Вернуться к Robotics: Aerial Robotics

4.5

звезд

Оценки: 2,413

•

Рецензии: 615

How can we create agile micro aerial vehicles that are able to operate autonomously in cluttered indoor and outdoor environments? You will gain an introduction to the mechanics of flight and the design of quadrotor flying robots and will be able to develop dynamic models, derive controllers, and synthesize planners for operating in three dimensional environments. You will be exposed to the challenges of using noisy sensors for localization and maneuvering in complex, three-dimensional environments. Finally, you will gain insights through seeing real world examples of the possible applications and challenges for the rapidly-growing drone industry.
Mathematical prerequisites: Students taking this course are expected to have some familiarity with linear algebra, single variable calculus, and differential equations.
Programming prerequisites: Some experience programming with MATLAB or Octave is recommended (we will use MATLAB in this course.) MATLAB will require the use of a 64-bit computer....

Oct 23, 2017

The course is very good.\n\nThe classes are well taught and show general concepts. It is necessary to do research on the internet, to solve the assignments. This is not a bad thing in my point of view

Jun 09, 2018

I think this is very good course of aerial robotics research. Being a student of robotics, I feel that some of stuffs in this course needs a good background in control and mechanical engineering.

Фильтр по:

автор: Zachary H

•Feb 20, 2016

So close but yet so far ...

Course concepts are interesting and the programming assignments are fun but the presentation can be greatly improved.

Criticisms include:

(i) The course isn't self contained. Physical concepts like 'resultant moment', 'inertial and body-fixed frame' and 'torque' are used without definition. Mechanics is not listed as a prerequisite but it should be.

(ii) Lectures are very mathematical but proofs, intuition and good problem sets are all missing. Listening to a math lecture without doing challenging problems or deriving mathematical results to build intuition can be a waste of time. Check out John Cochrane's Asset Pricing 1 and 2 or Tim Roughgarden's Algo 1 and 2 for great examples of thoughtful problem sets and intuitive derivations.

(iii) Way too much powerpoint! Speed reading a static powerpoint slide overloaded with dense mathematical formulas without using pointers or animations to focus the students attention is a recipe for confusion and frustration. I find hand written derivations, even when the handwriting is a little sloppy, much easier to follow than a static page of formulas plus a sound track. Hand written derivations impose a natural pace and focal point to the content. Check out Gilbert Strang's Linear Algebra, Sebastian Thrun's Artificial Intelligence for Robotics and Andrew Ng's Machine Learning for examples of good derivations of mathematically sophisticated material.

(iv) The programming assignments while fun were somewhat ad hoc and disconnected from the lecture material, specifically, the main task of every single assignment was to hand tune a pd controller. No systematic approach was ever described for performing this task.

автор: Cristina E

•Feb 12, 2016

Well balanced mix of theory and practical applicability. Explanation of the material is also very good.

The assignments are nicely built on the taught material to stimulate understanding.

автор: Pushkar K

•Dec 28, 2016

[I am speaking from my personal experience about this course. I don't mean to insult anyone or criticize the method of teaching and I am not doubting the credentials of instructors. It is just what I experienced from this course that I am saying. However, I don't mean to discourage anyone from attempting this course. This review is just a summary of what I felt about the first two weeks of this course.]

I don't think this course is for the beginners at all. The teaching method did not quite please me. It appears that the instructors and TAs are simply reading the transcripts and bombarding equations on the screen. Also, the course hasn't made any reading material available, and they are not even providing the slides for the lectures (as of till DEC 2016).

I have enrolled and completed a course on mobile robotics from Georgia Tech on Coursera and they were using slides and at the same time the instructors were scribbling equations on the slides and ensuring that they maintain synchronicity with the learning and showing them how a particular equation emerges. They also had lectures which were designed to help learners attempt the quiz and special section about MATLAB and how to build robots. They also provided slides to revise what was mentioned in the lectures. They were teaching and not reading from teleprompter.

This course looked lot of theoretical and I am not sure for whom it is designed for. Also, in the discussion forum, I haven't received answer to the questions that I'm posting(since right now it's holiday season, I can exempt them from not replying).

I knew I could carry on with this irritation and still get the course certificate for which I've paid for, but then there is no point in wasting time in which the explanation is not clear. It would take me almost 20 to 30 minutes to make notes over a 5 minute long video. I would rather read a book on this subject.

I would have appreciated if they followed certain steps:

1) Make some course material which will help students read and revise information.

2) Suggest some reading/reference material to understand the concepts which are not otherwise covered in this course.

3) Use pointers(touch screen devices) to show and point out which equations are being referred to and maintain synchronicity between the information given in the slides and the one said by the instructor.

4) Supplementary lectures are extremely fast paced and please don't take derivation of an equation for granted and please do explain.

So, if you are looking forward to do this course, I suggest you go forward if you have an in-depth knowledge about vectors, matrices and calculus.

