2018 Taiwan Half-size micromouse 2nd prize winner - Ning6A1

[@AlwaysExtraCrispy]

The mapping is insane. Especially the parts it remembers it can cut through at speed. Crazy.

[@DerusGrindz]

The pattern recognition of such a tiny device is insane.

[@davelowets]

Na, electronics are getting smaller and smaller every day.

[@Bloodlf]

@@davelowets yeah it's might not even be a custom chip they do them really small nowadays

[@b_2u]

The point is, the shortest path may not be the fastest, since this little guy can reach insane speed on a straight line

[@DerusGrindz]

@@davelowets still pretty good imo

[@user-qw9yf6zs9t]

@@b_2u then just take that to account probably not that hard

[@rickmatt3423]

With all that intelligence in the room, it's nice to know that someone can still mount the camera upside down.

[@Fiufsciak]

Nah, it's just Australia, bro. In Singapore.

[@shamsghani8346]

Its upside down because its mounted to the roof, the camera probably has a mount on the bottom, so they just mount in inverted and flip the video later. This is also common practice with projectors.

[@icarogillead4654]

It's on the other side of the world, that's why it seems upside down

[@DeezuLL]

🤣

[@apocalypticdaze2139]

Not so intelligent, there no doubt all still spinning around at a 1000mph on a nasa ball.

[@benosonline]

I thought the first go where it was learning the maze (I believe) was the actual run and I was very confused. Then he zipped through the fuckin maze like a champ and it made me happy.

[@applemauzel]

It's the best of 5 runs. So contestants tend to throw the first run to have the micromouse learn the map and find the most optimal route.

[@whateveritis3103]

@@applemauzel thank you,I had absolutely no idea wth was happening,no idea why this was recommended. Lol.

[@SilverScaleMA]

@applemauzel yeah, there was one I watched that was the winner for that year (I want to say it was 2015 but I am not sure) That the first 3 runs were pitifully slow and constantly going in circles/dead ends. Then the 4th and 5th run was a breakneck blur to the end and back. You could hear the jaws dropping in awe. 😆

[@wwerty234]

Same!! I was like this is not impressive at all and then it happened! I’m glad I continued watching

[@7esseanime]

I've never seen this, but it's fascinating. It's like looking into a person's thought processes. I love it.

[@Zhengrui0]

You flatter humans, really

[@ababab28]

@@Zhengrui0 We might be worse at memorizing mazes, but I'd like to see that little robot mouse design a little robot mouse that can memorize mazes.......

[@joysean21555]

Anyone else marvelling at the code/automation script written for this and the amount of corner scenarios they'd have covered to tackle every possible situation ❤️

[@amitsaini1181]

It's backtrack !

[@godlyvex5543]

edge cases

[@Tea20024]

@@amitsaini1181 what’s backtrack ? Can you elaborate

[@amitsaini1181]

@@Tea20024 it's using backtrack algorithm to finding the final path to reach till goal. It will not repeat the same path again and again. 🤗

[@Tea20024]

@@amitsaini1181 cool. are you aware of any site where i can get more info. checking google as well

[@ka7ao]

I swear I have no idea what in the hell I am doing here or watching...but it is fun

[@R0BERTMAY]

Yup... its 00:45am. I have no idea!

[@brewcoffee0]

Yep...4AM

[@shashank4297]

@@R0BERTMAY wtf! I just read your comment and it's 00:47 am

[@tinsku332Xd]

@@brewcoffee0 4.20am for me :D

[@Isaac-LizardKing]

the sophistication of the device itself is what amazes me. i’d never have the equipment nor the material to make a robot that compact

[@bodaciouschad]

@@owenedwards8514 grip and precision are 9/10 the mechanical requirements... then a microprocessor and several distance sensors are going to have to fit into the micromouse... Theres a fair bit more that goes into it than "just buy an rc car". That only gets you as far as having a chassis, power supply, motors, wheels (they'll be shitty slippy plastic wheels and you are going to have to replace them) and you'll have to rewire the motor/motors to be controlled by an onboard processor instead of radio... It'd make more sense to start from scratch, imo.

