THIS IS A COLLECTION OF PhD/MPhil
THESES PRODUCED BY STUDENTS
ASSOCIATED WITH THE COGNITION AND AFFECT PROJECT
Some of the work reported below is illustrated in video demonstrations using the
SimAgent toolkit here:
- Luc Beaudoin (PhD):
Goal processing in autonomous agents
For Luc's current activities see https://cogzest.com
He is continuing to develop themes in the CogAff project.
- Edmund Shing (PhD):
MEDEA: Exploring the design of a situated adaptive agent
Thesis not available online. For a sample of his work see this
Computational Constraints on Associative Learning
- Christian Paterson (MPhil):
The use of ratings for the integration of planning and
learning in a broad but shallow agent architecture.
Online in two parts
- Ian Wright (PhD)
Thesis online (PDF and Postscript)
Pop-11 code for the Minder1 program is available here,
modified to work with the latest version of the
The program requires the
, recent versions of which include the toolkit.
To run the program untar the file, to create a directory newminder1,
then read the file GO.p into the poplog editor Ved. Compile the
with the command
Then run the command that is printed out in the editor buffer.
After completing his PhD here, Ian worked for Sony for a while, then
went to California where he works for a games company,
AiLive Inc. He now (in 2015) lives in
Oxford while still working for the Californian company.
In his "spare time" he completed a second PhD, in Economics, at the
Open University, and is now an authority on political economy.
Cottrell, Cockshott, Michaelson, Wright, Yakovenko.
Classical Econophysics, essays in thermodynamics, information theory and
Routledge Advances in Experimental and Computable Economics.
Anupam Chakravorty, Rob Kay, Stuart Reynolds, Ian Wright
In Gamasutra, July 27, 2010
Taking Games Beyond Whack and Tilt
Chris Complin (PhD):
The evolutionary engine and the mind machine: A design-based study of
After leaving Birmingham, Chris joined a finance company (JP Morgan) and at one
stage was elected
"Fund Manager of the Year".
Prediction learning in robotic manipulation (2010)
Ph.D. thesis, University of Birmingham.
Supervisor: Jeremy Wyatt
This thesis addresses an important problem in robotic manipulation, which is the
ability to predict how objects behave under manipulative actions. This ability
is useful for planning of object manipulations. Physics simulators can be used
to do this, but they model many kinds of object interactions poorly, and unless
there is a precise description of an object's properties their predictions may
be unreliable. An alternative is to learn a model for objects by interacting
with them. This thesis specifically addresses the problem of learning to predict
the interactions of rigid bodies in a probabilistic framework, and demonstrates
results in the domain of robotic push manipulation. During training, a robotic
manipulator applies pushes to objects and learns to predict their resulting
motions. The learning does not make explicit use of physics knowledge, nor is it
restricted to domains with any particular physical properties. The prediction
problem is posed in terms of estimating probability densities over the possible
rigid body transformations of an entire object as well as parts of an object
under a known action. Density estimation is useful in that it enables
predictions with multimodal outcomes, but it also enables compromise predictions
for multiple combined expert predictors in a product of experts architecture. It
is shown that a product of experts architecture can be learned and that it can
produce generalization with respect to novel actions and object shapes,
outperforming in most cases an approach based on regression. An alternative,
non-learning, method of prediction is also presented, in which a simplified
physics approach uses the minimum energy principle together with a
particle-based representation of the object. A probabilistic formulation enables
this simplified physics predictor to be combined with learned predictors in a
product of experts. The thesis experimentally compares the performance of
product of densities, regression, and simplified physics approaches. Performance
is evaluated through a combination of virtual experiments in a physics
simulator, and real experiments with a 5-axis arm equipped with a simple, rigid
finger and a vision system used for tracking the manipulated object.
Verónica Esther Arriola Ríos
Learning to Predict the Behaviour of Deformable Objects through and for
Robotic Interaction (Phd thesis), University of Birmingham, 2013
Every day environments contain a great variety of deformable objects and it is
not possible to program a robot in advance to know about their characteristic
behaviours. For this reason, robots have been highly successful in manoeuvring
deformable objects mainly in the industrial sector, where the types of
interactions are predictable and highly restricted, but research in everyday
environments remains largely unexplored. The contributions of this thesis are:
i) the application of an elastic/plastic mass-spring method to model and predict
the behaviour of deformable objects manipulated by a robot; ii) the automatic
calibration of the parameters of the model, using images of real objects as
ground truth; iii) the use of piece-wise regression curves to predict the
reaction forces, and iv) the use of the output of this force prediction model as
input for the mass-spring model which in turn predicts object deformations; v)
the use of the obtained models to solve a material classification problem, where
the robot must recognise a material based on interaction with it.
- Work in progress
PhD Students can no longer apply to work on this project.
Aaron Sloman no longer accepts PhD students. Although formally retired, he is
now working on a much broader project, which subsumes all the themes of the
Cognition and Affect project, namely the Turing-inspired Meta-Morphogenesis
There are no funds associated with this project.
RETURN TO MAIN COGAFF INDEX FILE
Last Updated: 7 Jul 2014; 13 Aug 2015; 1 Sep 2015
This file is maintained by Aaron Sloman: