快猫短视频

LIKE a SENTINEL defending the cyber-sky, a graphical representation of a jet
fighter flies across a simple, polygonal landscape. Suddenly, off to one side of
the computer screen, a second jet appears. The defender responds immediately and
a dogfight ensues.

The intruder turns tightly and begins to climb. As it banks, the defender
follows close on its tail. Then the intruder levels off momentarily before
dropping into a steep dive. As if sensing that its prey will try to pull away,
the defender rolls over, aligning its nose with the fleeing aircraft. The
intruder is now dead in its sights, but there is no gunfire and moments later
both jets vanish.

Peter de Bourcier, who works for the Cambridge software company CyberLife
Technology, watches all this and notes down the defender鈥檚 tactics. Its
manoeuvres are typical of an experienced pilot hunting an enemy. Yet this is no
human Top Gun, but an intelligent software 鈥渃reature鈥� that defence researchers
hope will one day fly a real plane. Unlike the intruder, which simply performs a
set of pre-programmed routines, the creature must work out everything for
itself, from how to operate the flight controls in order to stay airborne to the
best tactics for outwitting its enemy.

The pilot is one of the most ambitious entities to be built with the
techniques of artificial intelligence and artificial life. It has 鈥渆yes鈥� that
see its world and a neural network for a brain which is washed with virtual
chemicals that alter its thinking and actions. Nearly everything about it is
controlled by binary genes. It can learn from past experience and reason when
faced with novel situations.

Its behaviour is uncannily human, which is why creatures like it are being
courted by everyone from high-street banks to defence research organisations as
a stand-in for the real thing (see 鈥淰irtual banking鈥�). Perhaps most surprising
of all, the technology that makes the creature tick is not the product of
high-flying academic or defence research. It started life in a virtual pet from
an innovative computer game鈥攁ptly called Creatures.

Released in 1996, Creatures opens the door to an interactive world called
Albia. Here, various virtual life forms eat, mate and play. The player鈥檚 role is
to rear a cartoon-like creature called a norn, and to help it through its
encounters. Behind the norn鈥檚 endearing exterior is a web of fantastically
complicated programs.

The man who dreamt up norns is veteran games programmer Stephen Grand. In
1992, CyberLife presented him with a challenge. 鈥淢y task was to create some
software agents that people would enjoy keeping as pets,鈥� he says. 鈥淚t was clear
that people would have to have a rapport with their creatures, and thus that
they would have to believe they were really alive. The point of no return came
when I reasoned that there was no way of fooling people that something was
alive. I would have to set out actually to create life.鈥�

Grand was the right man for the job. 鈥淚鈥檝e been fascinated by both virtual
worlds and biological approaches to AI for twenty years,鈥� he says. 鈥淚n 1992, I
suddenly found myself with the opportunity, the skill set and a plausible amount
of computer power, so I went for it.鈥�

He decided to create his creatures as nature had done, from the bottom up.
But rather than wait for evolution to run its course, he fast-forwarded: he gave
his animals more than 300 genes, dictating everything from brain structure to
biochemistry. Grand did not want to program every minute action of the
creatures. Instead, he wanted to make them autonomous in their own world. So he
gave them simple instincts and drives to satisfy, such the desires to eat, breed
and avoid pain. He endowed them with the ability to learn, and hoped that
complex behaviours would emerge.

The norn鈥檚 brain is a software-based neural network鈥攁 vast array of
nodes interconnected by a complex of virtual wires or dendrites. Each node has
one or more inputs and fires off a signal to other nodes when its inputs reach a
certain threshold. Although researchers have been designing neural networks for
decades, none had the properties Grand needed. 鈥淪o I had to invent my own,鈥� he
says. His solution is a network of 1000 nodes divided into nine 鈥渓obes鈥�.

As a norn explores Albia, it encounters many objects which it can see, touch,
hear, smell or taste. Signals from the norn鈥檚 senses feed through to its
鈥渁ttention lobe鈥�, which contains a node for every kind of object in Albia, from
carrots and toys to poisoned plants and other norns. The frequency and intensity
of the sensory signals cause the nodes to fire at different rates. An algorithm
monitors this firing and directs the norn鈥檚 attention to the most insistent
signal.

