Author: Drew Wicke

Drew Wickehttp://drew.psib.org

Smart Apartment Communities

I am getting a new apartment and am going to move-in in October!  This time it is a fancy one, not a basement of a house, but well it is still technically in a basement (subterranean as the apartment office calls it).  It is fancy in that it is part of an apartment complex.  The best part though is that I will be moving in there with my then to be wife, Leslie :).

So, last night Leslie was on her amazon because she was checking the shipping order for one of her friends wedding gift.  I was watching and she accidentally scrolled down too far and I saw what she got me for my Birthday!  She got me a Raspberry Pi 3!  So, it is a bit early for my birthday, but I don’t care.  I’m getting a raspberry pi!!!

This got me thinking of multiple ideas of what to do with it…  From making the whole kitchen into a smart kitchen.  Where we have smart outlets, automatic faucets, lights that turn on when you walk in or off when you leave, and automatic alarms that go off if the oven has been on for longer than you set it for, sound system controller, humidity regulator (since a basement probably will need a dehumidifier), temperature controller. dishwasher monitor, voice controlled kitchen timers…. I mean the list just goes on and on and on!

This got me thinking that apartment complexes would be the ideal candidate to start renovating for smart living spaces!  Essentially a smart community.  They could operate on there own smart/micro grid, have there own micro water plant (because why don’t we operate water and sewer like the micro-grid?  I mean that way the entire water system is not so easily polluted by a single source.  Also, that means a more exact amount of water is able to be cleaned etc.  idk but seems like a cool idea right?), also there would be solar panels installed on all the roofs (or at least those that make sense).  Then they could also renovate the apartments themselves.  Of course the more you pay the more the automation and the higher end the appliances etc are.  Of course you would want the smart house to be easily able to integrate the apartment resident’s devices and personal augmentation.  That way they could add more automation themselves if they desire.

So, that is a lot up front.  But, if the complexes start offering for a significant rent increase the basic smart house, they could start to increase there revenue and start to renovate the communities and start to make there company stand out.  Eventually they would have the dream of my last paragraph.  Of course if they are building a new community they might consider doing this from the start.

So, that was a fun idea I had.  I think that this would be a fun business to get into.  Contracting with apartment companies to renovate their apartment communities.

 

Kung Pow Chicken!

Kung Pow Chicken recipe I learned from Ermo and helped make with Leslie at his and Shu’s place today.  It was soooo sooo delicious!

4 chicken thighs cut into tiny-ish cubes.  Best if thigh is still somewhat frozen.  It is easier to cut.

Mix up the marinade for the chicken.  Some salt, soy sauce, vinegar, sugar, and corn starch (mixed with a bit of water).  Basically this is done without any measuring.  You do it to how you like it.  So, if you like it salty then more salt and soy sauce.  If you like it a bit bitter have more vinegar.  If you like a bit sweet and salty have more sugar.  Basically you have a bowl and you use a ladle and you pour those ingredients into the ladle and you use that to measure and mix.

Once you get it how you like it mix it into the chicken and let it sit for 20 minutes.

While that is sitting get your spices together.  Numb spice you just buy already and don’t do anything.  The chilli peppers you may have whole and you just use kitchen shears to cut tiny lengths.  Then chop up onion sprouts and a few cloves of garlic to your liking.  Also pour out some peanuts.  Can just use unsalted peanuts from the store.

By now the twenty minutes is probably up and you can heat oil in a wok on high and once the oil is very hot put the cut up chicken into the pan.  Stir vigorously keeping the chicken moving and flipping.  A sort of stir flip motion continuously.  Do this until you start to see the chicken change from pink to white.  Once that happens immediately take the chicken off the heat and put it onto a plate.  You may pour off any of the excess juice to either save or throw away.

Now turn the heat to a medium temperature and add in some oil again.  Let it heat up.  Then add in the numb spice and chili pepper and stir them around until it smells good and the garlic is looking nice.  Then add back in the chicken.  Turn up the heat a bit.  And then add in the onion sprouts and peanuts.  This part you must continue the stir and flip motion vigorously until the chicken is mixed in with the other ingredients and appears to be fully cooked.  Note that this does not take very long.

