Retour à Modern Robotics, Course 2: Robot Kinematics

4.8

60 notes

•

14 avis

Do you want to know how robots work? Are you interested in robotics as a career? Are you willing to invest the effort to learn fundamental mathematical modeling techniques that are used in all subfields of robotics?
If so, then the "Modern Robotics: Mechanics, Planning, and Control" specialization may be for you. This specialization, consisting of six short courses, is serious preparation for serious students who hope to work in the field of robotics or to undertake advanced study. It is not a sampler.
In Course 2 of the specialization, Robot Kinematics, you will learn to solve the forward kinematics (calculating the configuration of the "hand" of the robot based on the joint values) using the product-of-exponentials formula. Your efforts in Course 1 pay off handsomely, as forward kinematics is a breeze with the tools you've learned. This is followed by velocity kinematics and statics relating joint velocities and forces/torques to end-effector twists and wrenches, inverse kinematics (calculating joint values that achieve a desired "hand" configuration), and kinematics of robots with closed chains.
This course follows the textbook "Modern Robotics: Mechanics, Planning, and Control" (Lynch and Park, Cambridge University Press 2017). You can purchase the book or use the free preprint pdf. You will build on a library of robotics software in the language of your choice (among Python, Mathematica, and MATLAB) and use the free cross-platform robot simulator V-REP, which allows you to work with state-of-the-art robots in the comfort of your own home and with zero financial investment....

par SS

•Oct 01, 2018

It is a great start for learning kinematics of open chain robots, i wish i could learn ore about the closed chain robots too, but they have given the boost, now its your turn to learn more and more

par JM

•Dec 10, 2018

More difficult that most Coursera offerings. Lots and lots of glorious math!\n\nI really enjoyed it.

Filtrer par :

14 avis

par Arjun Sahdev

•Apr 01, 2019

Basic skills anyone with interest in robotics should have

par ABDULLAH HAMDAN ALDASSOUKI

•Mar 25, 2019

I just wanna say thank for the smooth and clear explanation

THANKs THANKs THANKs <3

par Chris Scarpelli

•Feb 22, 2019

Great course for going into the next layer of robot design. A bit heavy in theory at times but I assume this becomes more practical moving forward. It would be great if they added some complimentary videos to help translate some of the heavy math components to the quiz questions (i.e. here are the equations we just learned, now here's how to apply them to a practical situation).

par Pau Carre Cardona

•Feb 19, 2019

Very interesting course. It not only covers inverse kinematics but also manipulability and some statics coming from the Jacobian. The Jacobian singularities and its implications are very clear and well explained.

Small drawback is that it's better not to use the library that comes with the course as otherwise you won't learn so much. I implemented my own and learned a lot by implementing it.

Another small drawback is that there is no mention to Conformal Geometric Algebra as something to look at to implemente analytical solutions to inverse kinematics. Neither, iterative FABRIK as alternative to pseudo-Jacobian is mentioned. A mention and a reference would be nice for the learner as presudoinverse jacobian is very limited.

The other drawback, which is major, is that assignments are peer-graded instead of unit tested. It's not ideal at all. Hopefully they will be unit-tested at some point in time so that it's more fair and efficient.

par Ashish Rana

•Feb 04, 2019

Good course, very heavy on theory with little to no example problems. Its good to teach theory but should be followed up with multiple real world problem to solve by hand or code.

par Onur Akgün

•Feb 03, 2019

As a graduate student who has taken multiple Robotics courses in university, I can say that it is a very instructive course. However, it may seem tedious for those who are not familiar with Robotics. One last thing, I preferred Denavit Hartenberg method until this course. Now I can see that PoE is much more efficient than DH.

par Arnab Chatterjee

•Jan 03, 2019

Loved the course and the difficulty level of it. The assignment in particular will be good challenge for MATLAB beginners like me as you'll need to figure out how to do it. But its easy enough and if you have some programming experience, you can do it easily. What I love about this course is that it doesn't spoon feed you. You need to work hard to get all the benefits from the course.

par John Muth

•Dec 10, 2018

More difficult that most Coursera offerings. Lots and lots of glorious math!

I really enjoyed it.

par TANMAY KOWLGI

•Nov 26, 2018

Excellent course.It helped me to improve my programming at much higher level and I got good knowledge.Initially before taking this course I was worried whether I would complete this course but thanks to Kevin sir for such a great teaching

par Bassam Ali Mohammed Saleh Al-ghram

•Nov 18, 2018

It is very good

Coursera propose un accès universel à la meilleure formation au monde,
en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.