Do androids dream of electric sheep? Only Phil Dick knew for sure, but Christoph Adami has also been wondering on behalf of scientists.
In his recent paper What Do Robots Dream Of, Dr. Adami, Professor of Applied Life Sciences at the Keck Graduate Institute, speculates that a robot might benefit from some "down time" just like people do.
Recent work in the study of dreaming indicates that more than just subconscious entertainment is going on. Sleep appears to help us work through and understand events of the day. Sleep also seems to provide a mechanism for impressing important memories on the brain, to make sure we have a long-term record of an event or concern. Sleep also seems to have a role in learning a skill; people who practiced a skill and then slept on it were more skillful than those who had not yet had a chance to sleep.
Dr. Adami speculates that if robots were given an alternate state, one in which the robot stopped exploring and instead focused on a problem or obstacle, it could provide benefits for them just like it provides benefits for human beings.
“How would dream-inspired algorithms work in terra incognita? A robot would spend the day exploring part of the landscape, and perhaps be stymied by an obstacle. At night, the robot would replay its actions and infer a model of the environment. Armed with this model, it could think of–that is, synthesize–actions that would allow it to overcome the obstacle, perhaps trying out those in particular that would best allow it to understand the nature of the obstacle. Informally, then, the robot would dream up strategies for success and approach the morning with fresh ideas.“
The robot's software designers could provide a robot with an internalized model of itself as well as the parameters of the situation. Then, the robot could explore different "dreamlike" situations, in which different parameters were distorted or exaggerated, until a solution could be found.
I can think of no more perfect place to start than with the "Starfish" robot created by Josh Bongard, Victor Zykov, and Hod Lipson of Cornell University. The Starfish robot is a new four-legged robot that can automatically synthesize a predictive model of its own topology (where and how its body parts are connected), and then successfully move around.
Science fiction fans also remember SAL 9000, the artificial intelligence from the 1984 film 2010: The Year We Make Contact, taken from the book 2010: Odyssey Two (1982) by Arthur C. Clark. In the film version, SAL asks Dr. Chandra "Will I dream?" He replies "Of course you will. All intelligent beings dream. Nobody knows why... Perhaps you will dream about HAL - as I often do."
Update 19-Mar-2007 Several readers wrote in with an Isaac Asimov short story from 1975, Point of View, in which a big computer named Multivac is having problems coming up with the right answers. A dad remarks to his child that Multivac is not a simple mechanical device (a machine) that would be easy to fix, nor is it as intelligent as a man, in which case you could ask what was wrong. His son remarks that maybe Multivac was like a kid:
"... you say you've got to keep Multivac busy day and night. A machine can do that. But if you give a kid homework and told him to do it for hours and hours, he'd get pretty tired and feel rotten enough to make mistakes, maybe even on purpose. -So why not let Multivac take an hour or two off every day with no problem-solving - just letting it chuckle and whir by itself any way it wants to."
Thanks to Dave for thinking of the story and another reader for nailing down the details in the comments. (End update.)