Large MAS app. Parking lots

So the idea is that parking lots and local walmarts are not going to be able to afford remaking their parking lots so that when we have autonomous cars we can get dropped off at the door and the robot park somewhere and then pick us up at the entrance.  This is because structurally there is not enough room for a line of cars to wait for the customers to get dropped off.  Also, since most walmarts the entrances and exits are the same door we would also   The line would become like the one when picking up kids from school.  So, it is probably logistically best if the walmarts that are already built have the customers walk from the parking spot of the car.  The problem then becomes one of optimization.  One, I don’t want to walk far going into the store and coming out.  So, the idea is that the emmergent behavior that I want out of the bounties is one of a cycle where initially I want to park as close to the entrance as possible.  Then as time goes on the cars must move to spaces further from the entrance so that those just coming in can park and those leaving can move closer to the exit to pick up the leaving customers.  We want to have the robots learn patterns of behavior and adapt them rather than specific

Want to create behavior patterns and learn the patterns of the particular environment to adapt and choose which pattern of behavior should be used.  The dynamics change as you move through the parking lot since it all depends on the number of cars in the parking lot, the layout of the parking lot, the heterogeneity of the cars (trucks, tractor trailers, RVs, cars, motor cycles etc) and the uncertainty about how long each car is expecting its passengers to be in the store.  How long you are going to be in the store is not something you want to share with the other cars.  That is private information.  We only want our car to know this.  And this number is only an estimate since it is doesn’t know if you are going to stop and talk with a friend you happen to spot while in the store.  Of course to improve the accuracy there would be need to be an interface via your smart phone to be able to tell it your progression.  However, this seems like a nice area for those wearable sensors to be able to predict your progress in your trip through the store and make adjustments based on you seeing something you like that wasn’t on your list.

So the idea is that with the bounties is that the cars would have a distributed mechanism solving the constraint satisfaction problem of everyone needs a parking spot and the optimization problem of specific spots wanted.

So, I think that coalitions of agents will emerge due to common exit times of the customers.  Also I think we want to minimize the number of movements that the cars make.  So, essentially if you know that your passenger is going to be in the store for a while make room closer to the entrance.  Essentially you place a bounty out for a parking spot closer to the entrance.

To pay the bounties would your client have to collect tokens for parking far away and then you would be able to use them in order to park closer.

A case where a lot of vehicles are trying to park at the same time is at distribution centers such as Utz.  Many drivers leave the center and come back to the center to park all around the same time.  This might be interesting as well…  I don’t know…

This would also be useful in the case where we have a system where there are both autonomous and human driven cars.

Another problem is the size of the vehicles and finding parking spots that take up multiples.

That is why I think it would be awesome if the cars were sort of like the bike share program then there would always be a car waiting at the front.  The part that would yours could be stored in a locker…

Swarm of text

Can we use the Shapley idea to determine if there is a swarm on twitter based on tweets?  A swarm could be thought as a lot of retweets or a tweet with similar words.  We could find old tweet swarms characterize them and use them to predict whether certain tweets will become swarms.  I think the idea is identifying whether a tweet will go viral.  When classifying we can look at the social network of the originators and the topic.  Then we can see which words are most frequent in the emerging swarm.  If pretweeting (stockmarket on the words in twitter) was still around we could make money :).

Is twitter and your (virality index) related to the success of crowd funded operations?  Or just that you know some rich people.

How to bring about a virtual swarm and influence it in your favor is an interesting topic.  Sounds like marketing though…

Java 3D and Mason

Well I got MASON installed and working.  The 3D simulations are pretty neat.  But you need to get Java 3D and install it.

Some things to remember to speed the process of setting up netbeans for MASON would be that in order to add dll files you need to add something like:

-Djava.library.path=”C:Program FilesJavaJava3D1.5.1bin”

to the VM options in the run section of the properties of the project.  Also, you must remember to add the 3D Java jar files to the libraries section.  Otherwise you can just follow the tutorial here to get started.

We intend on using MASON as our test bed for the identification of swarms using the Shapley value idea.

Swarm Calculus!!!!!!

I found people who are actually trying to model general swarms mathematically rather than specific swarms.  This is awesome!  They are calling it swarm calculus.  I think that what we are doing would contribute to the swarm calculus.  It seems like everyone always assumes we know that what we are looking at is a swarm and that we can automatically apply swarm modeling techniques   But what if it isn’t a swarm?  Then we will have wasted time and resources learning nothing.

What happens if we used swarm calculus on a multiagent learning system? What would it tell us?  That might just be stupid.

