Ph.D. thesis available: Unsupervised On-line Data Reduction for Memorisation and Learning in Mobile Robotics

[Fredrik Linaker]

Dear Connectionists,

My Ph.D. thesis: Unsupervised On-line Data Reduction for Memorisation 
and Learning in Mobile Robotics

is now available for download:

http://www.ida.his.se/~fredrik/publications/linaker_thesis2003.pdf
http://www.ida.his.se/~fredrik/publications/linaker_thesis2003.ps.gz

Supervisor: Prof. Noel Sharkey, University of Sheffield, UK

An abstract follows.

I'd be very interested in information about open post-doc positions 
within the learning and/or robotics areas.

Best regards,
Fredrik Linaker
fredrik.linaker at ida.his.se



ABSTRACT

The amount of data available to a mobile robot controller is staggering. 
This thesis investigates how extensive continuous-valued data streams of 
noisy sensor and actuator activations can be stored, recalled, and 
processed by robots equipped with only limited memory buffers. We 
address three robot memorisation problems, namely Route Learning (store 
a route), Novelty Detection (detect changes along a route) and the Lost 
Robot Problem (find best match along a route or routes). A robot 
learning problem called the Road-Sign Problem is also addressed. It 
involves a long-term delayed response task where temporal credit 
assignment is needed. The limited memory buffer entails that there is a 
trade-off between memorisation and learning. A traditional overall data 
compression could be used for memorisation, but the compressed 
representations are not always suitable for subsequent learning.  We 
present a novel unsupervised on-line data reduction technique which 
focuses on change detection rather than overall data compression. It 
produces reduced sensory flows which are suitable for storage in the 
memory buffer while preserving underrepresented inputs.  Such inputs can 
be essential when using temporal credit assignment for learning a task. 
  The usefulness of the technique is evaluated through a number of 
experiments on the identified robot problems. Results show that a 
learning ability can be introduced while at the same time maintaining 
memorisation capabilities. The essentially symbolic representation, 
resulting from the unsupervised on-line reduction could in the extension 
also help bridge the gap between the raw sensory flows and the symbolic 
structures useful in prediction and communication.


http://www.ida.his.se/~fredrik/