[@sandeepr7141]

nor the brain power.

[@CarlosFlores-nl4gg]

@@sandeepr7141 this is just mean for no reason

[@sandeepr7141]

@@CarlosFlores-nl4gg Nop. It would only be mean if I called him stupid. There are 3 possibilities: 1. Really smart 2. Mid wits 3. Stupids Since most of the people belong to category 2 and it takes a smart person to create something like this alone, my statement is not an insult.

[@CarlosFlores-nl4gg]

@@sandeepr7141 still unecessary

[@hutaomainkai]

Anyone else from their recommended page?

[@hariseldon3611]

ezzyisonfire no

[@aggabus]

Yep

[@MrRoseandrc]

Just now 12/8/2019

[@rhomarklim9371]

Oh yes. March 31, 2020 Didn't know there was something like this.

[@hrishabhgour4149]

Just now

[@outsidethepyramid]

all that tec but they can't put the camera straight.

[@handtimmy]

@Masked Singer yeah but they are Taiwanese not Chinese

[@dude9326]

@@handtimmy one and the same

[@鴻鈞林鴻鈞]

麥歐北供

[@chester9116]

@@dude9326 Its like assuming Canadian as American. Just states that you're ignorant lol

[@Roflcorso]

They see it with other eyes dude. It is straight for them.

[@Nainara32]

I love the precision of these robots.

[@junho0525]

Impressive. Soon after the mouse explore the maze, it immediately integrates the path to find shortest path based on its experience. As a neuroscientist studying spatial navigation, I'm deeply curious about what kind of learning algorithm they(he?) used.

[@suhu9379]

Once the mouse had kept enough maze wall information, it would use the A* algorithm to find the shortest path with diagonal routes.

[@junho0525]

@@suhu9379 @JUING-HUEI Thank you for answering my question! 😄👍 We know that there are specific cells that encodes specific location, direction, borderness, ect., but how brain integrate those informations to find a way from one place to another is still unclear. If I read your paper(I've found some) and I could understand it(hopefully), it may give some interesting improvement on my project. Again, thank you, have a nice day and happy new year!

[@lovacc_1967]

@@junho0525 I guess our brain is just a biological microchip we can delete information that is not necessary to be used or choose to forget it

[@realsushrey]

@@lovacc_1967 What you are saying is roughly correct, however, human memory in general functions quite differently from computer data storage, even though both hold information. It is good to be careful about the computer-brain metaphor. They are very different things.

[@tesscrelli783]

First run: around 1 min, announcer didn't announce exact time Second run: 6.869 seconds Third run: incomplete Fourth run: 6.469 seconds Fifth run: incomplete I believe each competitor only gets five runs, bad luck that this guy had two incomplete ones.

[@heroclix0rz]

It seemed like he was cranking the speed up and down, and cleaning the wheels as much as possible for traction, trying to see how greedy he could get. The last run looked like a last ditch crank to 11.

[@TheThursty100]

I think the first run doesn't get time announced because it's the robot learning the maze. That said, how fast the robot can learn the maze would also me an interesting metric in such a competition

[@greengoat5654]

The way he's pushing it it's probably the best of time

[@CW91]

@@heroclix0rz maze competitions should let contestants make the software only, and they load their program into the same hardware which is shared by all.

[@carlosho9376]

I wonder how the maze is designed to have those diagonal line routes. The visual effects are amazing.

[@tebanots15]

2:56 when your GF tells you that she's home alone.

[@xGNxk3g0]

The code must be beautiful 😍

[@Rosielx]

I was thinking the same.... probably a breadth-first-search tree algorithm

[@amey7064]

Its a flood fill

[@timkuitems4431]

I agree. I don't code, but sure would like to see how that side of things works. There has to be sensors involved too. I wonder if there are location sensors in the floor of the maze? Or do they use vision sensors only? That would be amazing!

[@2000blobfish]

@@timkuitems4431 likely 3-4 distance sensors (I would guess ultrasonic, but laser distancing is also a possibility) corresponding to the cardinal directions on the mouse. The really impressive part here, imo, is the remarkably precise control loop running the actual motors.

