Estimated Time
6 months
At 15 hrs/week
Enroll by
April 14, 2020
Get access to the classroom immediately on enrollment
Prerequisites
Python, C++, & Mathematics
Built in partnership with
Built in partnership with
What You Will Learn
Download SyllabusSyllabus
Self-Driving Car Engineer
Hide details
Prerequisite Knowledge
Students should have experience with Python, C++, Linear Algebra, and Calculus. See detailed requirements.
Introduction
Learn about how self-driving cars work and about the services available to you as part of the Nanodegree program.
Computer Vision
Use a combination of cameras and software to find lane lines on difficult roads and to track vehicles.
Finding Lane Lines on the RoadAdvanced Lane FindingDeep Learning
Deep learning has become the most important frontier in both machine learning and autonomous vehicle development. Experts from NVIDIA will teach you to build deep neural networks and train them with data from the real world and from the Udacity simulator. You’ll train convolutional neural networks to classify traffic signs, and then train a neural network to drive a vehicle in the simulator!
Traffic Sign ClassifierBehavioral CloningSensor Fusion
Tracking objects over time is a major challenge for understanding the environment surrounding a vehicle. Sensor fusion engineers from Mercedes-Benz will show you how to program fundamental mathematical tools called Kalman filters. These filters predict and determine with certainty the location of other vehicles on the road. You’ll even learn to do this with difficult-to-follow objects by using an extended Kalman filter, an advanced technique.
Extended Kalman FiltersLocalization
Localization is how we determine where our vehicle is in the world. GPS is only accurate to within a few meters. We need single-digit centimeter-level accuracy! To achieve this, Mercedes-Benz engineers will demonstrate the principles of Markov localization to program a particle filter, which uses data and a map to determine the precise location of a vehicle.
Kidnapped VehiclePlanning
The Mercedes-Benz team will take you through the three stages of planning. First, you’ll apply model-driven and data-driven approaches to predict how other vehicles on the road will behave. Then you’ll construct a finite state machine to decide which of several maneuvers your own vehicle should undertake. Finally, you’ll generate a safe and comfortable trajectory to execute that maneuver.
Highway DrivingControl
Ultimately, a self-driving car is still a car, and we need to send steering, acceleration, and brake commands to move the car through the world. Uber ATG will walk you through building a proportional-integral-derivative (PID) controller to actuate the vehicle.
PID ControllerSystem Integration
This is the capstone of the entire Self-Driving Car Engineer Nanodegree Program! We’ll introduce Carla, the Udacity self-driving car, and the Robot Operating System that controls her. You’ll work with a team of Nanodegree students to combine what you’ve learned over the course of the entire Nanodegree Program to drive Carla, a real self-driving car, around the Udacity test track!
Programming a Real Self-Driving Car
All Our Programs Include
Real-world projects from industry experts
With real world projects and immersive content built in partnership with top tier companies, you’ll master the tech skills companies want.
Technical mentor support
Our knowledgeable mentors guide your learning and are focused on answering your questions, motivating you and keeping you on track.
Personal career coach and career services
You’ll have access to career coaching sessions, interview prep advice, and resume and online professional profile reviews to help you grow in your career.
Flexible learning program
Get a custom learning plan tailored to fit your busy life. Learn at your own pace and reach your personal goals on the schedule that works best for you.
Program OfferingsFull list of offerings included:
Enrollment Includes:
Class Content
Content Co-created with Mercedes-Benz
Real-world projects
Project reviews
Project feedback from experienced reviewers
Student Services
Technical mentor support
New
Student community
Improved
Career services
Personal career coaching
New
Interview preparations
Resume services
Github review
LinkedIn profile review
Resume shared with 95+ employers
New
Succeed with Personalized Services
We provide services customized for your needs at every step of your learning journey to ensure your success!
Experienced Project Reviewers
Technical Mentor Support
Personal Career Coach
Get personalized feedback on your projects
Reviews By the numbers
2000+ project reviewers
1.8M projects reviewed
4.85/5 reviewer ratings
3 hour avg project review turnaround time
Reviewer Services
- Personalized feedback
- Unlimited submissions and feedback loops
- Practical tips and industry best practices
- Additional suggested resources to improve
Succeed with Personalized Services
We provide services customized for your needs at every step of your learning journey to ensure your success!
Project Reviewers
Technical Mentor Support
Career Coaching
Get personalized feedback on your projects
Reviews By the numbers
2000+ project reviewers
1.8M projects reviewed
4.85/5 reviewer ratings
3 hour avg project review turnaround time
Reviewer Services
- Personalized feedback
- Unlimited submissions and feedback loops
- Practical tips and industry best practices
- Additional suggested resources to improve
Learn with the best
Sebastian Thrun
Udacity President
Scientist, educator, inventor, and entrepreneur, Sebastian led the self-driving car project at Google X and founded Udacity, whose mission is to democratize education by providing lifelong, on-demand learning to millions of students around the world.
