Posts Tagged ‘Robbie the Robot’
Wall-E is probably the CUTEST robot ever. (Except for my Styrobots, of course!) The way he says his name ‘WwwwaaallLL Eee’ is irresistible.
I see Wall-E everywhere. And, much to my joy one day… I looked out the back window, and I saw Wall-E! This means that at least once per day, I get to see Wall-E! WOOT!
I really can’t wait until this movie comes out!! Imagine how cool Epcot will be, too. Meet the Robinsons + Wall-E!! It’s quite crazy how Pixar is just doing better and better with each animation they make. I really never thought that anything would be better than Finding Nemo, ever.
One of the things I can’t wait for is the robot! Er well, I can’t wait for me to gently tear apart the robot and hack it OR make it run on an Arduino! How cool would that be?! Having a Wall-E working off of an Arduino, connected to Processing. I could have all sorts of ultrasonic sensors… personalize it… make a conversational program (based off of Robbie the Robot) for it… WOOT!
Check out these two videos – they’re REALLY cool!
Wall-E Spotted in LA! from Blink on Vimeo.
Robbie the Robot, a human-machine conversation computer program I developed, has the capability aid autistic children. I’ve been thinking about this intensely for the past few weeks. Today (March 28), much to my excitement, my favourite podcast – Talking Robots – features guest Kerstin Dautenhahn!
This is what they say about her…
Kerstin Dautenhahn who is Research Professor in the School of Computer Science, Faculty of Engineering and Information Sciences at University of Hertfordshire in the UK, where she is a coordinator of the Adaptive Systems Research Group. Autism is a developmental disorder affecting around 91 people in every 10,000, mainly causing difficulties in social interactions, communication and imagination. Using therapy robots in the AuRoRA project, Dautenhahn has been pushing autistic children to learn essential social skills such as turn taking, joint attention and imitation. Armed with a lot of patience and zeal, her team has been adapting their robots and therapy sessions to each individual child, whether it’s about playing with wheeled robots or Dautenhahn’s toddler-sized Kaspar humanoid. She also presents her new project on Interactive RObotic social MEdiators as Companions (IROMEC) which looks at how autistic children can learn to cooperate and interact with each other through the introduction of a robotic mediator.
So, I listened to the podcast a few times and took some notes…
- A person with autism has several problems interacting with others
- It’s a life-long development disorder
- Problems social interaction and communication
- Problems understanding facial expressions and body language
- It’s a spectrum dissorder
- You can have withdrawn people to very able people (different sides of the spectrum)
- Children with autism enjoy interacting with robots as much as any other person. They’re realy fascinated by it. // This is a great fact, especially for the future development of Robbie the Robot
- Since they were interacting with an autonomous robot, it was completely open! – No concrete hypothesis.
- Found they are very very very interested
- Enjoy interacting with it
- No fear interacting with the robot or touching
- They were smiling, and very keen.
- Autistic children have problems with behaviours like joint attention and immitation. Designed trials, to test this. Particular aspects of behavioural aspects.
- What they did in their work with a humanoid that was able to move its arms and legs:
- Children could interact with robot by similarly moving arms and legs
- Child became more interested, immitated the robot and innitiated the interaction
- If the robot was unable to do that behaviour, child would try something different
- Imagine not being able to know turns for conversations… turn taking in special need schools is what they are teaching // A key target for Robbie the Robot!
Robots are not a replacement for people. // AGREED!
- Human-human interaction is very complex
- Posture, body language, facial expression…
- Tone, politeness, rules, queues
- … we are to interpret them in a social way
- For example: Do you know what time it is?
Yes, it’s 4:30.
- Social correctness is the last one
- You need to interpret what you hear and interpret their behaviour
- Very difficult for a person with autism
- Humanoids are not as complex
- That way, you can use one to slowly teach the child
- First you need to connect, and get the child interested
- Lots of results have to be published on how children can imitate or use joint attention
- More clinical study is needed
- Types of robots
- Different types are suitable for different children
- Low functional end – successful mobile robot engages attention. (Applied AI Systems).
- Simple, robot moves around and has heat sensors and IR sensors
- Chasing, tag, run around, etc. Very very very simple robot
- More abilities, imitation … humanoid shape.
- Designs and types of behaviours you want to explore.
- Casper has facial expressions, it can turn its head, move arms, produce gestures, play peek-a-boo.
- It really depends on what groups of children you are dealing with
- Communication and interaction skills produce more challenges.
