I believe the meaning in this context is just a model saying what objects are nearby, where they are, how large they are, and what their velocity vectors are, and maybe guesses as to what kind of object (car, truck, pedestrian, lamppost, etc.) they are.

Mnyeah, I see what you mean, but I wouldn't call that a world model. Nouveau AI is great for classification, so it can certainly recognise what the individual objects around it are.

However, a "world model" should include the relations between identified objects, in some representation that can then be used for inference.

For example, a classifier can label an object in the path of a vehicle as, e.g. "tree", but a world-model would have to go further than that and provide some context about trees, why they don't normally grow in the middle of roads and why they should be steered around or otherwise avoided.

This kind of world model, that places entities in the world into a complex relational context, is, indeed, beyond our current capabilities (at least for the real world, as opposed to controlled artificial worlds).

I really don't think that's controversial. However, I got a few downvotes on my previous comment so I must have misunderstood the comment I was replying to.

I don't think your original comment was at all problematic.

There's a naturally impulse for a human being to look at a problem and say "of course you need a world for this and it will have X, Y and Z data and it will be give you all you need." That is until they figure out how it is to keeping X, Y and Z updated is.

The thing is that a bunch of data with something like objects and velocities isn't a world model. "How Large" a given thing is, is only one of a multitude of questions.

I think we humans are so good at just passively keeping track of everything in our environment we forget how difficult it is "keep a world model" from what one sees.

> The thing is that a bunch of data with something like objects and velocities isn't a world model.

Sure it is. Whether it's an adequate model for some particular purpose is another question. But no model includes everything.

Objects and velocities would be a good start. I don't know enough about the present state of the technology to know whether we even have that. But from some of these accidents we're seeing, it seems like we don't.

I would agree that a better model would attempt to infer intentions: what is that driver/cyclist/pedestrian likely to do next, based on what they're doing now?

Well, object labels and velocities is not a world model. You can say that they are the attributes necessary to build one, but just a bunch of values is not a model.

Current tech builds a (statistical) model of some aspects of the world that an agent must navigate- aspects that pertain to entity types, trajectories, velocities and so on.

But other bits are missing and they are important ones- for example, what is a human doing on top of a bicycle moving at the same speed as him or her? What is the relation between a driver and a car? And so on. We can still not represent stuff like that with any accuracy to speak of.

In short, what's missing for the most part is a representation of the relations between entities in the world- even where we can accurately represent the entities themselves, or their characteristics.