[@glashoppah]

These things are nuts. Are there any good sites for seeing how the robots are constructed?

[@savvasgamingchannel5062]

The robot mouse loves solving this maze at lightning speed!

[@yoyohanaBR]

The memory it has is absolutely incredible

[@mattweger437]

Quite literally perfect lol

[@pic18f452]

I don't understand motion planning and this is very impressive. Do they use hidden Markov model in deciding which side to go?

[@suhu9379]

We use flooding algorithm to find a path to the goal area. kzbin.info/www/bejne/naioZnuoj7iEpsk

[@pic18f452]

@@suhu9379 thanks very interesting approach. One more question, how does it create its own reference points or local map? Does it purely rely on its on-board sensors with a dead reckoning approach? Or does it have a "global" reference like ultra wide band system or something similar?

[@suhu9379]

@@pic18f452 Array variables are used to store the maze wall configuration. The starting cell for micromouse contests is always located at one of the corners of a maze, and the goal area will be at the right hand side when you stand near the start cell and facing the maze. This means that you can use two dimension coordinates to locate a maze cell, which is 18x18cm or 9x9cm. For classic micromouse mazes, which is 16x16 cells, we will set the coordinate of the starting cell to (0, 0). The goal area consists of four cells which are (8, 8), (8, 9), (9, 8), and (9, 9). For half size micromouse contests, the goal area will be designated before the contest begins, such that we can put them into the algorithm.

[@anu3097]

I have no idea what I'm watching or why I'm watching this but it felt nice to watch. Thank you KZbin algorithm

[@fanirama]

Fuck. I was impressed very much with the first run and then it blew my mind. I hope we don't program these into killer AI robots. We are finished

[@Tao_Tology]

"I for one welcome our new robot overlords"

[@grelm1322]

We absolutely will. All technology becomes weaponized in some form. Just what we do

[@helmutalexanderrubiowilson6835]

last run was amazing.. Im wondering how do they achieved to map all the maze?

[@suhu9379]

We use grid map for the maze. For example, a two dimensional array is used to store the maze wall structure.

[@helmutalexanderrubiowilson6835]

@@suhu9379 Interesting thanks for replying

[@ReynaxisSolutions]

I thought at first whatever it was doing during the first runs is just wasting time. But i think that it being slow in the beginning was on purpose while it was mapping out and saving infos about the corners and trying to calculate the best route to the yellow box. In the end, when it was re-released into the maze, it had the fastest way figured out.

[@ChillingSancharies]

I don't know why yt recommended this for me. I dont even know this type of games are there. What an intelligent programming. Happy with this recommendations

[@index7787]

Want to see this but with quads in 3d cube mazes. That math is actually insane.

[@justincase4812]

Not really. Build a tree/network and then prune it to build a shortest path (Dijkstra's)

[@joegerkrep7727]

@@justincase4812 shortest path =/= fastest (long times at high speed is better than stop and go turns for a shortest path)

[@justincase4812]

@@joegerkrep7727 Did you seriously think that someone who suggested to use Dijkstra's algorithm wouldn't know that? Jesus FC, modify it to include parameters.

[@justin9571]

@@justincase4812 It's never nice to see someone being stupid, but it's definetly worse to find proud and stupid. Maximum speed gained from a particular run of edges is not a parameter of a particular edge. It is still not nessicarily a parameter of (strictly) previous edges (from a fixed starting point), so there's no way dynamic programming can save you in this case - you'd have to compute the maximum speed with a *new* search from each edge (rather than the origional starting point). If it wasn't bad enough already, you *still* couldn't even get away with pre-computing all the max-speeds at each edge (in a manner that would be useful), because each max-speed at an edge is dependent on your previous path, so not only are you doing a tree search at every edge, but you're doing it for every *path* to each edge, so there goes any DP potential you had. With some reasonable heuristics you could probably get that tree search at a particular edge to be constant time, most of the time, so you'd still end up in Θ(n^2) for the entire thing, albeit with a constant factor speed decrease over typical dijkstra that would be bad enough in 2D, but would triple(?) in 3D, as you're searching 26 directions as opposed to 8. Point being - the notion of using a greedy algorithm with a parameter that isn't trivial only ends up with the combined drawbacks of BFS and DFS with the benefits of neither. I'll give you credit for novelty, this is the first time i've heard someone suggest putting "parameters" in this fashion on Dijkstra, but lmao I hope this will also be the last. if you find yourself googling "best algorithm for (task)" to back up some stupid idea you didn't think through, don't be rude to people like joeger who clearly know more than you and just take the L.

