Chevron Left
Retour à Robotics: Perception

Avis et commentaires pour d'étudiants pour Robotics: Perception par Université de Pennsylvanie

624 évaluations

À propos du cours

How can robots perceive the world and their own movements so that they accomplish navigation and manipulation tasks? In this module, we will study how images and videos acquired by cameras mounted on robots are transformed into representations like features and optical flow. Such 2D representations allow us then to extract 3D information about where the camera is and in which direction the robot moves. You will come to understand how grasping objects is facilitated by the computation of 3D posing of objects and navigation can be accomplished by visual odometry and landmark-based localization....

Meilleurs avis


31 janv. 2021

This course was truly amazing. It was challenging and I learned a lot of cool stuff. It would have been better if more animations were included in explaining complex concepts and equations.


31 mars 2018

Outstanding Course! I could always count on Prof.Jianbo to crunch some of the most complex and confusing parts of the course into a much easier understandable language.

Filtrer par :

126 - 150 sur 173 Avis pour Robotics: Perception

par Jesus F

20 oct. 2016

Good course, but assignmets are too long, difficult and with no much help. Workload is overpassed

par G G

18 févr. 2022

Amazing , will give you deep understanding on workings of the 3D reconstruction pipelines

par Xiaotao G

16 déc. 2018

It is hard compared to previous courses and need more time on it. But quite helpful!

par Rahul D

29 mars 2020

I was expecting Some implementation of the SFM pipeline from OpenCV or OpenMVG.

par Mike Z

10 oct. 2018

Really good topic but the material can be improved a lot more.

And it's free !

par Shubham W

13 août 2017

Excellent course!! Especially Bundle Adjustment was covered in good details.

par Jean K G R

24 janv. 2021

In some activities, the theory wasn't enough to complete the assignments

par Ricardo A R

14 févr. 2019

Need more videos for final weeks, hard to follow last week of the course

par Daniel C

23 déc. 2018

To put it simply: Shi's content is good and Danniilidis' content is bad.

par Bhavya G G

20 avr. 2021

Very detailed course. Need to think on your to clear all the concepts

par Aman B

29 janv. 2019

It was interesting, but damn the lectures are never ending.

par yanghui

27 oct. 2017

a bit difficult to understand, anyway,finally passed!

par Ákos G

13 sept. 2020

Good course, but the video subtitles are garbage.

par xiao z

3 mai 2020

need specific feed backs for those quizzes!!!

par li q

10 août 2016

The lecture notes should be better organized.

par Luming

22 sept. 2020

a little difficult for me,but learn a lot!

par Hussain M A

1 oct. 2019

Hard course but lots of good insight.

par Martin X

23 oct. 2016

The courses are good and helpful.

par Ali M

16 oct. 2018

Thank you Professors !

par Yafei H

18 févr. 2017

Unclear explaination

par Fredo C

3 févr. 2019

Great Course!


14 août 2021

so good

par Daniel S

20 mai 2017

This course could use some help. It's a very interesting and important topic and is also difficult, but it could be explained better and the tie in between the lecture videos, quizzes and homework assignments could also be better. Some of the quiz questions are not answerable from reviewing the lecture notes and require outside knowledge of linear algebra and rotation mathematics. The assignments should also be better defined and set up so that there is incremental feedback available for the intermediate steps. For example, the last week's assignment has 5 steps, each of which requires a Matlab function to be written. In many online courses, there are "correct" intermediate results given so that each step can be verified before proceeding to the next step. In this assignment, there is not much feedback until you get to the third or fourth step and even then it's not the best. I had an error in one of the functions, but the problem feedback (photo comparisons) showed it as being OK until I submitted it for grading. It's important, since there's no instructor feedback , to provide some means of checking if you're doing things correctly.Some of the terminology used would be more clear if it was standardized; sometimes coordinates are x and y, sometimes u and v, there's also u1, u2, u3 and things like X = [x,y,z,w] and x = [u,v,w]. Its often quite difficult to know what's being referred to it's called x. I did learn a lot from this course, but it could have been a lot easier.

par Rishabh B

10 juin 2016

The course is a very good overall description of the Perception field. The part I really liked is that there was no haste or a concept just superficially discussed - lectures are long and detailed. The presentation of lectures especially from Prof. Jianbo Shi are excellent - to represent Matrices in colours and give a intuitive sense of every formula(especially the Jacobians and treating the image blending process as painting) .

The bad part of this course is that pronunciations of faculties could be a little unclear and hence a very good transcript is required - which in this course is not upto the mark. There were few mistakes on the slides and should be rectified atleast in the pdf of the slides. What this means is that we have to go through some frustration while watching the video first time which gradually improves on second or third view. Also, there is absolutely no participation of teaching staff. A good content should be supplemented with assistance to further enhance learning experience. Few doubts because of this remains unclear and I wish I could have got this sorted in this class.

par Carlos R

14 mai 2016

I dont like how this course was presented. The professors are good but the way how they present the course is extremely inefficient. I mean, because the instructor only speaks moving hands from one side to other, it was very difficult to visualize what and where the instructor was referencing to. Eg. a figure with 3 formulas and many variables there was no way to know in what alpha variable in formulas the instructor was talking about, once all formulas had the alpha variable. Also, when trying to describe a 3D environment only moving hands, its quite impossible to determine what and where the instructor is. One suggestion to try to minimize this problem would be try to use a lase pointer or a stick or a pen or something similar to help the student to now where the instructor exactly is. One example of good presentation is the course of ML from Andrew Ng where he writes all the things while speaking which facilitates the student to follow the sequence. Hope this can help.