and communication systems. This course may be useful for Electrical Engineers who want to work on self-driving cars, which are electrical systems that require a high level of engineering expertise.

See salaries and explore the career path for Electrical Engineer

Data Scientist

Data Scientists use data to solve business problems. They work with data to identify patterns, trends, and insights. This course may be useful for Data Scientists who want to work on self-driving cars, which generate a large amount of data that can be used to improve the performance of the car.

See salaries and explore the career path for Data Scientist

Product Manager

Product Managers are responsible for the development and launch of new products. They work with engineers, designers, and marketers to ensure that the product meets the needs of the customer. This course may be useful for Product Managers who want to work on self-driving cars, which are a new and rapidly developing product.

See salaries and explore the career path for Product Manager

Systems Engineer

Systems Engineers manage complex systems, using their knowledge of engineering and science to make design decisions. They work with other engineers to ensure that the system is safe, efficient, and reliable. This course may be useful for Systems Engineers who want to work on self-driving cars, which are complex systems that require a high level of engineering expertise.

See salaries and explore the career path for Systems Engineer

Project Manager

Project Managers plan and execute projects. They work with stakeholders to define the scope of the project, develop a budget, and create a timeline. They also track the progress of the project and make sure that it is completed on time and within budget. This course may be useful for Project Managers who want to work on self-driving cars, which are complex projects that require a high level of project management expertise.

See salaries and explore the career path for Project Manager

Quality Assurance Engineer

Quality Assurance Engineers test software and hardware products to ensure that they meet quality standards. They work with engineers and other technical experts to identify and fix defects. This course may be useful for Quality Assurance Engineers who want to work on self-driving cars, which are complex products that require a high level of quality assurance.

See salaries and explore the career path for Quality Assurance Engineer

Technical Writer

Technical Writers create documentation for technical products. They work with engineers and other technical experts to gather information and write clear and concise documentation. This course may be useful for Technical Writers who want to work on self-driving cars, which are complex products that require clear and concise documentation.

See salaries and explore the career path for Technical Writer

Robotics Engineer

Robotics Engineers design, build, and maintain robots, dealing with hardware and software issues. They often work in specialized fields, including aerospace, healthcare, manufacturing, and defense. This course may be useful for Robotics Engineers who want to work on self-driving cars, which is a specialized subfield of robotics.

See salaries and explore the career path for Robotics Engineer

Sales Engineer

Sales Engineers work with customers to identify their needs and provide them with solutions. They work with engineers and other technical experts to develop and deliver solutions that meet the customer's needs. This course may be useful for Sales Engineers who want to work on self-driving cars, which are new and rapidly developing products.

See salaries and explore the career path for Sales Engineer

Marketing Manager

Marketing Managers develop and execute marketing campaigns to promote products and services. They work with other marketing professionals to create and deliver marketing campaigns that reach the target audience. This course may be useful for Marketing Managers who want to work on self-driving cars, which are new and rapidly developing products.

See salaries and explore the career path for Marketing Manager

Machine Learning Engineer

Machine Learning Engineers design and build machine learning models, focusing on developing and maintaining the infrastructure and systems around the models. They work closely with data scientists to operationalize the models. This course may be useful for Machine Learning Engineers who want to build self-driving cars.

See salaries and explore the career path for Machine Learning Engineer