I haven’t seen such a vivid explanation of the significance of non-Gaussian distributions in localization problems anywhere else. Thank you for the video and the supplementary resources. 👍🏻
this video is so awesome. i love it if an algorithm is shown visual! every step in it makes so much more sense after a little image. Thank you for that
As time went by (like ego motion of robot), your explanation made me converged to the point where I understood the AMCL, kind of like highest probability distribution of the particle filter at the end.
Hey Brian Congratulations! The best explanatory video I have seen from AMCL! You rocked! Which link is hosted the AMCL for opened environments and changeable environments (underwater for example?) very curious to figure out how localization can be done.
The kalman filter does actually not require the input to be gaussian, it just requires it to be white noise. The addition of it does of cause make it esay to work with. Right?
For sure! This is autonomous navigation which means the vehicle is autonomously determining where it is. You can do that without having to also do autonomous guidance, where the vehicle determines the best path through the environment to get to some goal, or without having to do autonomous control, where the vehicle determines the best actions to take to accomplish that goal. So, navigation could be done autonomously while guidance and control could be done with humans.
Oh my god, that moment when it finally clicked. Your presentations are top notch as always!
I haven’t seen such a vivid explanation of the significance of non-Gaussian distributions in localization problems anywhere else. Thank you for the video and the supplementary resources. 👍🏻
this video is so awesome. i love it if an algorithm is shown visual! every step in it makes so much more sense after a little image. Thank you for that
Glad it was helpful!
10/10. Very well presented. Would watch again.
As time went by (like ego motion of robot), your explanation made me converged to the point where I understood the AMCL, kind of like highest probability distribution of the particle filter at the end.
Probably the most pleasant and understandable video that can be found on this topic
That is by far the best video explaining the particle filter! Thank you so much!
Best explanation and visualization I’ve seen so far, thank you!
I think that is the best educational illustrative video I have seen
Propably the best explanation video I have ever seen
One of my all time favorite algorithms, together with RANSAC
I love you so much, MAY GOD BLESS YOU FOR THIS VIDEO!
🤗
WOW, its so legible and well formatted. Anyone can understand this video.
This video was so intuitive and well made. Thank you!!
Highly intuitive explanation. Thanks!
Worth its weight in gold. Great stuff as always.
Omg. Your pt skills is crazy 🙏🙏ty!
Excellent explanation, thank you :)
I appreciate that!
best video I've seen on navigation
what a amazing presentation, this video save my brain
Thank you very for this great video. Please where is the link to the example using MatLab ?
Such a lucid explanation! Thanks Brian!
Applauds for the efforts give into the is video
❤
Yes, Brian Douglas is very dedicated. Thank you for your nice comment.
what a great explanation, fantastic!
Great to hear, thanks!
Very nice explanation, you are the best
Brian you are a treasure!
Good explanation. Cool algorithm. Cheers to the one invented it :)
Very clear explanation
Thanks
Best simplified explanation!
Wow, this video is gold! Thank you!
Thanks so much! Very clear
Phenomenal explanation.
This is very well articulated!!
Perfect as always!
Excellent explanation!
Hey Brian Congratulations! The best explanatory video I have seen from AMCL! You rocked! Which link is hosted the AMCL for opened environments and changeable environments (underwater for example?) very curious to figure out how localization can be done.
very clear and easy to understand!
I'm so excited for the next part
The kalman filter does actually not require the input to be gaussian, it just requires it to be white noise. The addition of it does of cause make it esay to work with. Right?
Great video. :)
How about the speed is increased by time ? Any calculation inside ?
Can't wait to use this on 2b2t
I had to look this up. Apparently, I'm not up to date on my Minecraft anarchy servers!
Thank you Brian!
exceptionally good educational video!
Loved it, thank you such a simple explanation.
Excellent
OMG, thank you!!!
Excellent video - thanks!
Thank you
really amazing video sir! amazing! I subbed again :)
Thanks for the sub!
Thanks!
Too good a presentation !!!
Just AMAZING!
AMAZING
Can we apply same to vehicles that run through road which is not autonomous. Like navigation theough map
For sure! This is autonomous navigation which means the vehicle is autonomously determining where it is. You can do that without having to also do autonomous guidance, where the vehicle determines the best path through the environment to get to some goal, or without having to do autonomous control, where the vehicle determines the best actions to take to accomplish that goal. So, navigation could be done autonomously while guidance and control could be done with humans.
just awesome!
Perfect!!!!! Beautiful!!
Brilliant
This is perfect
Awesome 👍
Sample code of Monte Carlo localisation? Input from CSV file
👍👍👍
You're a boss !
Awesome!!
thank you.. finally i understood it...phewww...
Phenomenal presentation. A+