Blog

Aug 20, 2012

Enhanced AI: The Key to Unmanned Space Exploration

Posted by in categories: engineering, robotics/AI, space

The precursor to manned space exploration of new worlds is typically unmanned exploration, and NASA has made phenomenal progress with remote controlled rovers on the Martian surface in recent years with MER-A Spirit, MER-B Opportunity and now MSL Curiosity. However, for all our success in reliance on AI in such rovers — similar if not more advanced to AI technology we see around us in the automotive and aviation industries — such as operational real-time clear-air turbulence prediction in aviation — such AI is typically to aid control systems and not mission-level decision making. NASA still controls via detailed commands transmitted to the rover directly from Earth, typically 225 kbit/day of commands are transmitted to the rover, at a data rate of 1–2 kbit/s, during a 15 minute transmit window, with larger volumes of data collected by the rover returned via satellite relay — a one-way communication that incorporates a delay of on average 12 or so light minutes. This becomes less and less practical the further away the rover is.

If for example we landed a similar rover on Titan in the future, I would expect the current method of step-by-step remote control would render the mission impractical — Saturn being typically at least 16 times more distant — dependent on time of year.

With the tasks of the science labs well determined in advance, it should be practical to develop AI engines to react to hazards, change course of analysis dependent on data processed — and so on — the perfect playground for advanced AI programmes. The current Curiosity mission incorporates tasks such as 1. Determine the mineralogical composition of the Martian surface and near-surface geological materials. 2. Attempt to detect chemical building blocks of life (bio-signatures). 3. Interpret the processes that have formed and modified rocks and soils. 4. Assess long-timescale (i.e., 4-billion-year) Martian atmospheric evolution processes. 5. Determine present state, distribution, and cycling of water and carbon dioxide. 6. Characterize the broad spectrum of surface radiation, including galactic radiation, cosmic radiation, solar proton events and secondary neutrons. All of these are very deterministic processes in terms of mapping results to action points, which could be the foundation for shaping such into an AI learning engine, so that such rovers can be entrusted with making their own mission-level decisions on next phases of exploration based on such AI analyses.

Whilst the current explorations on Mars works quite well with the remote control strategy, it would show great foresight for NASA to engineer such unmanned rovers to operate in a more independent fashion with AI operating the mission-level control — learning to adapt to its environment as it explores the terrain, with only the return-link in use in the main — to relay back the analyzed data — and the low-bandwidth control-link reserved for maintenance and corrective action only. NASA has taken great strides in the last decade with unmanned missions. One can expect the next generation to be even more fascinating — and perhaps a trailblazer for advanced AI based technology.

6

Comments — comments are now closed.


  1. GaryChurch says:

    Explain what this has to do with the Lifeboat mission please.

  2. Tom Kerwick says:

    “Explain what this has to do with the Lifeboat mission please.”

    Space exploration/colonization is often discussed on Lifeboat — unmanned space exploration a precursor to this — and the subjects of AI and engineering also relevant.

  3. JohnHunt says:

    There is an interesting line of reasoning that goes like this…One increasingly likely explanation for Fermi’s Paradox is that intelligent civilizations routinely destroys itself via its own technology before said civilization can establish a self-sustaining colony far enough away from that technology. But a self-sustaining lunar or Martian colony is conceivably within reach within just a few decades. What technology would not only destroy the home planet but other planet in the solar system. And, if this were to be the case, then just how far out is safe enough? Another star system, the Oort cloud, or perhaps the outer solar system is far enough. Sending an automated system to prep a site for human habitation would serve the survival of humanity in all of these locations.

    I would like to suggest that you all Google: “ALPH automated Mars”.

  4. “Sending an automated system to prep a site for human habitation would serve the survival of humanity in all of these locations.”

    True, but sending a manned mission to establish a site would serve better.
    I do not think what Kerwick is citing as “AI” qualifies as such.

  5. Tom Kerwick says:

    “I do not think what Kerwick is citing as “AI” qualifies as such.”

    Gary- any machine with a learning capability constitutes AI- it doesn’t have to look like C-3PO. Adaptive control systems can have AI- a simple prolog script can have AI. I don’t think a retired coastguard with no background in AI is in a position to voice authority on what constitutes AI and what does not. NASA are doing great work with the unmanned missions. It amazes me on how far they have progressed, and I would hope to see them augment future missions with more and more enhanced AI as they progress in this field.

    I wouldn’t agree with you either on sending manned missions to new worlds without first checking out the terrain with explorers, though that’s just a matter of opinion — and risk.

  6. GaryChurch says:

    “I don’t think a retired coastguard with no background in AI is in a position to voice authority on what constitutes AI and what does not.”

    You are a jackass