Estimating Semantic Ambiguity via Gaussian Context Distributions for VLM-Driven Traversability Analysis

• URL: http://arxiv.org/abs/2609.08583v1
• Date: Tue, 08 Sep 2026 11:18:32 GMT
• Title: Estimating Semantic Ambiguity via Gaussian Context Distributions for VLM-Driven Traversability Analysis
• Abstract summary: We present a novel pipeline for vision-based traversability estimation that explicitly models contextual uncertainty.<n>Our approach utilizes Conceptual Anchoring to ground open-vocabulary VLM predictions onto a continuous physical traversability scale.<n>We derive both a dense traversability map and a dense uncertainty map based on the statistical properties of the distribution.
• Score: 14.31446990918297
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Autonomous navigation in unstructured environments requires robust scene understanding, yet Vision-Language Models (VLMs) often suffer from semantic ambiguity, where conflicting predictions can lead to dangerous failures. To address this, we present a novel pipeline for vision-based traversability estimation that explicitly models contextual uncertainty. Our approach utilizes Conceptual Anchoring to ground open-vocabulary VLM predictions onto a continuous physical traversability scale. By formulating the model's responses as a Gaussian Context Distribution (GCD), we derive both a dense traversability map and a dense uncertainty map based on the statistical properties of the distribution. Experimental validation on the real-world GOOSE dataset demonstrates that our proposed uncertainty metric effectively correlates with sources of ambiguity, such as visual artifacts and mixed terrain overlap. The method exhibits competitive performance while offering the distinct advantage of providing statistical uncertainty estimates to address semantic ambiguity, enabling safer and more reliable autonomous behavior in complex outdoor settings.

Related papers

• From General Vision to Reliable Traversability Estimation: Adapting Vision Foundation Models for Unstructured Outdoor Environments [12.275095764403432]
  We propose Vision-to-Traversability Adaptation (ViTA), a framework that adapts vision-based approaches for reliable traversability estimation.<n>ViTA injects task-specific knowledge through learnable traversability prompts while preserving the VFM's cross-domain generalization.<n>We show that ViTA achieves state-of-the-art IoU and Precision with substantial false-positive reduction and strong cross-domain generalization.
  arXiv  Detail & Related papers  (2026-05-28T08:16:20Z)
• Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere [2.803487857262511]
  We propose AsymVLM to build probabilistic embeddings from pre-trained vision-language models on the unit hypersphere, enabling uncertainty quantification.<n>We validate the effectiveness of the probabilistic embeddings on established benchmarks, and present comprehensive ablation studies demonstrating the inherent nature of asymmetry in the uncertainty structure of textual and visual data.
  arXiv  Detail & Related papers  (2025-05-16T09:24:29Z)
• Post-hoc Probabilistic Vision-Language Models [54.05237186168399]
  Vision-language models (VLMs) have found remarkable success in classification, retrieval, and generative tasks.<n>We propose post-hoc uncertainty estimation in VLMs that does not require additional training.<n>Our results show promise for safety-critical applications of large-scale models.
  arXiv  Detail & Related papers  (2024-12-08T18:16:13Z)
• Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere [3.572499139455308]
  This paper introduces a new perspective on incorporating uncertainty into contrastive learning by embedding representations within a spherical space. We leverage the concentration parameter, kappa, as a direct, interpretable measure to quantify uncertainty explicitly.
  arXiv  Detail & Related papers  (2024-05-26T07:08:13Z)
• Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidence [4.83420384410068]
  We propose an evidential semantic mapping framework, which integrates the evidential reasoning of Dempster-Shafer Theory of Evidence (DST) into the entire mapping pipeline. We show that our framework enhances the reliability of uncertainty maps, consistently outperforming existing methods in scenes with high perceptual uncertainties.
  arXiv  Detail & Related papers  (2024-05-10T06:32:01Z)
• Evidential Semantic Mapping in Off-road Environments with Uncertainty-aware Bayesian Kernel Inference [5.120567378386614]
  We propose an evidential semantic mapping framework, which can enhance reliability in perceptually challenging off-road environments. By adaptively handling semantic uncertainties, the proposed framework constructs robust representations of the surroundings even in previously unseen environments.
  arXiv  Detail & Related papers  (2024-03-21T05:13:34Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition [59.52434325897716]
  We propose a solution, named DMUE, to address the problem of annotation ambiguity from two perspectives. For the former, an auxiliary multi-branch learning framework is introduced to better mine and describe the latent distribution in the label space. For the latter, the pairwise relationship of semantic feature between instances are fully exploited to estimate the ambiguity extent in the instance space.
  arXiv  Detail & Related papers  (2021-04-01T03:21:57Z)
• Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
  We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-01-05T18:54:11Z)
• Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
  Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
  arXiv  Detail & Related papers  (2020-12-23T16:21:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.