Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation

Badi Li, Ren-Jie Lu, Yu Zhou, Jingke Meng, Wei-Shi Zheng

Keywords: Visual Navigation; Object Goal Navigation

TL;DR: We distill commonsense spatial priors from large language models into a flow-based generative model to help agents imagine unseen parts of indoor scenes for Object Goal Navigation task.

Abstract: The Object Goal Navigation (ObjectNav) task challenges agents to locate a specified object in an unseen environment by imagining unobserved regions of the scene. Prior approaches rely on deterministic and discriminative models to complete semantic maps, overlooking the inherent uncertainty in indoor layouts and limiting their ability to generalize to unseen environments. In this work, we propose GOAL, a generative flow-based framework that models the semantic distribution of indoor environments by bridging observed regions with LLM-enriched full-scene semantic maps. During training, spatial priors inferred from large language models (LLMs) are encoded as two-dimensional Gaussian fields and injected into target maps, distilling rich contextual knowledge into the flow model and enabling more generalizable completions. Extensive experiments demonstrate that GOAL achieves state-of-the-art performance on MP3D and Gibson, and shows strong generalization in transfer settings to HM3D.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 6688