Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Self-Driving Cars with Duckietown programme by edX revolutionises the life of the participants who take up this course as it combines both AI and autonomous movement of the vehicles. This course gives elaborate steps from the start to finish of scaling the self-driving cars. The software and hardware that are used in this car making will be also taught by the tutors of this course from ETHx.
Video lectures and course materials are given to the learners to gain knowledge about the Self-Driving Cars with Duckietown course. To sharpen the knowledge gained, students are given assignments and tests. Discussion forums are also conducted to clear the doubts regarding the syllabus and course content.
The edX offers both audit and verified track. Students can pursue the Self-Driving Cars with Duckietown online course for free of cost or as a paid course. The paid or verified track offers them with a verified certificate which has the signature of the instructors and the logo of the ETH Zurich on the bottom right corner and top right corner of the certificate respectively. They are also given coupons, scholarships, and financial assistance to pursue the Self-Driving Cars with Duckietown certification course.
This particular course on edX has 2 tracks namely audit and verified which may be opted by a candidate for enrolling. Both the tracks have a self-paced mode but the audit track offers only limited access to the course materials without any cost, and shares no certificate of completion. The verified track on the other hand offers unlimited access thereby offering a certification only if the candidates are interested in paying some money.
The Highlights
- Online programme
- Course from ETH Zurich
- Video transcripts available in English
- Shareable certificate
- 7 week course duration
- Verified certificate from ETHx
- Instructor led course
- Course Language
- Only 4 to 10 hours per week required
- Instructors from ETHx
Programme Offerings
- videos lectures
- Discussion Forums
- activities
- assignments
- quizzes
- Expert Faculty
Courses and Certificate Fees
| Certificate Availability |
|---|
| no |
Eligibility Criteria
Work Experience
All the participants who are interested in learning this concept can join the Self-Driving Cars with Duckietown course by edX. The details regarding the work experience of the candidates is not given in the website. Please check the website in future for more information.
Education
The course does not require any specific educational qualification to attend this course. Willing participants shall take up the Self-Driving Cars with Duckietown online course and earn a certificate.
Certification Qualifying Details
The students need to complete the Self-Driving Cars with Duckietown course successfully so that they can earn a certificate which is verified and has the logo of the ETH Zurich along with the signature of the instructors from the same institution. Kindly check the website for more details as it will be updated soon.
What you will learn
After completing the Self-Driving Cars with Duckietown programme given by edX, the learners will gain knowledge in the following concepts
- Programming the Duckie Boys which is used to navigate the car in road lanes of a city will be done by the candidates on their own.
- The techniques based on computer vision are learnt and used by the candidates to model the self-driving cars with rubber –duckies and pedestrians obstacles as a part of the Self-Driving Cars with Duckietown syllabus.
- Candidates can make their Duckiebot to drive in paths specified by the user.
- The robot subsystems such as memory, computation, sensing etc. and their functions are learnt and recognised by the candidates under the Self-Driving Cars with Duckietown course.
- Understanding the method to command a robot to reach the desired position.
- As a part of the Self-Driving Cars with Duckietown certification benefits, the candidates will grab the art of making their Duckiebot to take decisions autonomously according to modern and traditional approaches.
- The knowledge to set up the software environment related to robotics such as Python, Docker are also gained by the students.
- The learners will be able to program their Duckiebot to drive safely by recognising and avoiding obstacles in road lanes under the Self-Driving Cars with Duckietown course by edX.
Who it is for
The following candidates who want to attend the course by edX shall join the Self-Driving Cars with Duckietown programme.
- This course is for all the students who would like to build their career in this field and can take up this programme and get a certification.
Admission Details
The Self-Driving Cars with Duckietown course offered by edX can be learnt by the users by completing the steps given below.
Step 1: The users should go to the link https://www.edx.org/learn/technology/eth-zurich-self-driving-cars-with-duckietown to register the Self-Driving Cars with Duckietown course.
Step 2: To join the Self-Driving Cars with Duckietown course, the candidates should have an account in edX. Using the email or Facebook or Google account, they can create a new edX account and sign in.
Step 3: The existing users can directly sign into the account with the registered mail id and password. If they forgot the password, they can reset it by clicking on the “Forgot password”.
Step 4: Then search the course by its name or check the Self-Driving Cars with Duckietown training list. Select the desired course and click “Enrol”.
Step 5: Then they will be enrolled in the Self-Driving Cars with Duckietown.
Step 6: The candidates who just enrolled, will first pursue the Self-Driving Cars with Duckietown programme as an audit track.
Step 7: The users can change to the verified track later by clicking “Upgrade to verified track”. Then they will get a verified certificate from ETHx.
Step 8: The users can also avail offers and discounts on the certification fee by applying the coupons if given in the website of edX.
Step 9: After the successful payment completion, the candidates are enrolled to the verified track of the Self-Driving Cars with Duckietown certification course. They will be issued a certificate once when they complete the course.
The Syllabus
- Welcome to the course, by Prof. Emilio Frazzoli
- You will familiarize yourself with the logistics and navigation interface of the course resources
- You will start a learning journey in the world of robot autonomy with Duckietown
- The potentials and challenges
- Levels of autonomy
- The vision for autonomous vehicles (AVs)
- Activities: You will set up your learning environment, and your Duckiebot, and make your first challenge submission
- Making a robot
- Sensorimotor architectures
- Stateful architectures
- Logical and physical architectures
- Application: You will create a reactive "Braitenberg" agent to avoid duckies and see how your agent compares to other submissions
- Introduction to control systems
- Representations and models
- PID control
- Application: You will design an odometry function and PID controller to command your Duckiebot's angular velocity
- Introduction to projective geometry
- Camera modeling and calibration
- Image processing
- Application: You will develop image processing techniques necessary for visual lane servoing - controlling your Duckiebot to drive within markings
- Introduction to neural networks
- Convolutional neural networks
- One and two-stage object detection
- Application: You will train a convolutional neural network (CNN) to detect duckies and integrate your model with ROS to run onboard your Duckiebot and avoid duckies
- Bayes filtering framework
- Parameterized methods (Kalman filter)
- Sampling-based methods (particle and histogram filter)
- Application: You will build a state estimation algorithm combining the dynamics and sensor data of your Duckiebot in order to predict its pose as it travels through the world
- Formalization of the planning problem
- Application: You will create a collision checker to determine if your Duckiebot is crashing into an obstacle
- Graphs
- Graph search algorithms
- Application: You will tackle a variety of path-planning challenges and leverage all the skills you've built thus far to navigate your Duckiebot in a variety of simulated environments
- Markov decision processes
- Value functions
- Policy gradients
- Domain randomization
- Application: You will explore the capabilities and limitations of reinforcement learning models when applied to real-world robotics tasks such as lane following
Evaluation process
There is no exam required to join this course. The candidates can go through the website to get more information about this. This course is for all the students who would like to learn this concept.