Agent Technology

Systems, Tools, Languages, Standards, ...

The ALICE AI Funcation

The ALICE Artificial Intelligence Fundation

ChatterBox

http://www.sitepal.com/

Robocup

Robocup

Univrsity of Queensland team
University of Carnegie Mellon team

Components:

• Wireless module
  https://www.soanarplus.com/productSearch.do
  http://www.radiometrix.co.uk/products/bim2.htm
  http://www.sparkfun.com/commerce/product_info.php?products_id=7815
• DC Micromotors
  http://www.erntec.net/content/products/?0,3,a001,47
  http://www.mechtex.co.in/ (DCCS28a 12VDC 120RPM Shaft 4 x 14mm Torque - 1kgcm)
• Wheels
  http://www.kornylak.com/wheels/omniwheel.html (RW29 model, 48 cm, $2.00)
• Battery (7.2V run at 1.9A for 1 hr)
  http://www.mashobbies.com.au/mashobbies/content/products/product.aspx?intProductID=4003
• solenoid
  SoanarPlus (SS0902, 12VDC 50W 24R 2KG)
• Motor Driver (min 2A)

Massive Software

Massive Software is the premier 3D animation system for generating crowd-related visual effects for film and television. Using Massive, an animator or TD designs characters with a set of reactions to what is going on around them.

The reactions of the characters determine what they do and how they do it. Their reactions can even simulate emotive qualities such as bravery, weariness, or joy. The agent reactions can control key-framed or motion captured animation clips called actions.

Characters that perform on their own in this way are referred to as agents. Massive is a system for designing and running such agents. When scaled up into the hundreds - or hundreds of thousands - the interaction within the crowd that emerges from these individuals is highly realistic. By building variation into an agent, the Massive artist can populate a scene with individuals who are unique in everything from physical appearance to how they respond.

The intuitive node-based interface of Massive Prime™ allows artists to interactively create AI-enabled agents. The Brain Editor AI toolset gives artists the freedom to build custom responses for the specific behavior they want to simulate, without any programming.

The Motion Tree workflow and integrated Action Editor allow key-framed or motion-captured animations to be linked to the brain.

Hanson Robot Speaks, Learns and Interacts with People and Environment Driven by Academy Award-Winning Massive Artificial Intelligence Software.
Hanson says one of the robot Zeno’s biggest advancements is that its brain synchs wirelessly to a PC running a variant of Massive Softwar.

Robocup Soccer Simulator

RoboLog website
Robocup Soccer Simulator
The RoboCup Soccer Simulator is a research and educational tool for multi-agent systems and artificial intelligence. It enables for two teams of 11 simulated autonomous robotic players to play soccer (football).
Download
http://sourceforge.net/projects/sserver/

Robocup Soccer Simulator official website

Nero 2.0 machine learning game

Nero
Neuro-Evolving Robotic Operatives, or NERO for short, is a unique computer game that lets you play with adapting intelligent agents hands-on. Evolve your own robot army by tuning their artificial brains for challenging tasks, then pit them against your friends' teams in online competitions!
NERO is a result of an academic research project in artificial intelligence, based on the rtNEAT algorithm. It is also a platform for future research on intelligent agent technology. The NERO project is run by the Neural Networks Group of the Department of Computer Sciences at the University of Texas at Austin. To learn more about NERO, check the About page and the illustrative videos. To try out NERO, download the game binary and run the tutorial. To use NERO in your research or teaching, contact NERO team.
http://nerogame.org/

In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet, if game characters could learn through interacting with the player, behavior could improve as the game is played, keeping it interesting. This paper introduces the real-time Neuroevolution of Augmenting Topologies (rtNEAT) method for evolving increasingly complex artificial neural networks in real time, as a game is being played. In fact, rtNEAT makes possible an entirely new genre of video games in which the player trains a team of agents through a series of customized exercises. To demonstrate this concept, the Neuroevolving Robotic Operatives (NERO) game was built based on rtNEAT. In NERO, the player trains a team of virtual robots for combat against other players’ teams. This paper describes results from this novel application of machine learning, and demonstrates that rtNEAT makes possible video games like NERO where agents evolve and adapt in real time. In the future, rtNEAT may allow new kinds of educational and training applications through interactive and adapting games.
Real-time Neuroevolution in the NERO Video Game

rNeat algorithm
http://nn.cs.utexas.edu/soft-list.php

Robocode

http://robocode.sourceforge.net/