- 5
- 23 279
Bot Field
United States
Приєднався 15 чер 2020
Have you ever wanted to know how your robot vacuum cleaner figures out how to map and clean your house? Or maybe you've never wondered how complicated it is to control the 28 joints on the Boston Dynamics humanoid (human-like) robot Atlas. Have you ever wondered why mathematicians enjoy their work? Or probably you've never wondered at how many fields of math barely look like math at all. Have you ever wondered what on earth quantum mechanics actually is? Or how a machine learning program actually works?
Complex concepts don't have to be hard to understand. It turns out that for a lot of them you don't need much more than a middle school mathematics education. And many of the concepts are really interesting.
So watch a few videos, and if you have any questions, don't hesitate to ask in the comments.
Complex concepts don't have to be hard to understand. It turns out that for a lot of them you don't need much more than a middle school mathematics education. And many of the concepts are really interesting.
So watch a few videos, and if you have any questions, don't hesitate to ask in the comments.
The Greedy Algorithm and A* | Path Planning
The most efficient and effective way to find a path is A* (A-Star). The Greedy algorithm uses some of the same principles but can end up with a significantly worse path. Why do these similar algorithms end up with such different results, and why are they so much more efficient than Dijkstra's algorithm? Take a look to find out.
Переглядів: 4 017
Відео
Wavefront And Dijkstra | Path Planning
Переглядів 3,9 тис.4 роки тому
Common non-heuristic based path finding algorithms, including Wavefront, Breadth-First Search, and Dijkstra's algorithm. Though not usually used on their own for finding single paths, these algorithms are easier to implement and provide basis for more efficient algorithms.
Occupancy Grids | Path Planning
Переглядів 6 тис.4 роки тому
Occupancy grids are essential in a robot's interaction with its environment and are widely used in robotics. Like many things, though, they have their disadvantages. In this video I'll tell you a bit about why and how they are used, and how they can be improved. And of course you'll get to meet Tango.
Particle Filters | Robot Localization
Переглядів 9 тис.4 роки тому
This is the first video in a series of videos about robot localization. In other words, finding the location of a robot in a map. This method works basically on its own, and I think that's why it's so cool to watch as it works. Interested in exploring it for yourself? The code and download is here: github.com/elstaknis/ParticleFilter The README (click the link above and scroll down) will let yo...
Welcome to Bot Field
Переглядів 3074 роки тому
We did that thing where we worked really hard for a few years to get a college degree. Now we're going to extract all the fun parts and teach them to you. The best part? You only need a middle school level of math to be able to understand most of our videos. So subscribe to learn about the cool things happening in robotics, math, and physics all around you.
most easily understandable video
🦾
Awesome explanation and app developed!
What happened to this channel?
Making these videos took a lot of time, and my method for doing these animations was PowerPoint. Yes, PowerPoint. And yes, it was as terrible and time consuming as you would think. I was also in college at the time, and I just stopped having the time to do this. I may pick this channel back up at some point, but I would first need to learn an actual animation software or write my own
@@botfield2530 Ahh I see that is completely fair enough. Would’ve never guessed powerpoint from your videos… but anyways this is a great channel with very easy to understand videos! May I ask if you’re working in robotics now?
@@botfield2530 I hope you do, because you have an amazing explantation style :) Also, respect for using ppt that must have been hard
Great explanation! This is one of the better explanation videos I've seen on particle filters so far!
2:27 It should be ascending order I think ;) Although for what I know Wavefront labels search space from the goal node and then it would truly be descending order :)
The best video about Particle Filters, thank you so much
WOW!
Terrific!
Very cool
This is honestly one of the most easily understandable videos out there. Thanks!
Your videos are short, interesting and easy to understand. Very helpful video. Well-done! 👍🏽
amazing video you explained this so much better than my professor while also being fun and taking a 1/6th of the time he took
Thanks for the video. Just a quick question: in video, at 3:16, you say "set the center of bell curve at simulated robot's reading". I was wondering if that should be "set the center of bell curve as real robot's sensor reading". That way weights of all the simulated robot's readings will be probabilities using same gaussian distribution centered at real robot's reading. Got confused about it!
great
Have you implemented an occupancy grid map? What did you store your map in? 2 dimensional array or? End up on an OS?
Very helpful video. Thank you very much
Thank you so much for your efforts. It gets more clear with the animations. 🔔
Excellent!
thank you for the explanation!! you really helped me!!
Awesome video, more of this please! Also, code link seems dead
Thanks! Hopefully I’ll have time to make some more videos soon. In the meantime, code link should be fixed!
damn bra u smart as fuk
cool. note sure if you are a female or a kid :)
really good video. can't wait for the next videos
Great video...
great. thanks