Once the norn鈥檚 attention has been captured by an object, say a carrot, its
perception lobe collects the various messages from its sensors
(see Diagram).
It passes these to the 鈥渃oncept lobe鈥� which, with 640 nodes, is by
far the largest. This is essentially a pattern matcher. It looks for familiar
signal patterns coming from the perception lobe. The pattern triggered by the
size and shape of the object, for example, might tell the concept lobe that it鈥檚
dealing with a carrot.

The concept lobe sends a 鈥渃arrot鈥� signal on to the 鈥渄ecision lobe鈥�. This is a
small lobe with only 16 nodes, each of which represents a single possible
action, such as 鈥済o left鈥�, 鈥済o right鈥�, or 鈥渄eal with the object at hand鈥�. If the
object is a carrot, the norn will eat it.

One of the valuable properties of neural networks is that they 鈥渓earn鈥�. They
are used, for example, to look for flaws in glass bottles. The network is
trained by showing it images of flawless bottles, then images of bottles with
cracks. The firing thresholds of the nodes are then tweaked until the network
gives one output for a perfect bottle and another when it spots a crack. The
network鈥檚 structure and thresholds are then fixed, and it should be able to spot
any cracked bottles as they fly by on a conveyor belt.

By contrast, the structure and thresholds of the norn鈥檚 neural networks are
never set in stone. They are continually readjusted by experience. This gives it
an ability to learn and respond to new situations based on past experiences.

The dendrites between nodes, for example, weaken and die if they are not
used. But every time a dendrite carries a signal it is strengthened by a
reinforcing algorithm. When a dendrite dies, the node on the end can send out
another tendril to attach to an active node either in its own lobe or a
neighbouring lobe. If this new dendrite turns out to be useful then it will be
reinforced. This way the norn can forge connections for learning new things
without affecting the network鈥檚 established patterns of use.

This ability to continuously learn and the lobed structure are essentially
extensions of what other neural networks already do. The real innovation in the
norn is its 鈥渂iochemistry鈥�, which also helps to continually restructure the
network. 鈥淚t seems odd that AI missed out biochemistry when the brain swims in a
sea of chemicals,鈥� says Toby Simpson, executive producer of Creatures.

The levels of the norn鈥檚 drives鈥攕uch as the need to eat and avoid
pain鈥攁re controlled by 鈥渂iochemicals鈥�, which are really numbers from 0 to
255. Like real hormones and neurotransmitters, these numbers relay messages
around the norn鈥檚 body and brain. They influence the brain鈥檚 decisions by
changing the firing thresholds of nodes in the neural network.

The chemicals are secreted by 鈥渆mitters鈥� attached to neurons and sensors, and
their levels are monitored by 鈥渞eceptors鈥� attached to other neurons and sensors.
The higher the level of a chemical, the more pressing is its associated drive.
And as the norn travels around Albia it attempts to reduce these drives.

When a norn is born, it has only a few 鈥渋nstincts鈥�, such as the urge to
wander and to try to eat small things. These instincts are not hard-wired, but
learnt by the neural network before birth. So when an infant norn comes across a
carrot, it will instinctively eat it. As it does so, emitters release the
virtual equivalent of starch. Reactions inside the norn convert this into
glycogen (which real animals use to store energy), plus a chemical that reduces
the level of the hunger drive.

This does the norn 鈥済ood鈥� and, accordingly, receptors in its brain that
detect the decrease in the hunger chemical reduce the firing thresholds of nodes
involved in recognising carrots and deciding to eat them. These pathways will
then fire more easily than others and will be strengthened by the reinforcing
algorithm.

On the other hand, if the norn eats a poisonous plant, the emitters release
pain chemicals. Receptors respond by increasing the firing thresholds of nodes
in the concept and decision lobes that link poisonous plants with the decision
to eat. These nodes are then less likely to fire, and in time the dendrites
linking them die. In this way, the instincts of the young norn are overlaid by
appropriate responses to different situations鈥攊n other words, it learns by
experience.

And this is not the only way a norn learns. The player can also intervene to
influence its behaviour by clicking the cursor over 鈥渟lap鈥� or 鈥渢ickle鈥� zones on
the norn鈥檚 body, releasing punishment or reward chemicals that inhibit or
strengthen certain memory patterns.

