#43 overallEvergreen
Artificial Intelligence for Robotics
Udacity
10 recommenders · 10 threads · recommended in 8 years, 2012–2020 · score 13.1
A Udacity course taught by Sebastian Thrun covering probabilistic robotics and AI techniques such as localization, Kalman and particle filters, search, PID control, SLAM, and motion planning, using Python. Commenters describe it as the Udacity CS373 course.
Commenters call it an accessible, hands-on introduction to probabilistic methods like Kalman filters, with Thrun praised for explaining intuition clearly.
Machine Learning & AIintermediatefreevideo lectures#robotics#kalman filter#particle filter#slam#probabilistic robotics#thrun
Recommendations by year
20062026
While Kalman and Bayesian Filters in Python is a superb resource, probably the best out there, my recommendation for anyone new to the field would be to do Sebastian Thrun's free Artificial Intelligence for Robotics course [1] as an intro, then go through Labbe's work afterwards.
Thrun's course is more accessible and even more hands-on than Labbe's content. As a bonus he also covers Particle Filters,PID control, Search and SLAM (which cam out of Thrun's PhD thesis).
[1] https://www.udacity.com/course/artificial-intelligence-for-r...
Hello! Great questions.
1) If you already have a good grasp of Python, I always advise to start with the AI for Robotics MOOC at Udacity, which is my favorite class of all time. Once that's done, I'd take a look at their Deep Learning classes and the Self-Driving Car Nanodegree.
2) I think it's crucial to get to grips with how the whole stack works, so I always advise to get to grips with a middleware like ROS. Also, don't be afraid to dabble in algorithms (think problems in motion planning, computer vision, etc.)
3) The traditional programs (think PhD programs) create a lot of specialists focused on a single domain, but the industry is in dire need of more generalists. An engineer who is able to dive into any part of the stack is a huge value-add!
If anyone is interested in some of the algorithms behind this technology, then I highly recommend Sebastian Thrun's "Artificial Intelligence for Robotics" course on Udacity [1]. He makes unintuitive probabilistic methods easily understandable. I'm not aware of a better source for getting a basic understanding of complex methods like Kalman filters and particle filters [2][3]. I had never even heard of a "histogram filter" until recently reviewing this material, and it's a perfect solution for a problem that I currently have.
[1] https://www.udacity.com/course/cs373
[2] http://en.wikipedia.org/wiki/Kalman_filter
[3] http://en.wikipedia.org/wiki/Particle_filter
I'm 6 classes through it. Classes vary wildly in difficulty and applicability.
Favorites so far for me were AI4R (Ariticial Intelligence for Robotics) which is a more rigorous version of Udacity's Self-Driving Car course, ML4T (Machine Learning for Trading) where you implement various algorithms to optimize trading strategies, and ISYE 6501 (Intro to Analysis), which is a survey of various analysis techniques and ML algorithms.
Still have to take the reputed hardest course in the program, the General Algorithms course, the ML course, and an elective.
Worth the money, though I have had to skip a couple of semesters due to burnout. Work and this program are hard (for me).
It depends on the courses you pick. With your Math MS, you might actually do really well in the Machine Learning/AI courses that they offer. The projects are mostly in Python and a lot of students do not have a CS undergrad, so you won't be alone there. https://omscentral.com/ is a good resource if you want to see per-course reviews on what the courses are like or how much programming you do. The systems engineering courses (compilers, distributed systems, operating systems) are heavy in C/C++, but the machine learning courses are heavy in Python (AI for robotics for example, which is a great course). You can go to Udacity or Youtube and check out the videos if you want to try it out.
The course is also quite easy to follow without buying the book. I love the exercises in which you are programming an intelligent agent to move through a maze. It reminded me of how we learned programming in university using Karel The Robot.
This alongside Andrew Ng's Machine Learning course was my first exposure to the field. https://www.coursera.org/learn/machine-learning
I can also recommend Sebastian Thrun's Artificial Ingelligence for Robotics course: https://www.udacity.com/course/artificial-intelligence-for-r...
