A Neuro-Symbolic Framework for Reasoning under Perceptual Uncertainty: Bridging Continuous Perception and Discrete Symbolic Planning

TL;DR

This paper introduces a neuro-symbolic framework that integrates perception and symbolic planning under uncertainty, demonstrating high success rates in robotic manipulation tasks and providing theoretical guarantees for uncertainty propagation.

Contribution

It presents a novel neuro-symbolic approach coupling perceptual models with probabilistic planning, explicitly modeling and propagating uncertainty from perception to decision-making.

Findings

Achieved 90.7% average success rate on manipulation benchmarks.

Processed over 10,000 scenes with probabilistic predicates and calibrated confidences.

Provided theoretical and empirical validation of uncertainty's role in planning convergence.

Abstract

Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty from perception to planning, providing a principled connection between these two abstraction levels. Our approach couples a transformer-based perceptual front-end with graph neural network (GNN) relational reasoning to extract probabilistic symbolic states from visual observations, and an uncertainty-aware symbolic planner that actively gathers information when confidence is low. We demonstrate the framework's effectiveness on tabletop robotic manipulation as a concrete application: the translator processes 10,047 PyBullet-generated scenes (3--10 objects) and outputs probabilistic predicates with calibrated confidences (overall F1=0.68). When embedded in the planner, the system achieves 94\%/90\%/88\% success on Simple Stack, Deep Stack, and Clear+Stack benchmarks (90.7\% average), exceeding the strongest POMDP baseline by 10--14 points while planning within 15\,ms. A probabilistic graphical-model analysis establishes a quantitative link between calibrated uncertainty and planning convergence, providing theoretical guarantees that are validated empirically. The framework is general-purpose and can be applied to any domain requiring uncertainty-aware reasoning from perceptual input to symbolic planning.