автор: Matthew R

•Aug 07, 2016

The video lectures provide an introduction to quadrotor flight dynamics and path planning. The lectures are ok.

Unfortunately:

At least one of the coding assignments has a significant bug in the termination condition. The mentors will ignore any help requests that deal with the bug in their code.

The assignments involve a lot of hand tuning of PD controllers. That's a reasonable task to perform once or twice, but it rapidly becomes extremely tedious and detracts from the other materials that are being taught.

The final assignment doesn't do a particularly good job evaluating the required test condition.

If you do take the course I'd want you to know:

You should expect to modify the provided code to fix their bugs.

There are no "gotcha" quiz questions. If you are confused by getting a question wrong you might want to re-try your answer. There seems to be a bug in the way at least one quiz question is set up.

On the final assignment you can modify the simulation step where it makes things run in "real time". Removing that step makes the simulation run much more quickly and allows for faster iteration.

To conclude:

This is a course with a lot of potential, but unless Coursera makes an effort to improve the course I would not recommend it.

автор: Olena D

•Feb 29, 2016

I had very high hopes for this course. I was actually planning to purchase the specialization - just as a thank you gesture. Unfortunately, there is very little to be grateful for here.

In this course, you get a series of super short lectures giving you an overview of the math and physics behind the aerial robotics. I can't be the judge (since I hold a degree in this area), but I don't think you'll be able to get much if you aren't familiar with the topics yet. And you most certainly won't learn anything new if you had some previous training.

And then suddenly there are assignments. That have almost nothing to do with the lectures, but require quite a bit of Matlab programming (did I mention you won't be taught any Matlab in the process?) To make things worse, the assignments are rather poorly explained.

By the way, you won't get any replies from the course team - they even ignore questions about errors in lectures.

The course looks very sloppy. As if someone forced the team to put together something for Coursera. A huge disappointment :(

автор: Sathivada C K S

•Nov 25, 2018

Firstly. I thank Mr Vijay Kumar and his team to take time & efforts on preparing the material which is structure perfectly for a beginner like me.

Secondly for giving us explicit videos and materials for the research carried out on drones especially quadrotors at Penn State University, this not only helped me with the course for which I had liking, but has also opened up options for master program in your prestigious university.

Lastly, I thank all the students who have been active on the forum to respond on issues faced in programming assignments. Thank you all, happy learning.

автор: Ivan T

•Oct 23, 2017

The course is very good.

The classes are well taught and show general concepts. It is necessary to do research on the internet, to solve the assignments. This is not a bad thing in my point of view

автор: Sandesh T

•Jun 09, 2018

I think this is very good course of aerial robotics research. Being a student of robotics, I feel that some of stuffs in this course needs a good background in control and mechanical engineering.

автор: utkarsh m

•Apr 08, 2019

The course is very good and is designed such that even beginners can get a good grasp on the content that is made available. The discussion forums are great and help in making life easier.

автор: Pablo

•Aug 29, 2017

Quiz != lecture materials...

автор: Eric B

•Apr 27, 2019

I've learned a lot in 4 short weeks. This is a great course, especially for someone with an academic background in controls, but little practical experience.

автор: Tri W G

•Mar 10, 2018

It's a tough course, but it's really worth the time if you're interested in robotics, especially UAVs. You really have to spend more time in the programming assignment, especially the last one, trajectory generation. The suplementary materials are really really helpful. The downside is that the help in the forum is really minimum. You have to wait 2 or 3 days to get responses.

Thank you lecturer and the team, I learned a lot and I'm grateful for that.

автор: Lunghao L

•Jun 30, 2018

This is quite a good course, since I am a student who had learn control theory before, this class teach me something really practical. Believe me I don't think it is easy, although I have some basic knowledge about matlab and control, I still struggle in some part of class. What best is! The class show me what quad really do in real world, in the way I didn't imagine before. Thanks U Penn and professor and everyone in forum!

автор: Md. S H

•Jun 27, 2019

It was a awesome course. As a novice, I somehow completed it, however with great effort

автор: Nandakumar L

•Dec 27, 2018

Right course to understand the science behind quad-rotors.

автор: SAIKAT B

•Mar 14, 2019

b

e

s

t

автор: Andrew W

•Oct 14, 2018

Very interesting and very well prepared. I appreciate the instructors carefully constructed explanations and clarity. I understood there were no technical prerequisites required to take this course, but the material is not easy anyone lacking a science (e.g. engineering) background.

I was required to study the material and pull out my old text books to refresh on most of the topics. Also without any basic linear algebra and Matlab knowledge, the course could be very challenging.

автор: Châu M V

•Sep 08, 2017

General speaking, the course is very good, lecture contains great knowledge. But the programming task consumed time in unnecessary thing , PID tuning parameters, which does not help students understand the methods, just "blindly changing parameters"

автор: Abdelrahman A

•Sep 16, 2018

It needs more programming in depth and it will be perfect.