- All in all, start with what you know about the child, and design objectives of trials for therapy for the children
- Robots are individualized! This way, you can hope interaction capabilities develop
- Different types are suitable for different children
- Challenges from the Robotics point of view
- Nature – important that robot is predictable
- Scenerios are unconstrained
- Sensor system has 100% reliability
- More autonomy
- Summary of results
- Children respond to a robot differently to a non-robotic toy
- They are comfortable, they learn imitative behaviour, use robot to show joint attention
- Emphasis on mediation aspect
- Social mediator. 1 Robot, 2 children. Communication and interaction between the children
- Collaboration is very difficult for a child with autism
They use what they learn with the robot outside of the class.
- Although solid evidence is needed, there is big potential.
Robot assisted therapy is a growing area! Commercialize these robots. Here comes Robbie the Robot!
After breezing through all of my notes taken during this podcast, it becomes extremely obvious that Robbie can fit snuggly in a robot assisted therapy with an autistic child that is able to communicate, but sruggles slightly to keep a conversation going.
Now, the big question is how am I going to make Robbie to the point where it is extremely intelligent and can assist autistic children?
- Use and exploit language models – be sure to include anything that can happen, as it might happen
- Work on continuous speech recognition – this way sentences can be heard
- Convert what is heard into a probable sentence – if what it said was wrong, the child might correct it, where then I can monitor and adjust it accordingly
- Add some algorithms to advance the conversation according to the number of times Robbie has conversed with that particular child, and for how long — this way, Robbie will be able to ‘coach’ them to have a normal conversation — Once they are able to do so, they won’t need Robbie anymore!
- Create a teddy bear, or bubble boy physical device to make it seem less frightening — however, that would have to be tested, as maybe they would be more frightening that just a laptop
It definitely requires some thought, but I’m up for the challenge! ;D
Softpedia just awarded Robbie the Robot (version 022) a SOFTPEDIA “100% CLEAN” AWARD!
That’s pretty neat! I never knew they had those. Although, I have to admit, Robbie does have a virus … a virus to become potentially addictive! Ahah. But really, no viruses or spyware or adware. No memory leaks either! And it is 64 Bit. ;D
Well done Robbie!
4:45 AM – 1234 by Feist! Woowoo! Stayed in bed because I was having a dream about talking to Robbie, have to finish the conversation…
4:50 AM – Awake
5:00 AM – Watch goes off! It gets louder as time passes.
5:09 AM – So, I played around with Arduino on Xcode on my other laptop last night. I’m figuring that the speaking character view, the one that makes Robbie open and close his mouth, could have a pipe which would lead to the terminal so it could go something like
Which would upload the program onto the Arduino.
I’m not exactly sure yet how I’ll have it talking … a wire running out of the back of the stuffed animal to the computer doesn’t sound like a good idea to me :S Maybe I’ll get a bluetooth Arduino and a small wireless microphone. So really, you could have a server farm (hacked Apple TV) in one room, with a big USB hub and multiple Robbies open so that many people in one room can converse with their open copy of Robbie. Only problem would be getting the Apple speech event handler to not be confused, esp as it blocks out all other applications. Maybe I could have Robbie record the sound (speech), then ‘parse’ it. While the computer would be processing, the stuffed penguin would move its arms up and down… hopefully the processing time wouldn’t be too long! But then again, if you have 20 of these stuffies running at one time, it is possible that the computer would run slowly…
Maybe I can create multiple Apple event listeners… I can see it now! The tiny blue bubbles all across the screen (wow).
5:21 AM – Goes downstairs to eat. Or at least try to.
6:17 AM – Left the house
7:00 AM – Arrived at the school
7:10 AM – No one is here, and there’s nothing to do, much o_o
4:30 PM – Awards ceremony
8:10 PM – Arrived home
All I can really say is that I’m extremely disappointed in the MRSTF – no comments from the judges (there were FIVE judges), 2 of them didn’t speak my language, and I’m sure even more didn’t even READ the report. How can I go from a project, last year – that compared a light sensor and touch sensor – to this whole Robbie Robot and do worse? It has so many possible future uses! I wasted A LOT of time, and more importantly I wasted A LOT of other people’s time. I did worse than failure, in my eyes. So if we learn from failure… does that mean I learned close to the ultimate answer? Lol!
That’s pretty much the way I am thinking about it. I have the ultimate answer, so I’m still going to work on robotics – but you’ll pretty much have to pay me to do another science fair after this one — or at least ensure that the judges are qualified. I’m planning to work on Robbie until I get to version 500. (By version 500 I hope to have continuous speech recognition). ^_^ Yay!
I’m going to go to the store today to get a bigger breadboard and some wires – and some squishy things… I’m going to make my own Keepon… I’m thinking of a pink snowman! With glitter! Haha.