You can eat this by itself or if you want can serve with some rice.

Also, the cool part about this is that it is highly dependent on what you like and what tastes good to you.  So, there really is no wrong way to make kung pow chicken.  You could add other vegetables if you want or leave out some of the spice if you think it is too spice.

Wedding Prep and Research

Wow!  I’m quite busy.  Leslie and I’ve been putting together a wedding website (here, also she did it all.  All I did was suggest where and put in the map lol).  We have just finished our wedding registry and wow there is a lot you need for a kitchen.  Leslie has made wedding invitations and RSVP cards and cool art to go on them.  So cool!!! Well umm most of that has been what Leslie has been doing…

I’ve been helping some with that.  But I’ve been working on redoing the cloud robotics paper for ICRA and intermittently working on the theory for Bounty Hunting.  And I’m also planning on proposing my thesis and doing my comps this fall.  Along with getting married!

NYC for Agent Mix IJCAI Workshop 2016

Had an amazing first day in New York City.  Took the BoltBus with Leslie at 7am (July 10th).  We went and got pizza for lunch and went to the Met.  To get to the met we took the metro and walked through central park catching Pokemon along the way :).  We explored the Met for a while.  It is huge!!!  We left and grabbed an Uber back to my hotel and I checked in.  We took an Uber then back to the BoltBus stop and Leslie took the bus back to DC.

After she left I tried pizza from two more places.  At the one place I got 2 slices and a coke for $3.  I ate a slice in front of the building and then I folded the other slice up and grabbed my coke and ate, sipped, and walked.  That was so much fun!  Delicious pizza, with amazing surroundings.

Tomorrow at 11am I present at the Agent Mix Workshop a paper Ermo and I did on bounty hunting with task abandonment.  I can’t wait until 11:25 and my presentation is finished and I can have fun again :).

Going to have to figure out what I want to do in the free time!  I’ll post more then!

I’m Engaged!

On June 29th 2016 I formally asked Leslie Ann Brown to marry me.  She said “Yes!”.  In a couple days, July 3rd, that will be our four month anniversary for how long we have been dating.  Before that we knew each other from seeing each other at church for the past four years.  The past four months involved a lot of skype conversations while Leslie was in Germany.  And a number of dates, double dates, cooking together, geocaching, driving around and going on adventures together both before she left for Germany and after.  We are now committing to spend the rest of our lives together.  To love each other, help each other, and care for each other.

So, today Leslie came to the lab and she worked on her stuff and I worked on things I needed to get done at the lab.  But I had in mind that I would propose to Leslie in the afternoon.  I wanted to take Leslie to the parking lot of where I sat in the car with her waiting for the rest of my friends to get there to look at the stars at GMU’s observatory.  Also, it was where she first kissed me.  But to get her to the parking lot there is a Giant in the same shopping center and it was being renovated and I thought it was finished.  However, when I got there it was still closed.  So, I was like “I didn’t come over here just to get groceries to make the meatball sub.”  So, I pulled into a spot close to where we sat in my car those many months ago and asked “Will you marry me?”.  She said “Yes!”.  And then I got out a diamond necklace and put it on her.  That necklace has been passed down from my grandmother to my mother and now down to my future wife.  So, now that parking lot is also where I proposed to Leslie.  We have many good memories in that parking lot.

I love you Leslie!

Leslie’s Birthday!

My girlfriend, Leslie, had her birthday today :)!  I didn’t get to celebrate it with her because she is in Germany with her sister and brother-in-law.  She baked herself her special chocolate cake, took care of her niece, worked on applying for a job, and had fun doing some digital art for Beyond Porch and Portal (the book she is working on) while listening to a podcast.  So, I think all in all she had a pretty nice birthday, although I wish she was with me!  Planning on spending as much time with her as possible when she gets home :).  I can’t wait!