As if this degree of complexity were not enough, just about everything in the
norn鈥攆rom the way nodes operate and the structure of the lobes to the
locations of emitters and receptors鈥攊s determined by genes. Norns have a
single chromosome made up of a long string of bytes divided into 320 sections
that specify different aspects of the creature. When norns breed, some parts of
this code cross over from one parent鈥檚 chromosome to the other, so the genes
mix. This, plus occasional crossover errors and random mutations, means that
every norn is different. And, as with humans, a norn鈥檚 behaviour is a product of
the interaction between its unique genetic make-up and experience.

Before Grand began creating Creatures, most experiments in artificial life
had focused on replicating individual aspects of organic life. Researchers had
used neural networks to model brains, and genetic algorithms to study
evolutionary adaptations. But few had tried to create a whole organism with
these techniques.

This point was not lost on Dave Cliff, an artificial life expert now at the
AI Laboratory of the Massachusetts Institute of Technology in Boston. Warner
Interactive called in Cliff to give an opinion of Creatures when it was deciding
whether to invest in the game. At first he thought it was a con. He didn鈥檛 think
it possible to have such complex technology running in real-time on a home
computer. But when he turned the machine off and made Grand start the program
from scratch, the creatures began to evolve all over again in a completely
different way.

鈥淚t represented a major engineering achievement,鈥� says Cliff. 鈥淭he coupling
of the neural network to the biochemistry was genuinely novel.鈥�

Grand鈥檚 hope that employing artificial life techniques would allow norns to
display complex behaviours has not only been fulfilled, it has been surpassed.
鈥淲hen you鈥檙e trying to breathe life into something, you expect it at some point
to get up and start having a mind of its own, but it still comes as a shock when
it happens,鈥� he says. 鈥淭he first time I felt I was really onto something was
when I caught two of my creatures apparently playing ball with each other. I
nearly fell off my chair!鈥�

Grand admits that it鈥檚 difficult to tell if norns behave the way they do for
the same reasons that humans do. Nevertheless, their behaviour is
human-like enough to have caught the eye of researchers in other industries.

鈥淚t was clear that behind the trappings of a strange computer game, there was
some complex science going on,鈥� says Simon Hancock of the British government鈥檚
Defence Evaluation and Research Agency. At DERA鈥檚 flight management and control
research department in Bedford, Hancock has been trying to invent adversaries
for pilots flying missions in flight simulators. Up to now, DERA has used
computer-generated opponents that follow rigid, rule-based systems.

鈥淲hen we put a test pilot into a simulation of one of our new aircraft, we
need to put him in as realistic a scenario as possible,鈥� he says. 鈥淚f the pilot
can sense that something unnatural is happening, that distracts from his task of
evaluating the aircraft.鈥� Hancock hopes that norn technology will provide more
realistic enemies that fight with the skill and ingenuity of human pilots.

This is the project that is running on de Bourcier鈥檚 screen at CyberLife. His
machine is evolving generations of virtual pilots which are trying out different
flight strategies as they adapt to controlling the digital jet and tracking the
enemy. The success of each pilot is judged by simple criteria: at first, by how
long it stays up in the air, then by how closely it tracks its prey or evades an
attacker and, finally, by how long it holds the enemy in its sights. The best
pilots from one generation are then used to sire the next.

Like norns, the synthetic pilots contain a cocktail of biochemicals, but
these are not linked to specific drives. Instead, the chemicals, receptors and
emitters are just thrown in as wild cards to see what the pilots make of them.
It鈥檚 very difficult to tell if the chemical reactions that have evolved
represent fear, stress or aggression, says de Bourcier. Whatever their emotional
equivalent, they have helped to create formidable pilots.

After running populations of 40 pilots through up to 400 generations of
evolution, CyberLife has software agents that don鈥檛 crash their planes and can
keep targets in their sights for a long time. On paper, these synthetic pilots
look as good as human aces, but DERA has not yet put humans through exactly the
same test on a simulator. That would be one of the next steps for DERA and
CyberLife to take.

The synthetic pilots demonstrate some remarkably human behaviour, such as
banking the jet in a turn and rolling over before starting a steep dive. Humans
roll over before diving to stop the blood rushing to their heads. The synthetic
pilots don鈥檛 suffer such physical constraints. They have developed this tactic
because it helps to keep targets in their sights for longer. The synthetic
pilots have also evolved distinctly nonhuman techniques, such as flying the jet
in a continuous roll, which can improve stability in some extreme
manoeuvres.