Congrats to everyone that participated!
But, just to put this whole experience in perspective in one sentence- they stole our support our troops sticker off of our car.
It’s JUDGE DAY! Wooooooooooo!
4:45 AM – …And the wake up music is Bubbly by Colbie something… YAY! Well done iPod again – the random algorithm is really doing good
4:50 AM – Check results of Robbie Robot downloads … I broke the 1,000 mark!
4:57 AM – Looked and spy’ed to see what IP my computer is and where StatPress thinks it’s from – the flag is Canada, but it thinks it’s from Saudi Arabia! The ISP is correct, not sure how it gets SA! xD
5:00 AM – Watch goes off! Time to wake everyone up
5:02 AM – Time to get ready wooo wooo!
5:12 AM – Waiting for Dad :/
5:13 AM – Attempts to go downstairs… but hears a squeak and it’s too dark (even with my iPod as a flashlight)
5:40 AM – Time to get dressed
5:50 AM – Eat and drink (a bit — not really hungry)
6:10 AM – Put the bags in the car and got ready to leave!
6:15 AM – Left the house!
7:20 AM – Arrived at the school, yay
7:35-8:20 AM – Wrote log in the actual log book as opposed to my commonplace book
8:25 AM – Went into the gym and set up
1st judge – Remote control for Keynote presentation didn’t work However, judge didn’t understand anyway – I’m thinking that he’s anti-machine as he was absolutely repulsed at making friends with a computer or having a conversation with it. He didn’t speak English very well, either.
2nd judge – Rebooted my mac a few minutes before, but it was still was loading up when he was asking about my project. The remote worked though! But my ‘tardiness’ of the presentation probably lost me 10 marks, at least! In the end, he didn’t understand it.
3rd judge – A programmer! Awesome! He really liked the source code of Robbie, and how it was made on a mac. This particular judge knows C, Java and does some PHP on the side.
4th judge – I actually can’t remember this one for some reason. All I remember is that he wanted me to sit down with him, which was pretty neat! It was either this judge, or the next one, that asked me about Turing (who he was, why the test is so special, etc. etc.). He liked Robbie!
5th judge – This judge was astonished that I used Keynote. I was actually taken aback when he blurted out ‘Hey! That’s Keynote!’ I had to pull myself to get back to the conversation about conversations, instead of having a conversation about how much fun Keynote is. He really liked Robbie. At the end of it all, we were checking out iMovie to see if I could remotely fix his .AVI problem. It turns out that there’s some new encoder of .AVI’s, or something. Neat!
12:00 PM – Took a peak at some of the awards in the booklet. Only 2 people can go to ISEF. That’s pretty tricky! I really hope they choose a computer science project. Personally, I REALLY want to go as I want to be CHALLENGED! I’m eager for a challenge, difficult questions, and some computer scientists to nag me about my almost-OO code! McGill has 4*250 EE & CE prizes. They also have 2*100 CS Robotics awards. Concordia has a paloozle of awards, for instance 2*250 outstanding achievement in CS, 2*250 outstanding achievement in EE & CE, 2*250 women in engineering & CS, 2*250 faculty of engineering & CS award. Wow, so much CS from Concordia! I’m really amazed at how there is so many biology awards, it’s quite crazy. There is also the Ecole Polytech award (that I won last year). It will be nice if I win something, but I’m really not expecting anything. If I do win something, it will go towards books from amazon.com! I’d love to read more stuff!
12:30 PM (After lunch)
Profound Passerby-er #1 – This person knows Pascal AND Assembly! I was completely astonished. Assembly is like… the toughest language out there! It actually turns out that he used his Pascal program and debugger to create an Assembly code. That’s extremely neat! We talked about Java and Objecive-C, and of course Robbie. Pretty neat!
Profound Passerby-er #2 – This person is definitely the person you want to talk to your project about! Unfortunately, I was wandering around looking at other projects when he dropped by, so my Dad helped get him. I’m glad someone FINALLY asked me challenging questions! Although, they weren’t that challenging, but I actually had to think for a few milliseconds before answering some of them. (COOL!) He asked for my bibliography, which is not that impressive as I didn’t have many resources available 0_0. (The two things on there are MIT OCW, and Computer Speech Technology by Robert D. Rodman). He also asked if I could have Robbie tested with autistic children — ABSOLUTELY! I’d love to do that!
4:00 PM – Erin doesn’t understand why everyone is leaving
4:05 PM – Realizes it’s time to go home, so packed up the display and everything! I didn’t leave my logbook or report there, however. I’m extremely skeptical since last year.
