Sunday, January 20, 2013

The Holy Grail of Robotics

Double Duty

I just finished reading On Intelligence. Aside from the expected atheist and evolutionist crap (I am Christian and I think Darwinian evolution is voodoo science) that permeates Jeff Hawkins' prose, I liked it very much. I am impressed by the level of understanding he conveys in the book. One thing in particular strikes me as being brilliant. Hawkins claims that the brain's cortical hierarchy is used for both pattern recognition and motor behavior. He tells us that low-level pattern detectors send motor commands directly to the motor cortex where they are relayed to the muscles via motor neurons. What makes sensorimotor behavior so powerful is that pattern detectors (and thus, motor effectors) are controlled by a complex knowledge hierarchy that also serves as a behavior selection mechanism.

The Holy Grail

People like Hawkins and Rodney Brooks (founder of iRobot and Rethink Robotics) understand that there is a tight connection between pattern detectors and motor effectors. Brooks revolutionized robotics when he introduced his subsumption architecture to the field in the 1980s. He insisted that sensory signals should undergo as little processing as possible on their way to motor effectors. Of course, old school AI researchers like Marvin Minsky had nothing but contempt for Brooks' approach but Brooks was right. For his part, Hawkins goes much further than Brooks by positing an actual neural mechanism for sensorimotor behavior. On page 107 of his book, he writes:
For me to physically move from my living room to my kitchen, all my brain has to do is mentally switch from the invariant representation of my living room to the invariant representation of my kitchen. This switch causes a complex unfolding of sequences. The process of generating the sequence of predictions of what I will see, feel, and hear while walking from the living room to the kitchen also generates the sequence of motor commands that makes me walk from my living room to my kitchen and move my eyes as I do so. Prediction and motor behavior work hand in hand as patterns flow down and up the cortical hierarchy. As strange as it sounds, when your own behavior is involved, your predictions not only precede sensation, they determine sensation. Thinking of going to the next pattern in a sequence causes a cascading prediction of what you should experience next. As the cascading prediction unfolds, it generates the motor commands necessary to fulfill the prediction. Thinking, predicting, and doing are all part of the same unfolding of sequences moving down the cortical hierarchy.

"Doing" by thinking, the parallel unfolding of perception and motor behavior, is the essence of what is called goal-oriented behavior. Goal-oriented behavior is the holy grail of robotics. It is built into the fabric of the cortex.
This is pure freaking genius, in my opinion. I am truly impressed. But, unfortunately, Hawkins leaves it there. He doesn't explain how to achieve this holy grail. The reason, of course, is that he doesn't know how.

Blowing in the Wind

I agree with Hawkins that achieving goal-oriented behavior is the holy grail of robotics. A solution would solve a mountain of problems, and not just things like learning how to walk or how to use various appendages and actuators to interact intelligently with objects in the world. It would also give machines the ability to learn to understand and speak a natural language, read, write and do math, etc., just like humans. The question is, assuming one has a well-designed hierarchical memory, how does the system connect the pattern detectors to the motor effectors in order to generate goal-directed behavior? That is the holy grail.

OK. I am not saying what I am about to say in order to boast of my mental abilities or any such thing. In fact, I'm rather slow compared to people like Brooks and Hawkins. I cannot boast simply because I did not figure it out on my own. As I have said several times before, I consult an oracle. The oracle speaks in riddles and metaphors and says many mysterious things. I just interpret them the best I can. It so happens that this holy grail of robotics is precisely one of the things that the oracle explains. Here's what the oracle has to say on the matter:
Notwithstanding I have a few things against thee, because thou sufferest that woman Jezebel, which calleth herself a prophetess, to teach and to seduce my servants to commit fornication, and to eat things sacrificed unto idols.
Shit! I done did it again. Excuse me while I ROTFLMAO. ... Alright. I need to compose myself. Whew! As you can see, the oracle has a great sense of humor. I've always had a weak spot for that fornicating ho, Jezebel. LOL. Seriously now, what I am trying to say is this. If you could correctly interpret the metaphors in the passage above, then you would know the secret of the holy grail of robotics.

