Real World Robotics 2023

Course Description

This course guides RSC students through an entire robotic design process. Students will work in teams on a real-world robotics challenge: building an articulated robotic hand and programming a robust controller with reinforcement learning. The course covers high-level system design, robot simulation, fabrication, control, and testing. Students will learn the key theoretical concepts, develop hard- and software engineering skills and gain practical engineering experience by building their own unique designs! Prerequisites assume introductive courses for robot dynamics and control. You will learn everything else on the way! This class is only available during the autumn semester.

Time and Location

Mon 25 Sep - Mon 18 Dec, 2023

Pre-recorded, evening: Tutorial, website
14:15 - 15:00: Focus Talk & Q&A, CLA E 32.2
15:15 - 16:00: Workshop, CLA E 32.2

Course Schedule

Lectures will occur during the Autumn Semester 2023 .
New tutorial, slides, and lectures will be open-sourced every week starting 25th September!

: Tutorial

: Focus and Q&A Talk

: Workshop

: Check-Up

The Challenge & Showcase

Unit 1

25 Sept., 2023

[Slides] [Video]

Building and Fabricating a Robot Hand

Unit 2

02 Oct., 2023

[Video]

Prototyping and Fabrication Techniques for Robots

Unit 3

09 Oct., 2023

Simulating Robots and Soft Interaction with the World

Unit 4

16 Oct., 2023

[Slides] [Video]

Hardware Check-Up and Q&A

Check 2

23 Oct., 2023

Identifying Kinematics and Dynamics of Robots

Unit 5

30 Oct., 2023

[Slides] [Video]

Implementing Control Strategies for Manipulation

Unit 6

06 Nov., 2023

[Slides] [Video]

Teleoperation using Machine Learning and Computer Vision

Unit 7

13 Nov., 2023

[Slides] [Video]

Advanced Controllers with Reinforcement Learning

Unit 8

20 Nov., 2023

[Slides] [Video]

Software Check-Up, Q&A and Workshop

Check 3

27 Nov., 2023

Bringing Robots to the World and Project Check-Up

Unit 9

4 Dec., 2023

[Slides] [Video]

Presentation and Hardware Showcase

The Challenge I

11 Dec., 2023

[Info]

Teleoperation and Autonomy Showcase

The Challenge II

18 Dec., 2023

[Info]

Frequently Asked Questions

To whom is this course adressed?

Everyone from Robotics, Systems and Control is allowed to register!

The spots available are 40 at the most.
If you are in the waiting list, Click here for instructions

What is the grading policy?

RWR is offered as a 4 units course and graded on the final Project, the weekly Moodle Quiz and your physical attendance. Each week a tutorial and a Moodle Quiz are handed out. Students are supposed to answer the questions before the next Focus Talk. The Final Challenge will be split in many parts: Presentation, Report, Hardware and Software Showcase.

I'm in the waiting list, what now?

If you are an ETH student in the waiting list, you can attend the first workshops and wait. If new spots will be available you will be able to register.

What pre-requisites are required?

We are expecting elementary knowledge of linear algebra and calculus. An understainding of Control Systems and Robot Dynamics is required too
There are no prerequisites concerning Machine Learning but having some basics is a plus.

What is the schedule of the class?

Each week has its own structure. If there is a tutorial planned, it will be uploaded the monday before the respective Focus Talk. Students should watch the tutorial before the class (we suggest to it together with the group) and answer the quiz on Moodle.

How can I register for this course?

If you are an ETH student please register on myStudies. You can do this by logging in. Go to "functions" and then to "Course Registration". Click on "Add learning units" and look for "Real-World Robotics".

Are the course materials open-source?

All course materials are available online but are copyrighted and licensed under the ETH license. If you are an instructor and would like to use any materials from this course (slides, labs, code), you must add the following reference to each slide:

© Robert Katzschmann
ETH: Real-World Robotics
https://rwr.ethz.ch

For source code that was used to simulate and train the reinforcement learning agent, click here for the GitHub repository.

Is physical attendance mandatory?

Attending the workshops and the Q&A is a critical part of the learning process for this course. We will register your attendance since it will be considered for the final grade. If you are sick or are unable to attend contact the TA to get an exemption.