6:00 PM – Home sweet home!
So, now my plan is to see if I can get my Arduino running in Xcode! Once I do, I’ll be able to port the speaking character view of robbie to it, so that say, a stuffed penguin, will be able to move its beak up and down to signify that it is speaking.
I have to get this running ASAP, if I want to live up to what I said to Profound Passerby-er #2!
Apparently, tomorrow I have to wake up at the same time. Oh well! Doesn’t matter to me, as there is no formal judging. Just the fun stuff, no stress! If a profound person asks about your project, you can just take it easy – and not worry about outlining the dry and boring Purpose, Discussion, Conclusion. On with the demos and flowcharts!
One more thing – Robbie broke 1,000 downloads this morning!
Happy St. Patty’s Day! Enjoy these pics!
Well, it’s finally science fair! I’ve been looking forward to this day since … early September, so I’m going to make the most of it! Check out the funny timeline of events I’m tracking…
9:30 PM – We only have to leave at 9:30 AM tomorrow! I can get more slides done!
10:24 PM – OHWAIT! We have to leave at 7:00! Orly? YARLY!
5:45 AM – It’s time! iPod has awoken me with 1234, good choice! Woohoo!
5:53 AM – Eyes are burning! What?! Why is my light off? *turns it back on* Looks at all the bugs I have to fix on orange sticky notes…
5:56 AM – Erin struggles with the basic function of copy-paste while making this…
6:00 AM – Watch goes off! It sounds like a messed up cellphone ring, LOL
6:01 AM – I check COBA… Oh no! It’s down!!! I hope I didn’t forget anything that teachers would email me about >_<
6:05 AM – Checked science tech… Yay! The roof of the school is clear – no need to worry! Printed off 3 copies of the schedule
6:07 AM – Sleep’in the macbook to take care of the other things I have to do now…
7:30 AM – We were supposed to leave now… packing the car!
7:50 AM – Left the house, onto a journey of awesomeness!
8:30 AM – Arrived at the school hosting the event! They were cleaning the roof off even more!
8:40 AM – Checked in and received the table number! Set up the board . . . upside down (way to go Erin!) turned it around, set up the display, cables, battery pack & surge protector, macbook, written report!
8:45 AM – Realized the power is not working… Dad goes to speak to them
8:50 AM – Took several photos incase the project gets ruined, like last year
9:10 AM – Power is working! No more annoying beeping heard from my power pack throughout the gym
9:30 AM – The bamboo stick lady checked the measurements of the display board
10:30 AM – Introductory ceremonies – everyone is ushered into the auditorium
10:45 AM – Introductory ceremony begins
11:00 AM – Guest speaker talking about mainly him, and on the side, a few slides of immunology… (CD4-Fox3 Cells)
11:30 AM – Lunch! Had to grab my macbook from Dad, as he had to leave the gym for some reason…
11:45 AM – Ate my sandwich and fruit loops and cookies and chocolate!
12:00 PM – Hurried back to the gym
12:15 PM – Ran in to the gym (once they opened it) to check back on the display (it’s there, PHEW!)
1:00-1:30 PM – Peer evaluation! Was quite fun! The three projects I evaluated were about FerroLiquid, the emergency classification (like in Katrina), and stopping movie piracy using IR light
1:30-5:00 PM – Demonstrated Robbie to several people passing by… fun fact- when Robbie asks about hockey, 100% of the responses were Canadiens!
5:05 PM – Packed up the display and stuff, headed home!
6:00 PM – Home sweet home! Time to refine my presentation for the judges tomorrow and write my log book in my log book (I wrote my log in bad writing in my commonplace book – so I’m transferring it to a pink journal)
Well, that’s about it for Day 1! I’m exceedingly pleased. My booth is next to the one that won the big prizes last year, and next to the librarian at my school son’s project! I have to bring speakers tomorrow though, no one could hear Robbie! I’ll remember my keyboard tomorrow too, so the escape button is more accessible. The only problem, which isn’t really a problem, is that I have to wake up at 5:00 am tomorrow. My dad is a judge, so he has to be there early. I’m having SO much fun, I just want to spend as much time there as possible!
For now – I have to triple check my presentation and fill out my log book! I also have 9 survey results, so I’m crunching the numbers for them.
More timeline madness tomorrow! Enjoy these pics…
As Robbie would say… ‘Wowee’!
I’m so happy that Robbie made it in to the Apple downloads!
You can check it out here
MacUpdate also put it on its site!
That’s pretty awesome!
However, I still need people to complete the survey! So please, spread the word, and do the survey!