Bridging Learned Visual Perception and Symbolic Belief-Space Planning

arXiv:2609.16884 · cs.AI, cs.RO · Submitted 2026-09-15 · Read on arXiv

cs.AI, cs.RO

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: To appear in the Proceedings of the 3rd International Conference on Neuro-Symbolic Systems (NeuS), 2026

Code: https://github.com/CLAIR-LAB-TECHNION/ViPlanPO

License: http://creativecommons.org/licenses/by/4.0/

The gist: In partially observable settings, agents must act without full knowledge of the world state and rely on uncertain state-estimation pipelines.

Terminology

Abstract

In partially observable settings, agents must act without full knowledge of the world state and rely on uncertain state-estimation pipelines. Obtaining grounded and verifiable symbolic plans under such uncertainty remains a key challenge. Recent work has integrated Vision-Language Models (VLMs) to bridge perception and symbolic reasoning, following two main paradigms. The first, VLM-as-planner, maps images directly to action sequences, and the second, VLM-as-grounder, grounds observations into symbolic predicates used as the initial state by off-the-shelf planners. Both approaches ignore uncertainty in the planning process, compromising robustness. We introduce a third paradigm, VLM-as-probabilistic-grounder, a novel approach that captures the uncertainty of VLM predicate groundings as a probability distribution over symbolic states. This enables planning in belief space and producing robust plans under uncertainty. Experiments in simulated household robot settings show improved robustness and task success over deterministic grounding, underscoring how our approach leverages foundation models for reliable planning under uncertainty.

Sources

Related papers