David Silver
Curriculum Lead
David Silver leads the School of Autonomous Systems at Udacity. Before Udacity, David was a research engineer on the autonomous vehicle team at Ford. He has an MBA from Stanford, and a BSE in computer science from Princeton.
Ryan Keenan
Course Developer
Ryan has a PhD in Astrophysics and a passion for teaching and learning. He is also a lead instructor in the Robotics Nanodegree program. When he’s not building Udacious learning content you’ll find him up in the mountains or out in the surf.
Cezanne Camacho
Course Developer
Cezanne is an expert in computer vision with an M.S. in Electrical Engineering from Stanford University. Inspired by anyone with the drive and imagination to learn something new, she aims to create more inclusive and effective STEM education.
Mercedes-Benz
Mercedes-Benz Team
Mercedes-Benz R&D North America develops the world’s most advanced automotive technology and vehicle design with luxury and style. The team from Mercedes built our Sensor Fusion, Localization, and Path Planning content.
NVIDIA
Nvidia Team
NVIDIA is a company built upon great minds and groundbreaking research. GPU deep learning has ignited modern AI - the next era of computing - with the GPU acting as the brain of computers, robots, and self-driving cars that can perceive and understand the world.
Uber ATG
Uber ATG Team
The Advanced Technologies Group is comprised of Uber’s self-driving engineering team dedicated to self-driving technologies, mapping, and vehicle safety.
Student Reviews
(1076)
Farhan A.
This Nanodegree is an excellent introduction to autonomous driving. It has a mix of classical machine learning, deep learning and robotics and every lesson is taught with a programming quiz and every module has a programming project that involves building some component of a typical self-driving car software stack. As someone with a computer science background with some robotics experience, I enjoyed every bit of this Nanodegree. I was awestruck to find out that many of the techniques taught in the Nanodegree have been used by Google self-driving car and also being used by the latest breed of autonomous vehicles from Mercedes to Baidu. I'd like to see a sequel with more advanced content from computer vision, deep learning and control perhaps centred around a state-of-the-art simulator like Carla or Apollo that includes working with LIDAR and RADAR data, programming the CAN bus, 3D segmentation, object tracking, simulation and more.
Krishna K.
I had been an enthusiast and have been passively following the progress of deep learning and self driving cars, although i did take the advanced AI course (self driving cars) course with Udacity, it was much more theoretical. I finally had some time to take this course, i am blown away by how well thought out this course is, from course content to projects that are very practical. I can honestly say that i was enjoying the process of working through the projects as they were very practical, i feel like i have a much deeper understanding of how self driving cars work, i can navigate through this space by making sense of published papers in this space. I would also add that this is the best online class experience i had having taken several online courses. Can't wait to start term 2. Thank you for making this process such a joy.
Tim H.
I had no idea online training could be so thorough and rigorous. I haven't worked this hard since graduate school! Enjoyed every minute of it. Also would like to mention the level of professionalism and complexity of the web content. The material was well laid out and all of the mechanics of user interaction worked superbly - no flaws. Same for all of the downloads, project code, libraries, etc. - always worked. The level of the instructors was outstanding, the very best in their field. Could not get this level of instructors at a single top-level university. The staff was excellent as well. Always experienced prompt responses. The project reviews where next day, very thorough, and helpful - not just a quick cursory glance. All in all, a great experience.
Anu A.
The SDC-ND program has step-by-step guide towards understanding each concept. They let you code even a small concept, this led to a clear understanding of big concepts Eg. gradient descent. I totally agree until we code every damn part, we cannot have a good grasp of NN concepts. Thank you guys for building a material that gives clear understanding of concepts through code. Also, I recommend not to see the solutions until you come up with your own because mostly your struggle through the code will help you to learn these concepts. If you watch given solutions, it will look obvious to you, & you will miss the stupid error fixes which will be a huge bottleneck when you code a big project. This way you might progress slow but the learning curve will be steep.
Shreyas R.
This is a one of a kind nanodegree from giving brain to the car to giving it eyes and senses , I'm learning it all ! I specifically like the part that many industry experts teach the module giving a perfect insight how real self driving car works. It's a tough nanodegree and requires full focus but once you start the course you'll obviously be so excited to learn new techniques. David Silver , Sebastian Thrun and the entire team at Udacity has done a commendable job. The best course I've ever taken and yeah , It also helped me get a job since the teaching are not only specific to SDC but also to application of Computer Vision , Deep Learning and Sensor controls.
