Bilevel Planning with Learned Symbolic Abstractions from Interaction Data

TL;DR

This paper introduces a bilevel neuro-symbolic planning framework that combines learned probabilistic symbolic rules with continuous effect models to improve planning efficiency and reliability in complex manipulation tasks.

Contribution

It presents a novel bilevel approach integrating probabilistic symbolic reasoning with continuous verification, addressing limitations of previous deterministic symbolic methods.

Findings

Outperforms symbolic-only planning approaches.

Reliably detects failing plans through verification.

Achieves planning performance comparable to continuous methods.

Abstract

Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural effect predictors trained with a robot's unsupervised exploration. However, these methods rely on deterministic symbolic domains, lack mechanisms to verify the generated symbolic plans, and operate only at the abstract level, often failing to capture the continuous dynamics of the environment. To overcome these limitations, we propose a bilevel neuro-symbolic framework in which learned probabilistic symbolic rules generate candidate plans rapidly at the high level, and learned continuous effect models verify these plans and perform forward search when necessary at the low level. Our experiments on multi-object manipulation tasks demonstrate that the proposed bilevel method outperforms symbolic-only approaches, reliably identifying failing plans through verification, and achieves planning performance statistically comparable to continuous forward search while resolving most problems via efficient symbolic reasoning.