[@justincase4812]

@@justin9571 Excuse me? What a vitriolic display of pedantry - a complete hypocrisy on what you are hilariously accusing me of. But if that wasn't all.... No one is talking about dynamic programming, no one mentioned any of that which you have gone WAAAY out of your way to introduce strawaman after strawman. You must love talking to yourself. I don't have as much time as you do to write such a shameless vitriolic essay, however it is absolutely possible to determine max speeds at every traversed path. How can you possibly not undertstand that whether in 2 or 3-space. You ought to be ashamed of yourself.

[@SootherousNoise]

Why is this so mezmerizing to watch!??

[@noorazmi2329]

because we are dumber than we imagine ourselves.

[@siddharthahire4004]

I'm dying to know how it works!

[@alexandregagne4151]

How much can cost a micromouse like this? Can I buy one in a kit?? I really want to learn how to do this and that fast :) Very good video. Thank you very much.

[@davelowets]

No. You have to build one

[@bodaciouschad]

The entire project could cost under a hundred to several hundred dollars depending on what corners you are willing to cut, parts you use, experience and frugality, etc. The components list looks something like this: high traction tiny wheels (drivable axels included, presumably), motor/motors, at least 1 distance sensor array, a color sensor to determine when you've found the goal/start, some mechanism by why you will turn on a dime (preferably this means reversible drive along each side of the mouse which would be easiest to accomplish with 2 reversible motors), battery, wiring, microprocessor, emergency buttons for cutting power, resetting logic, etc. If you are a cheeky mofo, you'd say "ok, my first run will right turn + gap skip rules the whole maze to map it out, then my second run will calculate the exact trajectory needed to fling the mouse directly from the start to the goal and back to the start using a spring loaded chassis.

[@KETANRAMTEKE]

It moves like a fish 🦈

[@istg5619]

so you're telling me there's no one controlling the mouse? all by the program itself?

[@sugadevanarr1]

What sorcery is this? How I missed this for years?

[@gokukn2336]

wait.. what is this game called..? i ve never see this before.. what is that mouse thing, a robot? how its go and came to the same place automatically..?🤔🤔🤔

[@sinaesthesia6303]

Goku KN Magic.

[@e0505ee]

Is this a maze game for robots? It seems that the time is from the start point to the end point, taking the shortest time score.

[@malcolmmutambanengwe3453]

@@e0505ee Yes. The micromouse does not have "eyes" so it must remember every turn and try to get from start to finish in the shortest time.

[@오지훈-b3j]

With front right left three sensors, it make its own map in 1st try and than calculate the fastest doing all of it with it's ai

[@advertiserunfriendly]

Math

[@geez8780]

Is this a cctv footage?

[@Tea20024]

How did they program it ? What’s the logic ? Real impressive stuff . Does the car already have a map of the puzzle ??

[@suhu9379]

The firmware programs are all flashed into a microcontroller on the robot, which includes motion control, path planning, maze solving algorithms. The mouse robot uses infrared sensors to find out what the maze configuration is and keep them in the memory. The sensors sense the environment from 1000 to 10000 times per second. Your may check the contestant's simple introduction about his mice in sites.google.com/site/ngbengkiat/Downhome/Topic1.

[@Tea20024]

@@suhu9379 thanks!!!

[@raude111]

No se por que youtube me recomendó este video, pero me gustó.

[@justincredible9302]

Its insane how quickly and naturally it moves at full speed once it knows where to already go.

[@unusualvideos8269]

Has anybody noticed the maze was held in 2018 to the left bottom corner 👍

[@___OmerAJ___]

how much the prize?

[@baguettefish]

Why is the text in the upper right corner upside down ?

