Tuesday, July 29, 2014

On internal models, consequence engines and Popperian creatures

So. We've been busy in the lab the last few months. Really exciting. Let me explain.

For a couple of years I've been thinking about robots with internal models. Not internal models in the classical control-theory sense, but simulation based models; robots with a simulation of themselves and their environment inside themselves, where that environment could contain other robots or, more generally, dynamic actors. The robot would have, inside itself, a simulation of itself and the other things, including robots, in its environment. It takes a bit of getting your head round. But I'm convinced that this kind of internal model opens up all kinds of possibilities. Robots that can be safe, for instance, in unknown or unpredictable environments. Robots that can be ethical. Robot that are self-aware. And robots with artificial theory of mind.

I'd written and talked about these ideas but, until now, not had a chance to test them with real robots. But, between January and June the swarm robotics group was joined by Christian Blum, a PhD student from the cognitive robotics research group of the Humboldt University of Berlin. I suggested Christian work on an implementation on our e-puck robots and happily he was up for the challenge. And he succeeded. Christian, supported by my post-doc Research Fellow Wenguo, implemented what we call a Consequence Engine, running in real-time, on the e-puck robot.

Here is a block diagram. The idea is that for each possible next action of the robot, it simulates what would happen if the robot were to execute that action for real. This is the loop shown on the left. Then, the consequences of each of those next possible actions are evaluated. Those actions that have 'bad' consequences, for either the robot or other actors in its environment, are then inhibited.

This short summary hides alot of detail. But let me elaborate on two aspects. First, what do I mean by 'bad'? Well it depends on what capability we are trying to give the robot. If we're making a safer robot, 'bad' means 'unsafe'; if we're trying to build an ethical robot, 'bad' would mean something different - think of Asimov's laws of robotics. Or bad might simply mean 'not allowed' if we're building a robot whose behaviours are constrained by standards, like ISO 13482:2014.

Second, notice that the consequence engine is not controlling the robot. Instead it runs in parallel. Acting as a 'governor', it links with the robot controller's action selection mechanism, inhibiting those actions evaluated as somehow bad. Importantly the consequence engine doesn't tell the robot what to do, it tells it what not to do.

Running the open source 2D robot simulator Stage as its internal simulator our consequence engine runs at 2Hz, so every half a second it is able to simulate about 30 next possible actions and their consequences. The simulation budget allows us to simulate ahead around 70cm of motion for each of those next possible actions. In fact Stage is actually running on a laptop, linked to the robot over the fast WiFi LAN. But logically it is inside the robot. What's important here is the proof of principle.

Dan Dennett, in his remarkable book Darwin's Dangerous Idea, describes the Tower of Generate-and-Test; a conceptual model for the evolution of intelligence that has become known as Dennett's Tower.

In a nutshell Dennett's tower is set of conceptual creatures each one of which is successively more capable of reacting to (and hence surviving in) the world through having more sophisticated strategies for 'generating and testing' hypotheses about how to behave. Read chapter 13 of Darwin's Dangerous Idea for the full account, but there are some good précis to be found on the web; here's one. The first three storeys of Dennett's tower, starting on the ground floor, have:
  • Darwinian creatures have only natural selection as the generate and test mechanism, so mutation and selection is the only way that Darwinian creatures can adapt - individuals cannot.
  • Skinnerian creatures can learn but only by literally generating and testing all different possible actions then reinforcing the successful behaviour (which is ok providing you don't get eaten while testing a bad course of action).
  • Popperian creatures have the additional ability to internalise the possible actions so that some (the bad ones) are discarded before they are tried out for real.
Like the Tower of Hanoi each successive storey is smaller (a sub-set) of the storey below, thus all Skinnerian creatures are Darwinian, but only a sub-set of Darwinian creatures are Skinnerian and so on.

Our e-puck robot, with its consequence engine capable of generating and testing next possible actions, is an artificial Popperian Creature: a working model for studying this important kind of intelligence.

In my next blog post, I'll outline some of our experimental results.

I am hugely grateful to Christian Blum who brilliantly implemented the architecture outlined here, and conducted experimental work. Christian was supported by Dr Wenguo Liu, with his deep knowledge of the e-puck, and our experimental infrastructure.

Related blog posts:


  1. I've probably totally missed the point, but isn't this what chess computers do? Or how about robot dodgems....

  2. "An overt internal model is used for the basis of explicit, but internal, exploration of alternatives, a process called lookahead.
    Popperian creatures can have both tacit and overt internal models. Humans, for example, are Popperian creatures that with responses like vertigo, fleeing in terror and sexual attraction demonstrate the use of tacit models, whereas chess playing, for instance, demonstrates the use of overt models." http://view.officeapps.live.com/op/view.aspx?src=http://www.cs.bham.ac.uk/research/projects/cogaff/Complin.thesis.do

    1. Thanks for your comments Paul. I'm certainly not claiming this to be the only, or the first, artificial Popperian Creature. In fact I reference 4 examples in my Ethical Robots: some technical and ethical challenges slides.

    2. I was just trying to make sure I understood. I'm not sure I'd regard a chess computer as having a theory of mind if it's playing the board rather than playing the player.

      However, it could get more complicated if the consequence engine suppressed phrases that were inappropriate for it to use in the presence of a particular person.

      Let's say the machine builds a history of each time it interacts with a person, or even acquires information about that person.

      The idea is simply to use this to help it respond appropriately.

      But at what point do you cut off continuing improvements in the sensitivity of the machine's responses, its ability to comprehend, communicate and be socially aware so that it doesn't end up - as a by-product of this sophistication, almost - also modelling its own life history and feelings? (I'm thinking of your recent post Your robot doggie could really be pleased to see you. Also an older post on the narrative self, which I expected might be there from a recent tweet of yours and have now spotted amongst the Popular Posts!)

      I realise this is all highly speculative, but one thing that interests me is where you decide the cut-off is going to be that separates machines from humans, as the possibilities gradually increase, and how you might achieve that cut-off.