Artificial Models of Natural Intelligence

Bath AI  |  Intelligent Systems Group  |  Contact Us 

Current Research

This is an overview of current AmonI research projects.  For previous projects (some of which we are still interested in) see Older Research.  Our policy is to publish software as soon as the archival journal article comes out that it supports. That software is available on the AmonI software page.  See also our seminar series listed on our home page.

Ethics:  Robot Ethics, AI Ethics and Policy

Making NI Modelling Easier

  • Joanna Bryson designed a methodology for building complex AI systems called Behavior Oriented Design (BOD).  We are use this both for some of our more complicated modelling (see task learning & social behaviour below) and for cognitive systems development more generally (see further below).
  • Our currently released software is a BOD version of the agent-based modelling tool, MASON, and a  jython/python version of BOD's action selection, jyPOSH. Swen Gaudl is making a version in C#.
  • Swen Gaudl and Simon Davies are also working to improve the BOD IDE, ABODE.
  • Our affiliates Cyril Brom and his team in Prague support a version of POSH (with an IDE) in their games-development platform Pogamut.
  • Another aspect of this research is our work on improving the representation of life-like emotions.  To this end we developed the Dynamic Emotion Representation, available as part of EE-FAS, and the flexible latching system, which comes standard with jyPOSH and BOD/MASON.  More information is available under Older Research.

Individual Learning and Modular Intelligence

  • Bidan Huang is conducting a PhD on integrating learning modules into cognitive robots for health-care applications.  Her current research focusses on grasping.
  • Joanna Bryson has has a long-running interest on modularity in learning, for example why different regions of the brain learn at different rates and with different physical representational neural substrates. Her work is particularly focussed on modular models of a standard benchmark task from experimental psychology: Transitive `Inference' Performance.
  • Eugene Bann is working on determining the accuracy of models of emotions by looking at how they are implicitly described in language on twitter.

Social Behaviour

  • Karolina Sylwester, Simon Powers, Daniel Taylor and Joanna Bryson (with advice from Benedikt Herrmann) are working on understanding geographic variation in the prevelance of an apparently maladaptive cultural norm, anti-social punishment.  They are using Behavioural Economics to gather the data and Agent Based Modelling to express and examine the theory.
  • Gideon Gluckman is looking at understanding the impact of primate social organisation on their genetic evolution.  This relates to understanding how cognition and individual learning affect operate as adaptive strategies, a common interest held with Joanna Bryson, Marios Richards and Daniel Taylor.  It also extends from recent work done by Hagen Lehmann on modelling macaque social behaviour.
  • Joanna Bryson and Julia Lehmann are trying to understand the adaptive strategy of fission-fusion.  Joanna is also working with Petra Kaczensky on this, looking at the specific case of Wild Mongolian Asses.  Rob Jenks did a recent model of chimpanzee-like fission-fusion which is not yet published.  Ando Yasushi did an MSc on the impact of predation on primate social organization which also still needs extension for publication.
  • Daniel Taylor is looking at how social structures in early hominids might influence cultural evolution (see below).
  • Will Lowe studies political science using computational linguistics to determine policy dynamics.
  • We are working with Ed Feil and perhaps others (incl. Danny Rozen) on bacterial social behaviour and communication.

Social Learning and Cultural Evolution

  • Dominic Mitchell is working with Gordon Ingram looking at understanding the impact of gossip on the evolution of communication. Dominic is also interested in language evolution and public language.
  • Daniel Taylor is working on understanding the biological evolution of cultural evolution.
  • Joanna Bryson with Will Lowe, Ivana Cace & Avri Biolovich are working on understanding the evolutionary consequences of the altruistic communication of behaviour -- that is, culture.
  • Joanna Bryson has recently published a good deal of work on how interacting differences in representational capacities may account for the exceptional size of human culture, see our evolving human-like culture web page.
  • We are working with Harvey Whitehouse at Oxford University on understanding the origins of religious behaviour.
  • Bidan Huang may be using imitation learning for training her robots, although see our previous experience with real time imitation learning.

Biological Evolution, Culture, Individual Learning and Development

  • Daniel Taylor is very interested in cultural evolution specifically and evolutionary mechanisms more generally. He is working on Rogers Paradox and on modelling cultural drift and sexual selection.
  • Joanna Bryson and Nick Priest are working on epistasis (understanding the evolution of sex in terms of gene stability). Bryson started this work wity Alastair Fletcher & Steve Dorus. Marios Richards and Priest extended this work to look specifically at compensatory mutation.

Cognitive Systems:  Robots, intelligent spaces, VR Avatars and Computer Game Characters

Not all of our applications are scientific.
  • Bidan Huang is working on dexterous cognitive robotics with our collaborators in Aude Billard's laboratory at EPFL.
  • Bidan Huang, Jason Leake and Joanna Bryson are working with the Bath Institute for Medical Engineering on designing robots to assist nurses and help control infection.
  • Human-like intelligence is useful in computer games too. Besides being fun, this is a good test-bed for the usability of BOD & helps us debug and improve it.  The most recent published work on this is by John Grey, who created generative quests for non-player characters.  These give the characters individual history and social networks, making them generally more interesting to interact with.  This work needs extending. In 2012, Simon Davies made a BOD agent for StarCraft II: Brood War, and Tom Hyde made a BOD team for RoboCup 2D Simulation League.
  • Swen Gaudl is doing a PhD on improving game character AI, possibly through using genetic algorithms.
  • Cyril Brom's group working at Charles University, Prague have been working to make creating game intelligence easier with a goal to using it as a platform for teaching programming.