So what does that paper say about swarm calculus?

They assume cooperation is an essential part of swarms.  So right away my first thought is: Do they think Brownian motion is a swarm?  Interesting quote:

swarms generally face a tradeoff between beneficial cooperation and obstructive interference.

They find the two main components of swarms are cooperation and interference.  So is what they consider interference what I think of coordination?

They say mathematically that cooperation is:

[math]C(n)=a_1N^b[/math]

They got this formula from Breder 1954 to model cohesiveness.

They model interference by looking at the correlation between number of robots and their efficiency in the robot foraging domain.

[math]I(N)=a_2e^{cN}+d[/math].

c is less than 0 so this is a decreasing function.  So the efficiency of each robot decreases as the number of robots increases (since each robot will have to collect less).

They showed the existence of phases in swarms.  Like when there are x individuals then they all have the same speed.  But at a point other than x there might be 2 distinct speeds.  This was interesting as it points to how the number of individuals in the system can effect the emergent behavior.

Gaussian Surface to calculate the flux of swarms

If we have a physical swarm (not the general swarm).  We could use a Gaussian surface to calculate the flux of the individuals.  Could this be part of the general swarm calculus.  If we defined the domain using features other than distance?  A more general type of Gaussian surface?

Could this be applied to any types of systems.  What useful things could we say then using this info?  Could we model coordination using the ideas of the flow of (simplified idea of) electrons in a wire?

Combine this with the idea of how to model coordination.  Could we then model the general swarm?

Future: year 2213

Combine augmented reality, nano robot swarms and mind-device communication.  So the idea is you first imagine a structure.  This imagined structure is displayed (could be on glasses contact lens etc), augmenting reality.  Using the image you can then improve and change the design.  Could use your hands to manipulate it or just use your thoughts which ever is easier.  The nano robots can then form the imagined structure.  You could then store useful structures for later use and the system could learn to predict and suggest new structures based on your preferences and behavior.

You all knew I am a bit crazy ;).

Thoughts on old research question

Back in undergrad (July 2010!) my professor, Dr. Babcock, posed the following question in order to help expand my narrow focus:

The really interesting question is how does making the individual rules more complex affect the aggregate behavior patterns (or does the society no longer have patterns).

As I am studying MAL, swarms and emergence I am thoroughly intrigued with this idea.  I am hoping that with a better mathematical framework for understanding emergence and swarms I can formulate an answer.

Based on nature patterns generally emerge from either coordination or cooperation.  So, a better question might be can coordination and cooperation be so far abstracted due to the complexity of the rules that aggregate behavior patterns do not emerge?  Then at that point we may still observe emergent behavior only due to some more complex social notion.  So, what is it and how can we observe it :).

 

*On a side note: Since I found that email, I noticed the date I sent, July 2 2010, and he replied July 6 2010.  I really had a cool professor to take his time to reply even around July 4.

Some swarm thoughts

UPenn researchers have collected examples of swarms or group behaviors found in nature.  More than half of the papers describing the collective behavior of swarms exhibited coordination.  The cool thing was that they found that coordination behavior is present from killer whales to cancer cell populations!  It definitely seems that the ideas of coordination and cooperation are the keys to characterizing swarms.

So far, I have been assuming that swarms relied on cooperation and that was why I thought that the Shapley value would be very useful in characterizing them.  However, it can only describe half the cases.  Because in nature, coordination without cooperation happens.  Some good examples I found in the powerpoint here are:

”A group of people are sitting in a park. As a result of a sudden downpour, all of them run to a tree in the middle of the park because it is the only source of shelter.”

or

“Individual drivers in traffic following traffic rules”

The difference between having cooperation and not is responsibility.  They give the counter example of a convoy of drivers.  They are cooperating.

So, I believe that there are at least three types of swarms.

joint coordination cooperation

Only coordination

Only cooperation

The good news is that joint intentions are useful in describing coordination.  So, I need to read up on that.

 

This paper seems very interesting because it takes a wholly physics approach to describing the swarm phenomena.  Also this paper is interesting because it determines the most influential k nodes in a social graph using the shapley value.

Characterization of the Culture of Swarms

One of my goals over the winter break was to determine a good paper idea that had a lot of math and that would move the field of large multiagent learning systems forward.
Our contributions would be:

1. Alternative shapley value formula for swarms
2. Integration of the swarm value with k-order additive fuzzy measure theory
3. Solving the inverse problem to determine if a large system of agents is a swarm
4. Using the information to create autonomous hybrid swarm/multiagent learning environments

 

However, we might determine that the amount of work might be too much for one paper.