Bounty Electricity

What if each appliance posted a bounty for providing in real time the amount of electricity it needed to function.  The bounty would first be attempted by the house itself and if the house did not have any spare electricity in its batteries then it would post a bounty out for that electricity.  The first to supply the needed electricity would win the bounty.  Would not limit it to only the power stations supplying the electricity.  Could be houses nearby that could provide the electricity.  By using a bounty hunting system and using a first to supply mechanism or something similar it would be essentially like the cloud robotics except instead of putting a bounty out for the servo positions we are putting a bounty out to receive electricity!

Machine Learning and History

I’ve had this idea for doing clustering and data mining of history texts.  Would be interesting to creating learning algorithms that can learn timelines and context.  Essentially history textbooks are structured possibly geographically and as a time series of events.  Then doing graphical analysis and social analysis on these structures.  Could compare history texts and see what is left out and maybe what each text places more emphasis on what events.  Also, doing this across time to see how history texts have changed in what the historians themselves find interesting.  Possibly finding patterns in history itself that were not evident or obvious without such algorithms that can crunch large large volumes quickly.  Doing the normal sentiment analysis as well.

This could then lead to producing a better picture of different countries and people groups and how they were formed.  Possibly doing anomaly analysis or creating other types of filters to uncover gaps in the history texts themselves.

This of course seems like it should have been done.  Main issue is getting digital copies of the history books for the algorithm to work with.  So, it may not have been studied.  Creating learning algorithms that can understand human history seems like an important area of research.  Especially as we are writing history now it is important to maintain a grasp of the entire picture and how everything fits together.

Research and Math :)

The IROS paper was submitted 10 minutes before the deadline on March 1st.  The paper was okay, but I’m not thrilled about it because it is only the beginning stages of the work.  So, it doesn’t really use the bounty hunting stuff to its fullest.  Future papers will hopefully provide that.  We also had to create a video.  Ermo and I got the footage of the Pioneer doing the visual servoing on the ball both indoors and semi-successfully outdoors (either due to lighting or to the massively long ping times was not able always stop in time before running into the ball).

Now that is over I’m taking a bit of a break from working with robots and am working with Ermo to do some research in continuous action multiagent learning (CAMAL our acronym, don’t steal it!).  It has been a ton of fun!  I’ve been doing derivations and learning new math (and re-learning some old math!).  Getting to work out how the equations and proofs of convergence happen I believe will aid me in my work with doing proofs of convergence with bounty hunting in the future.  So, it is benefiting Ermo and me at the same time and we are having fun in the process :)!  We are working on this for a paper in NIPS.  If our algorithm concept is successful and we can show some convergence we should have a very strong NIPS paper.  David is also trying to join in and we can greatly use his help as it is a very challenging problem.  Main issue is he is still taking classes.  Can’t wait for his classes to be done!

Dan wants us to write up a paper for the Robocup Symposium on how we were able to adjust the behaviors to work with a robot that could not turn that well using HiTAB (our learning from demonstration software).  That is due March 25!  He just told us about it this monday.  Thankfully though we won’t have to produce any experiments or results we just need to write about what we did.  So we are actually pushing that off until the 22nd because Ermo and I need to make a poster and a slide for GMU’s first CS symposium.  Just what we need, not!  The really frustrating part is that it is mandatory for all CS PhD students to attend and those selected to present are required to present!  So, it is not optional.  I guess they figured no one would show up otherwise.

 

Starting on IROS 2016 paper

I got the rejection email from AAMAS last week for my paper on task abandonment for my bounty hunting system.  However, I sort of was expecting this as it needs some more theoretical basis.  So, I have to work on that.

In the mean time there is still IROS!  That is in Korea :).  The paper is due March 1st and I just started working on getting the code written for that.  But this is a fun paper as it is combining cloud robotics (can’t stand that name!) and my bounty hunting work.  So, I’m giving myself a lightning fast tutorial on ROS, raspberry pi, and the pioneer 3dx robot!  Plan is to get the base system working by friday so next week we can start doing experiments and collecting results.  Then the week before the paper is due we can write it!  So, I think we will have just enough time to pull it off.  At least this paper seems likely to be accepted as it both cloud robotics and bounty hunting are very cutting edge and putting it all on an actual robot should seal the deal :)!  So, hopefully I’ll be going to Korea in October!