Jump to content

  • Log In with Google      Sign In   
  • Create Account


The AI in my game engine tries to learn to fly a space ship (video)


Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.

  • You cannot reply to this topic
9 replies to this topic

#1 Vexal   Members   -  Reputation: 416

Posted 23 May 2013 - 05:18 PM

 

This is the result of putting an AI in the ship that attempts to keep the ship level when balls are thrown at it.  The ship has 13 thrusters total, which the AI fires off to apply torque to attempt to counteract its change in orientation and velocity.  The results are amusing.



Sponsor:

#2 way2lazy2care   Members   -  Reputation: 782

Posted 23 May 2013 - 09:14 PM

 

This is the result of putting an AI in the ship that attempts to keep the ship level when balls are thrown at it.  The ship has 13 thrusters total, which the AI fires off to apply torque to attempt to counteract its change in orientation and velocity.  The results are amusing.

It was doing so well! :(



#3 JTippetts   Moderators   -  Reputation: 8159

Posted 23 May 2013 - 09:21 PM

It was doing so well! sad.png

Yeah, it seemed like it was doing better at the beginning.

#4 Vexal   Members   -  Reputation: 416

Posted 23 May 2013 - 09:31 PM

I was trying to make a PID controller for keeping it level, but it's not stable so it begins to oscillate further and further until it passes a threshold and explodes.



#5 swiftcoder   Senior Moderators   -  Reputation: 9599

Posted 24 May 2013 - 07:36 AM

You need some serious damping there.


Tristam MacDonald - Software Engineer @Amazon - [swiftcoding]


#6 Bacterius   Crossbones+   -  Reputation: 8158

Posted 24 May 2013 - 09:31 AM

Impressive. Unstable equilibrium FTW! The explosion at the end is strangely fitting.


The slowsort algorithm is a perfect illustration of the multiply and surrender paradigm, which is perhaps the single most important paradigm in the development of reluctant algorithms. The basic multiply and surrender strategy consists in replacing the problem at hand by two or more subproblems, each slightly simpler than the original, and continue multiplying subproblems and subsubproblems recursively in this fashion as long as possible. At some point the subproblems will all become so simple that their solution can no longer be postponed, and we will have to surrender. Experience shows that, in most cases, by the time this point is reached the total work will be substantially higher than what could have been wasted by a more direct approach.

 

- Pessimal Algorithms and Simplexity Analysis


#7 Vexal   Members   -  Reputation: 416

Posted 24 May 2013 - 01:33 PM

I'll post an update once I get the kinks out.



#8 ranakor   Members   -  Reputation: 439

Posted 24 May 2013 - 01:38 PM

Show that to someone who's scared of flying and then tell him "don't worry, we're on autopilot!"



#9 ActiveUnique   Members   -  Reputation: 769

Posted 25 May 2013 - 05:07 AM

It's perfect. Who's ever had a giant ball thrown at them while they piloted a hovering spaceship? I bet that same thing happens.

Mr. obvious was too ironic - ActiveUnique


#10 Vexal   Members   -  Reputation: 416

Posted 25 May 2013 - 03:38 PM

Some ships will crash when just a bird hits them!






Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.



PARTNERS