Semantic Evidence Regulation via Relational Bias for Zero-Shot Object Navigation
Object navigation requires an embodied agent to locate a target object in an unknown environment through visual observations. Existing zero-shot methods typically leverage open-vocabulary perception and semantic priors to identify promising search regions. However, these methods often assume that semantic cues provide reliable guidance, while lacking mechanisms to assess and adjust their influence during exploration. Consequently, misleading semantic evidence can persist throughout navigation, biasing frontier selection and causing agents to repeatedly explore unreliable regions. To address this problem, we propose SER-Nav, a training-free framework that achieves dynamic Semantic Evidence Regulation via relational bias. SER-Nav introduces dual relational biases: activation reinforces target-related and contextual evidence to guide exploration, while inhibition attenuates misleading evidence caused by perceptual confusion and failed verification. These relational biases dynamically update the navigation search space, and a reliability-aware commitment gate prevents premature pursuit of insufficiently verified targets. By adaptively adjusting the influence of semantic cues, SER-Nav preserves useful guidance while mitigating persistent semantic misguidance under noisy open-vocabulary perception. Experiments on standard ObjectNav benchmarks demonstrate that SER-Nav consistently improves success rate and path efficiency over representative zero-shot methods. Extensive ablation studies further validate the effectiveness of each component. Real-world robot experiments further validate its robustness and practical applicability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Evaluating Compositional Generalisation in VLMs and Diffusion Models
A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years,…
Relational ReasoningZero-Shot LearningZero-shot Image Recognition Using Relational Matching, Adaptation and Calibration
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descri…
Domain AdaptationGeneral Classificationimage-classificationImage Classification+1Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
Autoregressive LLMs perform well on relational tasks that require linking entities via relational words (e.g., father/son, friend), but it is unclear whether they learn the logical semantics of such relations (e.g., symm…
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
Pretrained transformers readily adapt to new sequence modeling tasks via zero-shot prompting, but relational domains still lack architectures that transfer across datasets and tasks. The core challenge is the diversity o…
Binary ClassificationWireless Power Control Based on Large Language Models
This paper investigates the power control problem in wireless networks by repurposing pre-trained large language models (LLMs) as relational reasoning backbones. In hyper-connected interference environments, traditional …
Zero-shot GeneralizationRelational ReasoningGraph Neural Network