Controlling a digital aircraft in the calm of cyberspace is one thing, but
could norn technology triumph in a real plane in a real dogfight? The
researchers at DERA and CyberLife want to find out. 鈥淚f these artificial pilots
can fly simulated aircraft around in cyberspace, why can鈥檛 they fly in real
life?鈥� asks Hancock.

Most existing unmanned air vehicles are flown remotely by a pilot on the
ground. This is not ideal. 鈥淔irst, it is very difficult to fly an aircraft
successfully without all the cues from the outside world,鈥� says Hancock.
鈥淪econdly, if the communications between the ground and the aircraft are jammed,
the aircraft is cut off.鈥�

One answer, Hancock believes, is to create a synthetic pilot that a commander
on the ground could give instructions to and then leave to carry out the mission
autonomously. If attacked by an enemy, it would know how to take evasive action.
But the implications go further than that. If there is no human inside the
aircraft, its design need no longer be constrained by human dimensions and
frailties. For example, it could be smaller and be made to turn and accelerate
faster. Humans can tolerate a force of up to roughly 9 g鈥攁
synthetic pilot might find it useful to pull 25 g turns.

One thing that the work on synthetic pilots, norns and other projects has
demonstrated, says de Bourcier, is that 鈥渢o develop intelligent behaviour you
need a dynamic environment: one that reacts and changes鈥�. CyberLife is now
employing this lesson back in its virtual world. The company is experimenting
with the idea of turning the entire environment of Albia into an autonomous
synthetic biological system, with a sun that rises and sets and a gaseous
atmosphere that plants and animals breathe. So far, the company has created
digital plants that photosynthesise sunlight and digital bees that look for
nectar and pollinate plants. Already, unprogrammed behaviours have emerged,
such as swarming bees and plants that adapt to different levels of water and
shade.

It seems anything is possible. Virtual pets may be fun, virtual ecosystems
may be instructive, but if virtual fighter jet pilots can replace real pilots,
who knows what human roles these exotic creatures will be taking on next.

HOW long would you spend queuing in a bank before storming out? The American
bank technology company NCR wanted to find out what really goes on in customers鈥�
heads when they enter a high-street bank. So it commissioned CyberLife to breed
surrogate people that could wander around inside a virtual bank and test the
layout of machines and services鈥攚ithout the time and expense of real-life
tests.

鈥淭he technologies that [CyberLife] were working on seemed to give us the
potential to produce very complex simulation behaviours without having to spend
hundreds of man-years defining the behaviour in fine detail,鈥� says Lee Dove of
the Dundee-based advanced technology branch of NCR鈥檚 financial solutions
group.

CyberLife adapted its technology to create software agents complete with a
number of 鈥渄rives鈥�, such as the desires to deposit or withdraw cash or consult a
financial adviser. When an agent first enters the bank it doesn鈥檛 know where to
go for money or a statement, so it wanders around and tries interacting with
things. These include virtual automatic cash machines, cashiers and financial
and business advisers.

NCR records the activities of real bank customers on video cameras and the
information is used to evolve agents with the same characteristics as customers
of individual branches. Customers in a city-centre branch behave differently
from those in a rural branch, for example, says Dove. 鈥淚n the city, you have a
lot of people who come rushing in, grab what they want and get out again. In the
rural areas you鈥檝e got people drifting in鈥攖hey鈥檝e got social requirements,
they want a chat, they meet their friends.鈥� Eventually, Dove expects virtual
versions of typical types of customers to emerge, such as old ladies,
businessmen and so on.

CyberLife found that its agents queued and used the different services in
similar ways to real customers in a real bank. 鈥淚t proved that our creatures
behave in a realistic way,鈥� says Anil Malhotra of CyberLife.

Banks can use mathematical algorithms to work out the rate at which queues
will move with various combinations of cashiers and cash machines. But unlike
the maths, the software agents will reveal how quickly customers reach a level
of frustration that will make them walk out. The agents have one drive that
encourages them to wait, and another which urges them to leave. These compete
with the agent鈥檚 desire to withdraw cash or see an adviser. A successful bank
layout will enable the agent to complete its transactions before it is
overwhelmed by the urge to take its business elsewhere.