State Estimation and Localization for Self-Driving Cars に戻る

4.7

星

447件の評価

•

75件のレビュー

Welcome to State Estimation and Localization for Self-Driving Cars, the second course in University of Toronto’s Self-Driving Cars Specialization. We recommend you take the first course in the Specialization prior to taking this course.
This course will introduce you to the different sensors and how we can use them for state estimation and localization in a self-driving car. By the end of this course, you will be able to:
- Understand the key methods for parameter and state estimation used for autonomous driving, such as the method of least-squares
- Develop a model for typical vehicle localization sensors, including GPS and IMUs
- Apply extended and unscented Kalman Filters to a vehicle state estimation problem
- Understand LIDAR scan matching and the Iterative Closest Point algorithm
- Apply these tools to fuse multiple sensor streams into a single state estimate for a self-driving car
For the final project in this course, you will implement the Error-State Extended Kalman Filter (ES-EKF) to localize a vehicle using data from the CARLA simulator.
This is an advanced course, intended for learners with a background in mechanical engineering, computer and electrical engineering, or robotics. To succeed in this course, you should have programming experience in Python 3.0, familiarity with Linear Algebra (matrices, vectors, matrix multiplication, rank, Eigenvalues and vectors and inverses), Statistics (Gaussian probability distributions), Calculus and Physics (forces, moments, inertia, Newton's Laws)....

Oct 14, 2019

There are many interesting topics. Without the help and suggested readings from this course, I wouldn't be able to finish by myself. Also, the final project is very enlightening.

Feb 09, 2020

One of the most exciting courses ever had in terms of learning and understanding. Kalman filter is a fascinating concept with infinite applications in real life on daily basis.

フィルター：

by mert s

•Nov 01, 2019

excellent course

by Nejc D

•May 06, 2020

The course covers some interesting and highly important concepts regarding state estimation. I guess the videos are not intended to be a "follow-along" lectures but more of a "these are the topics you should study by yourself" videos. In other words, the videos tend not to go deep, instead only the important results are quickly presented. On the other hand the programming assigments are quite fun.

Reflecting on how much knowledge and understanding somebody needs to show to pass this course I wouldn't rate it as advanced, I would rather say intermediate.

To sum up, this is either a course for somebody who wants to get some basic ideas about state estimation applied to self driving cars or for somebody who wants to dive deep into this topic and wants to use this course as a guidance on his/her self-study journey

by Maksym B

•Apr 04, 2019

The course has very advanced material and I value this course a lot. However I am very confused at some key concepts and didn't understand many details conceptually. For example it is not clear what is the difference between EKF and ES-EKF.

Also, for the final project the formulas have been given. I implemented the project using the formulas, but I didn't understand deeply enough the meaning of those formulas. For example what does Kalman Gain represent.

Maybe the topic is just so advanced, or maybe I should be reading more resources outside the lectures. But I finished the course with the feeling that I have a lot to learn in the space of localization and state estimation.

by Huang, B

•Jul 29, 2019

Great course that teaches you most of what you need to know about state estimation. What is missing is the state estimation using particle filter, it would be great if there is a module dedicated for that. Some video lectures are little bit confusing, specifically at the error state estimation part, but if you read the provided reading materials, you should be able to understand it more thoroughly. The final project is difficult, you are expected to read some advanced papers on state estimation, but it is very rewarding once you figure out on your own.

by Nicolas Y

•Dec 04, 2019

This course is wonderful, however, is it quite tough, not only for the technical content but also because I believe it could use some more clarification for the quizzes and other.

All in all, I thought it was a very satisfying way to review old skills and learn new state-of-the-art techniques!

