Rough world – a simulation based comonsense knowledge system for Artificial Intelligence

  • Rough world – a simulation based comonsense knowledge system for Artificial Intelligence
EEECS Summer Research Internships 2018

Proposed Project Title:

  • Rough world – a simulation based comonsense knowledge system for Artificial Intelligence

Principal Supervisor(s):
  • John Bustard


Project Description:

Roughworld[1] is a platform for common-sense AI which aims to represent everyday human life in a manner that an AI program could use and understand.

The project is currently in its early stages but is able to create and store 3D maps and objects, as well as a general representation of a human body, and can move this model into many different poses.

We can simulate a human’s day-to-day activity, representing changes to poses and objects as ‘actions’ and a series of actions as a ‘story’.


Objectives:

This project is concerned with moving towards this goal by developing effective tools to collect useful data on human activity that is usable by the rough world system. The project includes splitting this ambitious goal into a number of smaller data collection tasks, such as formalising floorplans/interior layouts, human poses, common human ‘activites’ etc.

The project also involves gathering and formating existing datasets, such as American Time-Use data to create a high level scope of the data to be collected (as wordnet is used for imagenet).

Time permitting, the project includes the development of software to assist with collecting suitable data using the sensing systems of the Makerspace and IoT lab as well as using Amazon’s mechanical turk to crowdsource this data.


Academic Requirements:

The scheme is open to all EEECS Undergraduates (apart from students on the BIT degree pathway and students who are due to graduate this summer)

The project is suitable for someone interested in getting an introduction to scientific data collection, management and crowdsourcing, crucial skills for those interested in doing research in data analysis and machine learning.


General Information:

Each internship will last between 6-8 weeks and will pay a weekly stipend of £250.

Accommodation and travel costs are not provided under this scheme.

Start date: (Flexible based on student availability provided the project is complete before the start of term)

Duration:  8 (Weeks)

Location: Computer Science Building (IoT Lab)

Further information available at: http://www.qub.ac.uk/schools/eeecs/Research/


Contact details:

Supervisor Name: John Bustard
Address:

Queens University of Belfast
School of EEECS,
Computer Science Building,
18 Malone Road,
Belfast
BT9 5BN

Email: j.bustard@qub.ac.uk

For further information on Research Area click on link below:

[1] https://github.com/johndavidbustard/RoughWorld/wiki