For math/stats&probability in the specific problem domain of autonomous vehicles (of which self-driving cars are a subset) I'd recommend no other than Sebastian Thrun's Udacity course "Artificial Intelligence for Robotics" [https://www.udacity.com/course/artificial-intelligence-for-r...]. The content is practical, and Thrun, in my opinion, is great at breaking down complicated topics (e.g. Kalman filters) into simpler sub-components and explaining the intuition behind them. You'll get a heavy dose of math/stats&probability in the context of autonomous robots (and in certain cases, Thrun contextualizes to his work in the DARPA grand challenges while at Stanford, which laid the groundwork for his work at Google on the self driving car project [now Waymo]). I can't speak to how much the "traditional" localization, mapping, and planning techniques taught in the course crossover to deep learning approaches, but you'll no doubt get the math/stats&probability knowledge you're looking for, in the context of self-driving cars.
I took the AI for robots on Udacity, the Machine Learning at Coursera and the Control of mobile robots on Coursera. They are all very good in my opinion. Of those, I would start with the Machine Learning course. Not only is it an excellent course and has material found in the others, but if you are at all rusty on your Linear Algebra it will help with that, in addition to the programming of course all of these course make heavy use of linear algebra. The coursera course both use Matlab, the Udacity course uses Python.
Of the robotics course I would say the one on Courera is better in terms of the basics of a robot, like odometry, PID control, etc. The one on Udacity I found more informative in terms of higher level concepts like route planning and localization.
I'd take Thrun's course on autonomous robots.
I'd then implement it on a physical system - I'd focus on something other than Arduino, which doesn't translate well, and do it on RaspPi or similar.
All Coursera courses are deadline based. Some of the courses remove their material at the end of the course. Others, such as the database one, are later opened up as self-study but do not offer a certificate of completion.
In the case of edX, MIT's 6.00x course is strictly deadline based. CS50x allows you to take the course at your own pace as long as you finish everything before the 13th of April, 2013.
But those aren't the ones you're looking for. Udacity meets all your requirements. They have open enrollment, meaning you can join in at any time. Furthermore, they have no deadlines. As long as you complete all the problem sets and give the final exam, you get a certificate.
Here are some Udacity courses that might interest you:
Statistics 101 - http://www.udacity.com/overview/Course/st101 - Taught by Sebastian Thrun
CS271 Introduction to Artificial Intelligence - http://www.udacity.com/overview/Course/cs271 - Taught by Sebastian Thrun and Peter Norvig
CS373 Artificial Intelligence for Robotics - http://www.udacity.com/overview/Course/cs373 - Taught by Sebastian Thrun
Hope that helps.
Edit: There's CS188.1x by Berkeley on edX - https://www.edx.org/courses/BerkeleyX/CS188.1x/2012_Fall/abo...
It's deadline based, but I don't know whether they will remove their material at the end of the course or not.
Also check out Sebastian Thrun's videos from the "AI for robotics" Udacity course (2012). He explains with similar examples:
https://www.youtube.com/watch?v=LXJ5jrvDuEk
https://www.youtube.com/watch?v=HTL5-0DDqE4
https://www.youtube.com/watch?v=cUKlYjQEQGY
https://www.youtube.com/watch?v=hUnTg5v4tDU
So? I failed to ascertain from the article why this is supposed to be some kind of problem.
Also, as far as I can see, quite a few people do find some reason to stay in, and fight for their grade. I've taken several online courses:
• The Norvig/Thrun AI class at Stanford
• Thrun's robot car class at Udacity
• Evans' applied cryptography class at Udacity
• Jackson and Shoham's game theory class at Coursera
• Ng's machine learning class at Coursera
• Abu-Mostafa's learning from data class at Caltech
At most of these, the forums were full of people who evidently found a reason to stay in. Whenever there was any ambiguity in a question, there would be spirited discussion and vigorous arguments from those who thought that the ambiguity had cost them a point.
There did tend to be more of this on Udacity courses than on Coursera courses. I think it because the Udacity forums are based on a Stack Exchange clone, whereas the Coursera forums are more like traditional forums.
On the other hand, the Caltech learning from data course had some good forum action, and its forums are quite plain and simple, so I don't think forum software explains the difference between Udacity and Coursera. Part of it might be that Abu-Mostafa frequently answers questions on the forum, whereas at Coursera I didn't see the professors on the forums much--only TAs.
If you need some kind of threat looming over you in order to motivate you to stick with a course and no such threat is available, why take that course? Go take some course in a subject that actually interests you enough that learning more about it is sufficient motivation.