Slashdot Mirror
Smart Satellite Sets Its Own Priorities
Roland Piquepaille writes "Currently, satellites take pictures of whatever is in front of their cameras. But hydrologists from the University of Arizona (UA), working with the Jet Propulsion Laboratory (JPL) are creating spacecraft that think for themselves. Their smart software, which is tested on NASA's EO-1 satellite, can be used on all kinds of spacecraft. This software has three components: an image formation module, a science algorithm module, and a continuous planning module. This onboard planner reschedules what to film in conjunction with what the scientific algorithms have detected. This software has already detected floods in Australia and will be adapted to also detect volcano eruptions and changes in ice fields. More details and references are available in this overview, including images of the flood detected by this smart software."
Nasa: For the last time, will you please stop looking at the nude beaches on Earth and instead look at Pulsar 19834
Satellite: I'm afraid I can't do that Dave
Well I tried that in my last job and got canned!
from the previous story. *Then* we're all in trouble...
The "hot chick chick next door suntanning nude in the backyard" detection module, that is.
I browse Slashdot at +3, Funny
just remember:
"I've just picked up a fault in the AE35 unit. It's going to go 100% failure in 72 hours"
or
HAL: This mission is too important for me to allow you to jeopardize it.
Dave Bowman: I don't know what you're talking about, HAL?
HAL: I know you and Frank were planning to disconnect me, and I'm afraid that's something I cannot allow to happen.
Dave Bowman: Where the hell'd you get that idea, HAL?
HAL: Dave, although you took thorough precautions in the pod against my hearing you, I could see your lips move.
[The satellite's] onboard planner reschedules what to film in conjunction with what the scientific algorithms have detected. This software has already detected floods in Australia and will be adapted to also detect volcano eruptions and changes in ice fields.
John Ashcroft has directed engineers at the National Security Agency to design algorithms to follow, in increasing order of priority, the movements of terrorists, dissidents, persons engaged in the sin of dancing, and calico cats.
Opinions on the Twiddler2 hand-held keyboard?
It's not like this software has to be on board the spacecraft. It's well under a second to do a round trip communication with a satellite, so there isn't much value to having the camera steered on board vs. from a ground computer unless you are photographing things that are over in 1/2 a second. Most anything large enough to see from orbit is going to unfolding slowly over days, not seconds.
The obvious exception would be a nuclear explosion, but there is already a network of satellites in place to detect those.
For spacecraft that venture further afield this could certainly be of value though.
Currently, satellites take pictures of whatever is in front of their cameras.
and will continue to do so for a long time.
Isn't this what software here on earth can do and are doing? Putting it on the satellite does not change anything. I think you would want the satellite to send all the data it collects, so why not filter it here on earth. If the satellite sends only the data it finds interesting, it will miss some events that it was not programmed for but would be useful to the scientific community. Send all the data and filter it here.
This reminds me a lot of the robot scientist from earlier this year, which was able to formulate hypotheses and perform experiments to determine the metabolic pathways of yeast. I'm quite excited about where this sort of technology can take us in the future, removing much of the drudgery that grad students/technicians have to do and accelerating the advance of scientific progress.
mmmmmmm... lusting after overclocked mobos outside of their cases wanting to do a little bit of Software EXchange but only being able to do single player mode... ;p
Base: "Err..., we're getting a little bit of unexpected orbital variation in the new satellite and I can't tell it to point its detectors away from the intermediate hardware production plants..."
So.
When does SkyNet become self-aware?
Between this story and the one the immediately preceded it, was anyone else thinking SkyNET? Or another summer movie?
V GER.
Gaze control is important, but far more useful in earth-bound systems. A good application would be to use it with surveillance cameras and traffic monitoring cameras, so that the interesting stuff is presented to humans, while endless pictures of empty rooms and smoothly flowing traffic are ignored.
The problem with satellites is it's not like you can just climb down into the bomb bay and turn them on to existentialism and hope they'll convince themselves they don't exist so they'll disarm.
This article reminds of the optical systems of mantis shrimp as a supreme example of controlled visual integration of optical information.
With up to 10 color bands and 2 to 4 polarizations in a multi-band linear array across each eye, the little beastie is the champion for color vision . Because the eye bands of the left and right eyes are at an angle to each other, the shrimp can sweep the two linear arrays across an area to create binocular polychromatic vision (more remarkable is that each eye has a central trinocular field of vision so each eye has independent depth perception). The entire system is controlled by X-Y scanning of the two eyes (either independently or in sync) to sweep across an area to to create a 2-D high resolution multi-spectral image from 1-D linear arrays.
The point, for satellite sensors, is that more dynamic control of a multi-spectral sensor Earth-observing system can adaptively gather data at multiple resolutions -- gathering super-resolution scans on interesting regions such as a flash floods, forest fires - while retaining a low resolution full-image situation awareness. This intelligence needs to be local because, in the mantis shrimp at least, the control loop operates on millisecond timescales. Satellite-local processing would also reduce the downlink bandwidth requirements as the raw sensor output could easily exceed 10 gigabits/sec.
Two wrongs don't make a right, but three lefts do.
So it can learn from what sort of things you have asked to observe in the past and have future unrequested data flagged as interesting? Very difficult for it to actually produce useful results. Ground based crunching of a vast data glut from a large constellation of inexpensive dumb sats with lots of redundancy would seem more appropriate with ground based commanding and intra constellation communication to handle sats that are out of contact (interesting orbits are not geosynch)
Its an interesting challenge to be responsive to variable priority planning requests from multiple clients some of whom can request 'in theatre' with mobile transmitters not just at permanent ground-stations. Really hard computational problem with strict time constraints and lots of factors such as power-up times, manauover times etc.
I had a nice idea of auctioning satellite time so that you have to pay more to bump requests. Disruption to a schedule by a new request would be factored into the cost of accepting the request but the various clients would be put into financial competion to outbid for service. Use the market to schedule.
They are a big deal.
Spacecraft control automation has been a huge problem for decades. The ability to manage failures and continue degraded operations rather than safemode the spacecraft (and stop collecting data in many cases) is still unproven.
Lets hope the developers of this new smart technology dont teach it pleasure or mission control will be given an error code while it silently records nude beaches and voyeur material. The next paparazzi may be a mechanical one. Hide the children, the satellite is coming!
-Rights? What rights?
It was really only a matter of time before automated image selection moved to further applications. From what I understand, Fermilab has been doing a very similar thing - with millions of "images" from each collision, the _only_ way to look at the remotely interesting ones is to have an automatic selection process.
It does, however, make you wonder about the really interesting things that could be missed in the process.
This statement is false.