[@suhu9379]

It’s our carelessness in using a dashboard camera to record this video.

[@DominickQuaye]

I am interested as to how this thing was built. Is there any place online where I could find a cad or pictures of this design?

[@suhu9379]

You may find the circuit diagram and PCB layout via the connection maintained by BengKiat Ng. sites.google.com/site/ngbengkiat/Downhome/Topic1/ning5

[@DominickQuaye]

suhu9379 thank you so much!

[@PackNshipp]

Something like this could be used for cave mapping?

[@suhu9379]

Cave mapping is more difficult I think because of its arbitrary shape, infinite size, and 3D information. Micromouse map is limited in its size and confined in a 2D space.

[@lachlanokeefe8020]

Very cool, but isn’t this mostly a use of a* as well as some admittedly impressive robotics for the sensors?

[@suhu9379]

Yes. The contest also serves as a target system so that students can try to integrate their knowledge and skills. They could also learn from competitive contestants those brilliant ideas in implementing the winning robot.

[@lachlanokeefe8020]

@@suhu9379 awesome, thanks for the reply.

[@RazaPlaysGames]

2:54 was just epic!!!!!!! 4:05

[@qwertyqwerty5018]

Those machine learning algorithms and the data on which it is trained are so cool.

[@mooiijloup]

Need to see it in three dimensions challenge

[@suhu9379]

It is a great idea for micromouse.

[@gaborkovacs8765]

I never seen something like this before! What is this? If this little something, have a memory, to safe and remember the track, is very impressive! 😲

[@suhu9379]

It's called micromouse contest. There are two categories, classic (~40 years old) and halfsize(~10 years old).

[@gaborkovacs8765]

@@suhu9379 thanks!

[@alib8396]

@@suhu9379 can you please elaborate

[@samre3006]

Is he petting the mouse after each run?

[@suhu9379]

He tried to remove the dust on tires, such that the robot would not skid at high speed turns.

[@JuneJulia]

Who came here after watching recommended-out-of-nowhere 2016 contest video?

[@traceretsu]

How does the robot know he reached the goal? It is because it's the only square in the maze, the different color wall or something different?

[@suhu9379]

The participants would know before the contest date where the goal area is. For example, All Japan micromouse contest declared the goal area information on their webpage. www.ntf.or.jp/alljapan2022/

[@DaniPro-zc4xz]

hello how do you get one

[@zsavage1820]

so when it makes it... do you give it some new battery instead of cheese?.... just curious on what it gets for making it....

[@davelowets]

Nothing, it's a machine, it doesn't desire anything

[@Stuff_And_Things]

I find that alternating left and right turns at intersections will get you out of most mazes. I haven't found a maze that hasn't worked with yet. As far as finding a point in the center I don't know. My motivation if I'm in a maze, is escape.

[@suhu9379]

We never tried this idea before 🤔. Whenever a dead end is met, we often use flooding algorithms to find a new path to the goal area, and continue to explore the maze.

[@dalea1691]

The award should go to the creator of that maze.

[@nagarjunvinukonda162]

What algorithm is it using?A-star?PRM?Djkstra?...

[@MauricioSetz]

Where is the first place winner

[@bmg2k12]

2:10 when even robots reject u.

[@kellengaskill2085]

Miami Spotz was that a joke?

[@leonathan0862]

@@kellengaskill2085 of course

[@compresswealthdivideeconom3757]

Is it not shorter going up the right side then to the left and back to the right a little shorter?

[@emielverbeeren8181]

Acceleration seens to be a big factor here too. The route it takes has longer straight pieces so it can go faster.

[@bryanmayfield7916]

How did I get here??

[@81freewilly]

Do they have put stop as well?

[@suhu9379]

What do you mean by ‘put stop’?

[@rahhannan9171]

real mice ?. i never saw it closeup

[@GarhwalTrader]

How it is moving on its own can someone tell me plz?

[@joannaforthewin]

On the bottom left it writes 2018.

[@pikasnipe1]

Whats the masking tape do?

[@wrestleswithangels]

Where can you buy one of the mice?

[@seemlyme]

You have that much Time ?

