Contributions towards "AI for Social Good" Theme
Austin Tate, 29-Oct-2019


-----------------------------------------

AI Planning for Emergency Response

Our AI Planning Group explores representation and reasoning mechanisms
for inter-agent activity to support teams of people, robots and
computer systems working in a coordinated fashion. The group develops
generic approaches by engaging in specific application areas
especially for emergency response, crisis action planning, help desks
and procedural assistance as well as command and control, space
systems, manufacturing, logistics, construction, etc.

The long term aim of the work is the creation and use of task-centric
virtual organisations involving people, government and
non-governmental organisations, automated systems, grid and web
services working alongside intelligent robots, vehicle, building and
environmental systems to respond to very dynamic events on scales from
local to global.

Links

AI Planning Group Website: http://www.aiai.ed.ac.uk/project/plan/
The Helpful Environment Vision: http://blog.inf.ed.ac.uk/atate/helpful-environment/

Images

http://www.aiai.ed.ac.uk/project/cosar-ts/
Has some images I took at an exercise in the Firth of Forth - click on
small ones to get full res versions. Please credit images as described
there.

http://www.aiai.ed.ac.uk/project/co-opr/
Image in there might be of use as it shows Inf people and
collaborators in our simulated operations centre that was in Appleton
Tower.


-----------------------------------------

The Helpful Environment

"The Helpful Environment" vision is of a future in which ubiquitous
computing, sensor grids and networked systems combine to help the
individuals, families, businesses, organizations, the public at large,
regions and countries to be self supportive and mutually helpful with
specialised resources for their daily lives, for help and assistance
in emergencies. The vision, some international programmes which
contribute to it, some of the organisations that are pursuing this
vision and some of the Edinburgh projects and research that will we
hope will help make it a reality are described in this paper:

The Helpful Environment: Geographically Dispersed Intelligent Agents
That Collaborate, Special Issue on “The Future of AI”, IEEE
Intelligent Systems, May-June 2006, Vol. 27, No. 3, pp 57-61. IEEE
Computer Society.

Link

http://www.aiai.ed.ac.uk/project/ix/documents/2006/2006-ieee-is-tate-helpful-env-as-published.pdf

Images

http://blog.inf.ed.ac.uk/atate/files/2011/09/2010-05-13-Train-for-Success-1.jpg
http://blog.inf.ed.ac.uk/atate/files/2018/01/helpful-environment-logo-v2.png

-----------------------------------------

Firegrid

The FireGrid consortium brought together many bodies with an interest
in improving response to fire emergencies. The FireGrid project aimed
to harness the potential of advanced forms of computation to support
the response to large-scale fire emergencies. The team included fire
brigades, the UK regulatory bodies for fire safety, supercomputer
centres in the UK and Singapore and other specialist groups and
scientists. The challenges were in:

* Sensing: Data collection from the emergency location with
  instantaneous and continuous relay to the emergency response system
  (involving a large array of sensors communicating with each other as
  a network and with the response system via the Grid);

* Modelling: Simulation tools running in a predictive mode to model
  the evolution of the fire, establish its impact on the structure
  (and therefore predict the collapse), while also analysing the
  intervention alternatives and evacuation strategies;

* Forecast: All simulations, analyses and communications to be
  achieved faster than the evolution of the emergency in real time;

* Feedback: Processing of the continuously updated sensor and
  simulation data relayed back to the active response systems at the
  emergency location and to the emergency services to assist their
  intervention;

* Response: Effective co-ordination of all intervention by a command
  and control system using an intelligent execution support aid.

At the University of Edinburgh, AIAI provided expertise on the
intelligent command and control user interface to present useful and
actionable information to the emergency response coordinator. EPCC's
role was to provide expertise on high-performance computing for
simulation and modelling. Computational models of physical phenomena
were developed, deployed and analysed on High Performance Computing
resources to infer incident conditions by assimilating live sensor
data from an emergency in real time - or, in the case of predictive
models, faster-than-real time. The results of these models were then
interpreted by a knowledge-based reasoning scheme to provide support
information for the emergency responder. These models were accessed
over a Grid from an agent-based system.

The system carried out large scale fire trials, including the
instrumented burning of disused tower block in Glasgow. The Firegrid
project was the subject of much media interest and covered on a BBC TV
Horizon programme.

Link

See http://www.aiai.ed.ac.uk/project/firegrid/

Image
http://www.aiai.ed.ac.uk/project/firegrid/img/Firegrid-Book-Cover-Front.jpg


------------------------------------------

OpenVCE: Open Virtual Collaboration Environment and I-Room: Virtual
Space for Intelligent Interaction

A long term programme of research, development, evaluation and
deployment of assets to support collaborative teams working in a
distributed fashion without necessarily travelling to be
collocated. The OpenVCE and I-Room concepts and approach supports
agility and a green agenda via the creation, release and promotion of
the availability of open source and open educational assets that have
been used thousands of times and are provided in a number of academic,
commercial and US government platforms as starter facilities for
others to create their own tailored virtual collaboration, exhibition
and event spaces. OpenVCE mixes social media, a shared content
management platform and virtual worlds technology support
communities. Part of this is I-Room technology - a "Virtual Space for
Intelligent Interaction" - which has been provided in virtual worlds
such as Second Life, OpenSim and Sinespace and can be used in Virtual
Reality (VR). This award winning facility is designed for distributed
brain storming style meetings and as a virtual operations centre.

Links

http://blog.inf.ed.ac.uk/atate/i-room-a-virtual-space-for-intelligent-interaction/

Images
http://blog.inf.ed.ac.uk/atate/files/2011/09/2010-05-13-Train-for-Success-1.jpg
http://www.aiai.ed.ac.uk/project/i-room/resources/e-response/img/2007-10-17-eResponse_001.jpg


--------------------------------------------------

EASE: knowledge-based system for assessing workplace exposure to
potentially hazardous new substances

EU regulations require a manufacturer of a new substance to notify the
appropriate authority, who will carry out a risk assessment of it. To
aid this process, guidance is provided by the regulator for use by
both authorities and manufacturers. A computer based guidance system
was created which considered exposure to a substance in the
workplace. Exposure assessment is an expert task, requiring an
experienced occupational chemist, as many of the chemical and physical
properties of a new substance are not known to the assessor a
priori. For the system to be deployed, it had to incorporate best
practice knowledge engineering techniques and, as there are
safety-related considerations and AIAI and the HSE are committed to
quality, the work had to be carried out in accordance with ISO9001
standards.

AIAI and the UK Health and Safety Executive (HSE) worked together
using the CommonKADS knowledge engineering methodology to model the
task and capture the knowledge involved. Execution of the work was
audited against TickIT criteria by Lloyds Register. EASE guides the
user by offering a menu of appropriate choices whenever it needs
information. When numerical values must be provided, e.g. vapour
pressure, sanity checks are carried out. The user can always
back-track and change the answer to an earlier question and a full
explanation of the conclusion is always given as well as an
explanation of why a particular question is being asked. The system
has been widely distributed for use by authorities throughout Europe.

Link

http://www.aiai.ed.ac.uk/project/ease/