l CoVErFEAtUrE l
The thinking space robot
Dr Derek Long of the Department of Computer
and Information Sciences presents the Mars rover
What is the focus of might take longer than expected, a on Earth learn about one they have
your research? drill might hit hard rock instead of missed it! An intelligent rover could
My research is in artificial soft sand and so on. Currently, in be programmed in advance to take
intelligence (Ai) – specifically this situation, the rovers are forced photos as soon as it sees a dust devil.
Ai planning and problem to simply do nothing and wait for a
decomposition. this involves new plan from Earth. Meanwhile, What stage is the project at?
constructing activities to achieve scientists back on Earth are working Last November we finished a large
pre-determined goals, and selecting on a new plan based on the collaborative project called ‘the
between these goals should assumption that the previous plan Autonomous scientist’, funded under
any problems occur. this has was successful. By the time they CrEst (Collaborative research in
applications in a wide variety of next communicate with the rover, it is Exploration systems technology),
which involved creating an ExoMars
prototype robot, for which i did the
WHAT PEOPLE DON’T OFTEN REALISE IS THE ENORMOUS re-planning programming. i am
SPIN-OFF SPACE RESEARCH HAS ON EARTH
now working on the specification of
software architecture. the target date
for completion is the European space
areas, including space research, too late to rewrite the new plan. this Agency’s ExoMars mission in 2013.
logistics, industry, supply chain system can result in days – and vital
» DR DEREK LONG
organisation and even daily activities scientific opportunities – being lost.
Derek has
What potential does this
such as planning tourist itineraries. By migrating the decision-making
masterminded
new technology hold for
the creation of
Ai is particularly interesting in the process from Earth to space we
space robots
space research?
context of space because it’s so could save a lot of time. Every day
with AI, paving
this technology could be very
high risk – one mistake could lose we lose due to failures in planning is
the way for
exciting – the thinking rovers are
the craft. For that reason the space an opportunity for science lost.
greater scientific
capable of making some amazing
industry is pretty conservative about discoveries discoveries. What people don’t often
introducing new technology until it What kind of activities would realise is the enormous spin-off
has proved it’s trustworthy. these rovers be capable of? space research has on Earth. Mars
Ai enables the rover to recognise once had an atmosphere but today it
how can AI benefit space good science targets, deploy its is a dead planet, so investigating the
missions in practice? instruments and collect and transmit history of the planet could prove very
in space missions, the activities of data without having to wait for important in understanding the effects
robotic rovers are planned on Earth specific instructions. For example, of climate change on Earth and
and transmitted to the rovers to be currently soil drilling only happens preventing it from happening here.
executed over one or more days. when there’s full solar energy, while
they might instruct the rovers to the intelligent rover could start the
collect data such as soil samples work in late afternoon
or photos of sedimentary rock. but recognise when it
scientists on Earth might have needs to stop and retract
two 40-minute windows each day instruments, once more saving time.
in which to communicate with the Another example is dust devils,
rovers. A problem is that plans which are mini tornadoes on
created on Earth can fail when they Mars. these are of great
are executed by the rovers – an interest to scientists but
instrument might fail, navigating by the time scientists
strathclyde people 19
US-SP-SP08.indd 19 11/4/08 16:10:21
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36