Recommending it heavily, but be ready for frustrations.

by mike w c

•Jun 18, 2019

There are several errors in the presentations and in the videos, the tutors did not correct them and thus the assignments were very confusing due to stupid math mistakes made by the organizers, it is clear that they are not taking it 100% serious, nonetheless I have seen few courses were they explain State estimation for SDV so good as this one.

by Shubham R P

•Sep 20, 2019

Great course! Very in depth understanding of Kalman Filters and Sensor Fusion. You need to look more literature to understand the concept. Final project is very nice. May be more insight could have been provided about orientation,quaternions and euler angles conversions.

by Atharva K

•May 30, 2020

A pretty involving course.

Good points - EKF, UKF explained properly.

Bad points - The weeks 3 onwards course is not sufficiently explained, less mathematics and more intuitive understanding, tough time if you do not have experience with python programming.

by Yulia M

•Mar 11, 2019

The content of the course is great, very useful and applicable ! The lectures are well told, animations are brilliant. I rate this course as 4 stars due to a low feedback activity from the teaching staff.

by Shrutheesh R I

•Jul 17, 2020

Thank you for this absolutely fantastic course. Kalman filters and state estimation in general is a concept that I've tried to understand for a long time, and I'm glad to have finally understood it!

by Harshal B

•May 22, 2020

A well-taught course by Prof. Jonathan Kelly.I accumulated huge amount of knowledge after undergoing his teachings.The supplementary readings proved to be of great help to ace the final project.

by Farid I

•Sep 25, 2019

Challenging course, specially the assignments. The extra literature resources are great. The explanations and examples on the videos could improve. Step by step Hands On examples would fit great

by Sheraz S

•Aug 13, 2019

For new learners, this course provides the beginner to intermediate knowledge. The explanation with examples are quite interesting and easy.

by Aref A

•Jun 26, 2019

Content is great but lack of instructor support makes the course hard to understand.

by 蒋阅

•Jun 28, 2020

Need more code example or supplementary reading about python and numpy

by Jorge B S

•Jun 30, 2020

Some information was really difficult to understand.

by Ahmad I B

•Jul 31, 2020

Loved Every bit of it. Looking forward to get more

by 胡江龙

•May 07, 2019

good!

by Hongfei Y

•Jul 06, 2020

Very informative about the definition and application about EKF at self driving car. However, I am a lidar engineer who want to know more mathematical and application details about how the lidar ToF data are translated to help with the localization, step by step...

On the other hand, videos kindly provided some of the derivation results of the ESEKF going to be implemented into final project. But the arithmetic process of the Quaternion calculation is quite confusing for the first-time learner and the professor didn't clearly explain the meaning of the algebras used in the videos, such as Cns, q(), capital omega, etc... which cost much unnecessary search time for me to figure them out.

Overall, this is a good course in Coursera Unlimited.

by Salma S L

•Mar 26, 2020

some equations weren't explained and remained ambiguous to me, needs more explanation on the mathematical side, other than that a great course and great effort

by Wentao T

•May 17, 2020

too hard, and the data is not good

by D.B

•Apr 05, 2020

The course content is good, the instructors are good, and the projects are good. But I hate the quizzes and notebooks throughout the course that don't provide better guidance or step-by-step solution checking. It would be much better overall if quizzes and notebooks in the courses either provided step-by-step solution checking or provided the solutions so students could check their work along the way. I’d much prefer the notebooks provide the solutions or most of the solutions and have a difficult final project for each course where there were no solutions given. I’d learn much more through the course and have confidence while completing the final projects, and have a sense of accomplishment that I applied what I learned. I’m so frustrated with this that I’m cancelling my subscription for now.

by Rade

•Jun 07, 2019

Very dry lectures!

Quiz automated grader buggy and not working at times. Example: not well defined python environment for the quiz in module 4. A grader expects a certain format that you have to guess. But to guess you need to submit the quiz in order to see if you satisfied the grader. So you can do that 5 times every our. A lot of time spent on satisfying the grader format that learning material.

The reason I am realty trying to stay in the class is because I am very interested in the subject but the execution of this class is a disaster!

by Andrea B

•Jun 16, 2020

too much high level, no in depth treatments of the topics. There are free course avaiable online which are more in depth than this (paid) course