[@dushkin_will_explain]

По поведению видно, что оно не только распознаёт образы, но и строит модель местности, причём некоторые гипотезы о состоянии внешнего окружения принимает на основании эвристик. Прикольно.

[@KacyCodes]

Looks like a depth first search algorithm. Explore a path as deep as you can, and when you hit a dead end, backtrack and try another unvisited path.

[@braiandeivid]

Is it an Deep First Search?

[@suhu9379]

BengKiat said he was using the A* approach to search.

[@braiandeivid]

@@suhu9379 thanks!

[@ha1d0g]

Why did i think he was controlling it with the tape

[@richardsalzmann7946]

Taiwan is a country?

[@suhu9379]

We hope so, but the China and the United Nations do not agree😅.

[@ginaldyzz]

2nd ? where the 1st place ?

[@dichosonaljon5273]

Whats.that?its controlable?

[@OscarMaris]

was he slow?

[@recuperacaorecuperacao7329]

*What is this?* What is this thing yellow on the hands of man? Why he "put" the "mouse" on this thing?

[@drewcliff82]

Idk what this is or why I'm watching it but it looks pretty awesome.

[@NullScar]

You got the year wrong. *It's clearly 8102.*

[@csm8245]

This was in 2018, why does my lawn mower robot from 2021 gets stuck and confused all the time?

[@Silent_Control]

amazing tech, great work Juing Huei

[@gavincurtis]

Like the way it turns round at the end to be picked up; like a real animal expecting a reward

[@suhu9379]

When the mouse comes back to the starting position, it would either be confident in finding the shortest path or just finish dashing from the starting position to the goal area. That’s what we thought at the contest. You give me another viewpoint, which is also great!

[@kedericzaizai3949]

What use?

[@Civil_inside]

What is this

[@satyajitmahapatra9487]

Its so interesting and equally amazing as spacex.

[@donaldzee]

What is that?

[@Experdao]

What is this?)))

[@compresswealthdivideeconom3757]

Programming the dimensions of the board, some of the turns would be uneccesary. A slight improvement could be made.

[@elijahbuscho7715]

You're talking about when it's learning?

[@MrHaaan]

I wonder what the 1st prize winner did.

[@K1llb0t]

The little micromouse is just like me whenever I play a new metroidvania: starting slow exploring every possible paths and even going back couple of times where I've been, and later just skipping every area like if I live there

[@inversei8287]

If this 2nd, where's the first 🥇?

[@小魚吃蝦米]

這是機器學習,並找到最優路徑用最短時間到達終點並回到起點嗎?

[@suhu9379]

沒有用到機器學習啦，黃明吉老師用的是A*演算法來找最短路徑。

[@小魚吃蝦米]

@@suhu9379 謝謝解答疑惑.

[@rimshaaiman3098]

Hey!! I enjoyed this thoroughly! There are a couple of harsh comments, don't get bothered with them though. You doing great!!

[@dcn8375]

Wait so is this a mouse or nah???

[@mydogcoda9072]

This is a thing?

[@bosantidurnich986]

What was that?????

[@invictuz4803]

4:55 he felt his entire life's work crash and burn in that moment.

[@saladinhamza2271]

wow you kill me taiwan respect from algeria i want to know how this mouse works ?

[@BigL10000]

She knows how big the whole thing is. Then in the first round she explores it and makes a map. After that she calculates the fastest way . Not that difficult

[@kallewirsch2263]

adding to what you know who already said.The hardest part is to get it to run straight and to do precise turns

[@eliasoeliaso4493]

@@thealchemist5376 LOL

[@gr8t1bobo]

Does it bother anyone else that it has 2 possible routes?

[@陳政宏-k7b]

自動認路嗎

[@suhu9379]

是在探索迷宮終點的同時，記憶迷宮的組成，並且盡可能找出多數可能到終點的路徑，再用演算法找出最短路徑。

[@suhu9379]

這是模擬的演算法。kzbin.info/www/bejne/ap2UqJiBma19qtU

[@snapforge]

Anyone else notice "2018" written on left bottom of board

[@thomaswayne4655]

Welcome to yet another episode of WTF si this doing un My recommended videos..