Vishal R.
I am deeply proud to be the part of this amazing nano-degree and learning about Self-Driving Cars (SDC) in depth. By the completion of my term 1, I already got 2 job interviews for Deep Learning and Computer Vision profile in SDC space. Credit of this entire goes to my amazing instructor David Silver as well as all the other instructors of this program including entire team of SDCND and Udacity. This is an amazing journey and I am falling in love with every bit of this program. Definitely better than conventional learning and totally worth time and energy. Everything about Self-Driving Car Nano-degree program is Stupendous! Proud to be an Udacian.
Related Nanodegree Programs
Program Details
Why should I enroll?
The Self-Driving Car Engineer Nanodegree program is one of the only programs in the world to both teach students how to become a self-driving car engineer, and support students in obtaining a job within the field of autonomous systems. The program’s nine projects equip students with invaluable skills across a wide array of critical topics, including deep learning, computer vision, sensor fusion, localization, controllers, vehicle kinematics, automotive hardware, and more. As part of their capstone project, students have the rare opportunity to run their code on an actual autonomous vehicle owned by Udacity.
What jobs will this program prepare me for?
Our wide-ranging curriculum will prepare you for a variety of roles in the autonomous vehicle industry, including: System Software Engineer, Deep Learning Engineer, Vehicle Software Engineer, Localization and Mapping Engineer and many others. If you elect to work outside of automotive engineering, your foundation in deep learning and robotics will enable you to fill any number of related roles in artificial intelligence, computer vision, machine learning, and more.
How do I know if this program is right for me?
This advanced Nanodegree program is ideal for anyone with a programming, technical, or quantitative background who is interested in obtaining a job within the field of autonomous systems, or refreshing or developing their skills within the realm of machine and deep learning, systems integration, sensor fusion, and many others.
What is the difference between the Intro to Self-Driving Cars Nanodegree program and the Self-Driving Car Engineer Nanodegree program?
The Intro to Self-Driving Cars Nanodegree program is an intermediate program open to anyone with an interest in autonomous systems, who has some programming experience, and/or a quantitative background. The Self-Driving Car Engineer Nanodegree program is an advanced program focusing on in-depth knowledge of autonomous systems. The program is designed for those with moderate to high programming, technical, and/or quantitative skills.
PROGRAM OVERVIEW - WHY SHOULD I TAKE THIS PROGRAM?
Do I need to apply? What are the admission criteria?
There is no application. This Nanodegree program accepts everyone, regardless of experience and specific background.
What are the prerequisites for enrollment?
Students should have prior experience with the following:
- Intermediate Python or C++
- Basic Linear Algebra
- Basic Calculus
- Basic Statistics
- Basic Physics
You will also need to be able to communicate fluently and professionally in written and spoken English.
If I do not meet the requirements to enroll, what should I do?
We have a number of Nanodegree programs and free courses that can help you prepare, including: Intro to Self-Driving Cars Nanodegree program, Robotics Software Engineer Nanodegree program, and AI for Robotics Course.
ENROLLMENT AND ADMISSION
How is this Nanodegree program structured?
The Self-Driving Car Engineer Nanodegree program is comprised of content and curriculum to support nine (9) projects. We estimate that students can complete the program in six (6) months, working 15 hours per week.
Each project will be reviewed by the Udacity reviewer network. Feedback will be provided and if you do not pass the project, you will be asked to resubmit the project until it passes.
How long is this Nanodegree program?
Access to this Nanodegree program runs for the length of time specified in the payment card above. If you do not graduate within that time period, you will continue learning with month to month payments. See the Terms of Use and FAQs for other policies regarding the terms of access to our Nanodegree programs.
Can I switch my start date? Can I get a refund?
Please see the Udacity Program FAQs for policies on enrollment in our programs.
I have graduated from the Self-Driving Car Engineer Nanodegree program but I want to keep learning. Where should I go from here?
Once you have completed the Self-Driving Car Engineer Nanodegree program, the Robotics Software Engineer Nanodegree program and the Flying Car Nanodegree program are ideal for continuing your learning.
TUITION AND TERM OF PROGRAM
What software and versions will I need in this program?
For this Nanodegree program, you will need to the minimum equipment requirements outlined here: https://www.udacity.com/tech-requirements.
Which version of TensorFlow, Keras, ROS, and C++ are taught in this program?
The following versions are taught in this program (subject to update):
- TensorFlow Version 1.3
- Keras version 2
- ROS Kinetic
- Python Version 3
- C++ Version 11