автор: Harshad V

•Jun 30, 2018

The course was very detailed and gives some hands on experience in assignments. Thanks to Prof. Vijay Kumar and TAs for excellent explanation. The course is explained well step by step, however it doesn't spoon feed you. I wouldn't say It is very easy, however it depends on the person, but It requires little effort from the learner side to understand the concept well and apply it on the assignments and quizzes, this makes it more interesting. Some fluency in math and programming is helpful. Discussion forum is best tool if you get stuck somewhere. I had to watch the videos several times to get some topics, read slides and discussion forum. Things start becoming clear and make sense while completing assignments (It is well designed to cover important concepts and apply it). Overall, great course for those who love robotics and want to learn it. This course covers basics of an autonomous quad-copter, its kinematics, dynamics, control, planning, etc.Material provided is very helpful and is designed to clear concepts and connect all the nodes.

автор: Nada A A

•Oct 09, 2019

This course is extremely useful and it helped me to get a bunch of valuable knowledge about the topic. It is also very challenging, and it requires a lot of searching and dedication. My advice to the future students on this course is to never give up even when they feel frustrated by the amount and difficulty of new concepts. It is not a course for beginners in the field; however, anyone with desire and determination to complete the course will do it. Do your best and your hard work will pay off.

Also, I would like to express my appreciation to the instructor, TAs and colleagues helping us in discussion forum. This learning environment makes the course more fantastic, and encourages students to continue the course.

автор: Kenan

•Jun 22, 2018

This course helped me to understand the basics of control theory. I watched all videos including the supplementary material at least twice (and sometimes by adjusting the speed of the videos). In that way I was able to repeat the material and remember the details. The quizes were mostly easy and the answers were hidden in the corresponding material, but at times some questions required additional information. The first two programming exercises were straightforward. The second part of the last assignment (i.e. trajectory planning) was very tricky. Prior to the last assignment, a practical homework can added to prepare students to the 2nd part of the last assignment.

автор: An N

•Feb 09, 2016

Great course. Initiate you to review much of your math and engineering control knowledge by specific problems. This is more of an application course, you see the application, the math behind and use Matlab to program certain situation. Beware, it's a one month course so they don't spend time to walk you through the basic math, some specific terms are explained during the lecture but not all, a reference for some Control book maybe needed to know what are those terms.

If you have no knowledge in these area, some supplemental material maybe provided but be ready to learn and explore more on your own.

автор: Yifan W

•Feb 12, 2016

I'd like to say a big thank you for Professor Kumar for putting this together. I work full time and in my spare time some of my friends are thinking about building a in-house small quadrotor with 3-D printed parts and rasberry pi & basic camara. The information of this course is very, very useful and the Matlab practices and assignments are challenging and interesting.

Not to mention this course has successfully pulled me away from my favorite video game...a remarkable achievement.

I hope that the notation in the videos and in the assignments could be more clear as that can cause confusion.

автор: Michael P

•Sep 19, 2017

A very informative course! I learned a ton about aerial robots and their control and applications. The programming assignments were challenging but I learned a lot through struggling with the problems. I think that supplemental section providing examples of PD/PID tuning and trajectory programming would've been very helpful and would have reduced some of the frustration I felt (and other students felt as indicated by the forum posts). Finally, I would have liked have seen better, more constructive guidance from the T/A's. I think this could be managed without providing the answer.

- Искусственный интеллект для каждого
- Введение в TensorFlow
- Нейронные сети и глубокое обучение
- Алгоритмы, часть 1
- Алгоритмы, часть 2
- Машинное обучение
- Машинное обучение с использованием Python
- Машинное обучение с использованием Sas Viya
- Программирование на языке R
- Введение в программирование на MATLAB
- Анализ данных с Python
- Основы AWS: введение в облачные приложения
- Основы Google Cloud Platform
- Обеспечение надежности веб-сервисов
- Разговорный английский язык на профессиональном уровне
- Наука благополучия
- Научитесь учиться
- Финансовые рынки
- Проверка гипотез в здравоохранении
- Основы повседневного руководства

- Глубокое обучение
- Python для всех
- Наука о данных
- Прикладная наука о данных с Python
- Основы бизнеса
- Разработка архитектуры на платформе Google Cloud
- Инженерия данных на платформе Google Cloud
- От Excel до MySQL
- Продвинутое машинное обучение
- Математика в машинном обучении
- Беспилотные автомобили
- Блокчейн для организаций
- Бизнес-аналитика
- Навыки Excel для бизнеса
- Цифровой маркетинг
- Статистический анализ в здравоохранении на языке R
- Основы иммунологии
- Анатомия
- Управление инновациями и дизайн-мышление
- Основы позитивной психологии

- ИТ-поддержка Google
- Специалист IBM по привлечению клиентов
- Наука о данных IBM
- Прикладное управление проектами
- Профессиональная сертификация IBM в области прикладного ИИ
- Машинное обучение для Analytics
- Пространственный анализ данных и визуализация
- Проектирование и управление в строительстве
- Педагогический дизайн