MI competition 2003Summary of Entries
Entry 1: The Nottingham Trent University, Dr. Tony Allen ()
Name of System:
Speech-enabled Attain travel information system
Description of system:
The ATTAIN system enables users to interact with a computerised bus travel information system using spoken dialogue exchanges over mobile telephone links.
For example, when prompted by the system to state your journey, a user can say " would like to go from Arnold to City Centre after 13:30 please". The system will automatically recognise the speech input, extract the relevant information fields and then pass this to a Web based travel query processing system. This system calculates, in real-time, the shortest bus journey that would meet the user requirements and then passes this information back. It can be spoken back to the user or mailed to their mobile as a sms text message e.g. 'OK, you can catch bus 58 from Arnold Gleneagles Drive to Victoria Centre at 13:35.'
Entry 2: Centre for Hybrid Intelligent Systems, University of Sunderland, Cornelius Weber, Alexandros Zochios and Stefan Wermter ()
Name of system:
Visually guided grasping robot MIRA
Description of System:
A mobile robot which is capable of identifying and grasping a fruit on a table, taking into account the fruit's position. The behaviour is guided by verbal instruction. It focuses on the practical use of visual recognition and navigation in a continuous world which is easy for humans yet traditionally difficult for machine intelligence.
Entry 3: School of Computing, University of Leeds, Eric Atwell and Bayan Abu Shawar ()
Name of System:
Afrikaans.java
Description of system:
A program to learn from a dialogue corpus (transcript of human dialogue), to train a chatbot (human-machine dialogue system). We can now train chatbots (eg to attempt the Turing Test) to mimic human dialogue directly.
Entry 4:Cardiff University, Alia Abdelmoty ()
Name of System:
SPARQS
Description of System:
SPARQS is an automatic reasoning engine for deriving spatial relationships over randomly shaped objects in space. Given a spatial relationship between two objects A and B and another relationship between objects B and C, the system is able to compute the relationship (or possible relationships) between objects A and C.
SPARQS represents a major step in realising automatic manipulation of objects and relationships in space. It is capable of deriving the composition of spatial relationships between objects of random shapes and types. To our knowledge, it is the first and only available system that is capable of deriving composition tables for different types of spatial objects.