Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a framework for abstract world models that jointly learns (i) symbolic state representations and (ii) causal processes for both endogenous actions and exogenous mechanisms. Each causal process models the time course of a stochastic cause-effect relation. We learn these world models from limited data via variational Bayesian inference combined with LLM proposals. Across five simulated tabletop robotics environments, the learned models enable fast planning that generalizes to held-out tasks with more objects and more complex goals, outperforming a range of baselines.

Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on both in- and out-of-distribution tasks across five simulated robotic domains. Results show that our approach offers better sample complexity, stronger out-of-distribution generalization, and improved interpretability.

An ancient ship containing hundreds of stunningly-preserved wine jugs has been found on the floor of the Mediterranean. The 40-foot vessel, found 1 mile deep on the seafloor 56 miles from Israel's coast, dates back 3,300 years to the late Bronze Age, experts say. It's thought to be the oldest ship found this deep in the Med, as previous shipwrecks from this era never ventured this far away from land. This suggests ancient seafarers were more capable at navigating the deep seas than historians previously thought. The ship likely sunk either from a storm or after coming under attack by pirates, the discoverers believe.

It's easy for us to forget that the vast majority of the world doesn't really care about (or even know about) robots. With that in mind, it's understandable why most roboticists consider robots operating "in the wild" to be "anywhere that isn't the controlled environment of my lab." But there are "real world" environments, and then there's the actual wild, and we almost never hear about research happening there. This is too bad, because we don't have nearly enough appreciation for how robots can potentially be used to mitigate problems throughout the developing world. There's also very little research into how different cultures react to robots with a social component--most human-robot interaction (HRI) studies rely on local participants who are easy (and cheap) to recruit, and are consequently full of students, which is a terrible representation of most of the rest of the world.

An African tale says that in Taubiland there lived in ancient, ancient times a man who possessed all the wisdom of the world. He hid all the wisdom in a jug. One day when he climbed a tree to hide the jug, his son gave him some advice about climbing ( a lesson of wisdom, which was supposed to be in the jug). His disappointment was so great that, with all of his might, he threw the jug of wisdom as far as he could. The jug hit a rock and broke into a million pieces.