跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.14781 · v1

Robust Task-Aware State Estimation from Pre-trained Perception

首次提交 2026-11-11 06:12
版本更新 2026-11-11 06:12
雷达观测 2026-11-13 10:09
arXiv ↗PDF ↗

摘要

Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into a single best-guess state and make decisions as if it were ground truth. This is brittle because when the guess is wrong, the agent's decisions may be unsafe or infeasible. At the other extreme, maintaining a full probability distribution over symbolic states is often intractable. We propose a middle path, drawing on the underlying probabilities the perception model already produces (e.g., a VLM's output-layer token distributions) to construct a θθ-confidence Minimal Belief Set (MBSθ_θ), a minimal subset of states whose cumulative probability meets a user-specified belief-mass threshold. The minimality of an MBSθ_θ ensures that the agent considers only the most likely states, enhancing robustness in downstream decision-making while maintaining computational tractability. Using a novel three-layered belief system, we efficiently approximate individual state probabilities from per-feature predictions and task-level constraints. On this belief construction, we base our MBSθ_θ construction, while maintaining only a lean factored representation of the belief. Our algorithm, Probability-Ranked Valid State Search (PRaVaSS), takes advantage of the unique structure of this belief system to construct an MBSθ_θ with correctness guarantees and polynomial complexity in the unconstrained case. Using a VLM as the backbone of our state estimator, we validate our method's theoretical properties, scalability with problem size, and improvement of downstream decision-making when used in a task-planning pipeline.

作者备注:The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-11 06:12 · 最新观测版本

Robust Task-Aware State Estimation from Pre-trained Perception

Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into a single best-guess state and make decisions as if it were ground truth. This is brittle because when the guess is wrong, the agent's decisions may be unsafe or infeasible. At the other extreme, maintaining a full probability distribution over symbolic states is often intractable. We propose a middle path, drawing on the underlying probabilities the perception model already produces (e.g., a VLM's output-layer token distributions) to construct a θθ-confidence Minimal Belief Set (MBSθ_θ), a minimal subset of states whose cumulative probability meets a user-specified belief-mass threshold. The minimality of an MBSθ_θ ensures that the agent considers only the most likely states, enhancing robustness in downstream decision-making while maintaining computational tractability. Using a novel three-layered belief system, we efficiently approximate individual state probabilities from per-feature predictions and task-level constraints. On this belief construction, we base our MBSθ_θ construction, while maintaining only a lean factored representation of the belief. Our algorithm, Probability-Ranked Valid State Search (PRaVaSS), takes advantage of the unique structure of this belief system to construct an MBSθ_θ with correctness guarantees and polynomial complexity in the unconstrained case. Using a VLM as the backbone of our state estimator, we validate our method's theoretical properties, scalability with problem size, and improvement of downstream decision-making when used in a task-planning pipeline.

查看此版本解读 →查看此版本原文 ↗