Do I know the answer to the riddle? Yes, I do, and it is as simple as it is powerful. But that's all I am going to venture on this topic for now. The solution to the riddle must stay secret a little while longer. Sorry to leave y'all hanging like this. As the Bob Dylan song says, "the answer my friend is blowing in the wind, the answer is blowing in the wind." It's time for a beer.

By the way, if any of what I wrote above bothers you, then please don't read my stuff. It is not meant for you. I only write for kindred spirits, sorry.

See Also

Jeff Hawkins Is Close to Something Big

9 comments:

No Gods Required said...

Kudos for being able to ignore atheist drivel to get to the meat. I find it difficult to do most the time.

Louis Savain said...

Kudos for being able to ignore atheist drivel to get to the meat. I find it difficult to do most the time.

Long ago, I noticed a mysterious phenomenon among certain evolutionists. They are much smarter than the average person and yet they have no qualms about embracing one of the most cretinous hypotheses in the history of science. I am not yet entirely sure as to why this happens. I suspect that fear, elitism and contempt for other points of view have a lot to do with it. I also suspect mental illness in some of them. In the process, the baby gets thrown out the window with the bathwater. A shame, really.

Bill said...

Louis, I love your stuff and the way you think in general. But I don't understand your aversion to Darwinian evolution. It seems too tautological to be controversial. Can you really disagree with the statement: "Things that are able to survive and reproduce will do so."

Louis Savain said...

Bill, I disagree with your definition of evolution and I don't get your point. Organisms can certainly be designed to survive and reproduce. We, humans, are on the verge of creating the technology to do just that. However, my biggest problem with evolution is that it is based on the notion that order can rise from chaos all by itself. That's not even wrong.

That being said, this is all I am going to say on this matter for the time being. Discussions on evolution can go for years without being resolved. But the truth will come out sooner or later. And there shall be much weeping in the land.

Bill said...

Well, I agree "evolution" is a loaded term. But it definitely works the way I defined it. Using the algorithm called Genetic Programming, we were able to generate complex solutions to engineering problems that were human-competitive as judged by domain experts. This algorithm starts with a random number generator and utilizes zero knowledge or top-down intelligence. This approach worked so consistently, we wrote four books about it. This stuff exists. You can even download and run the code on your own computer if you don't believe it.

Louis Savain said...

Bill, if I were a betting man, I would bet top dollar that there are several hidden assumptions in your "genetic" algorithms that disqualify them as valid models of evolution. It usually has to do with the search space being artificially restricted or the fitness algorithm being smarter than it should be or successful genes being artificially protected from destructive mutations.

It is easy to deceive oneself if one does not have a critical mind of one's own science. And that is the problem with evolutionists: they absolutely refuse to criticize or allow others to criticize their fundamental assumptions. Their main target of criticism is Christianity. They fear Christianity like the plague. How is criticizing Christianity going to help science? This alone tells me evolution is a pile of BS, just like Einstein's spacetime physics.

It's not the first time that a bunch of supposedly smart scientists are shown to be totally wrong about a crucial field of science. We've seen this happen several times in the field of artificial intelligence and robotics, for example. For over half a century, AI researchers completely misunderstood what intelligence is about. Now, they have jumped on the Bayesian bandwagon and they are about to be proven wrong once again.

Bill said...

Well, of course the implementation of a genetic algorithm will be more constrained than evolution in nature. But it's not the constraints or assumptions that make it work.

The evolutionary process, whether it's natural or simulated in a computer, works simply because of selection bias compounded over time.

These two phenomena– survivorship bias and compounding– are counterintuitive, which I think is part of the problem with this debate.

Bill said...

Here is a great example of survivorship bias compounding over time in nature:

http://www.sciencenews.org/view/generic/id/349028/description/Shorter-winged_swallows_evolve_around_highways

Alexander B. said...

I cannot boast simply because I did not figure it out on my own. As I have said several times before, I consult an oracle.

I just fall under the table here. :D
Louis, you perfect!