I am currently engaged in research in the area of Artificial Intelligence, specifically as it relates to interactive computer games. My work aims to investigate how human behavioural data can be collected and used to form the basis of intelligent computer-controlled characters. While some researchers have already acknowledged the possibilities offered by the games domain in developing human-level AI, most implementations thus far have centred upon rule-based systems; comparatively little work has been done in translating human examplars into intelligent agents. Given the enormous quantities of raw behavioural data generated on the world's game servers every day, this would seem to be something of an oversight; hopefully, my research will help to address it.

In conjunction with Martin Fredriksson of the SOCLAB group at Blekinge Institute of Technology, I have developed the Quake Agent Simulation Environment, a Java-based API designed to facilitate both AI research and tuition through games. It has proven quite successful, having already been adopted by a number of institutes; all our work, as detailed in the publications list below, utilises QASE to both train and deploy game agents.

Conference Proceedings

• Gorman, B. and Humphrys, M.
  Towards Integrated Imitation of Strategic Planning and Motion Modelling in Interactive Computer Games, in Proc. 3rd ACM Annual International Conference in Computer Game Design and Technology (GDTW 05), Liverpool, November 2005, pages 92-99
  
  
  • winner, "Best Presentation" award
  • selected for publication in ACM CiE Journal
    
  • this web version corrects some minor errata:
    • page 2: "contributions [13][14][15]" changed to "contributions [13][14]"
    • page 4: "Figure 6 above" changed to "Figure 6 below"
    • page 6: "point 2 above" changed to "point 1 above"
  
  
• Gorman, B., Fredriksson, M. and Humphrys, M.
  QASE - An Integrated API for Imitation and General AI Research in Commercial Computer Games, in Proc. IEEE 7th International Conference on Computer Games: AI, Animation, Mobile, Educational & Serious Games, Angoulême, November 2005, pages 207-214
  
  
  • winner, "Best Paper" award
    • references: citation of our GDTW paper altered to insert page numbers
  
  
• Gorman, B., Thurau, C., Bauckhage, C., and Humphrys, M.
  Bayesian Imitation of Human Behavior in Interactive Computer Games, in Proc. Int. Conf. on Pattern Recognition (ICPR'06), volume 1, pages 1244-1247. IEEE, 2006.
  
  
• Gorman, B., Thurau, C., Bauckhage, C., and Humphrys, M.
  Believability Testing and Bayesian Imitation in Interactive Computer Games, in Proc. 9th Int. Conf. on the Simulation of Adaptive Behavior (SAB'06), volume LNAI. Springer, 2006
  
  
• Gorman, B. and Humphrys, M.
  Imitative Learning of Combat Behaviours in First-Person Computer Games, in Proc. 10th International Conference on Computer Games: AI, Mobile, Educational & Serious Games, 2007
  

A 3D tennis game for network or single-computer play, written in pure Java. Originally created as a final-year project for my undergraduate course in Computer Applications at Dublin City University, it was intended to demonstrate that Java3D is both suitable and practical for full-scale games. The project page contains installation and gameplay instructions, as well as full technical details of how the application was written.