让机器人在全景环境中先想象再搜索，提升视觉寻物效率。
Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
- 将探索拆分为想象器和执行器，单步预测未见区域语义布局。
- 生成超196万条训练样本，搜索成功率显著提升。
- 适合需要低标注成本的机器人视觉导航研究者。
人形视觉搜索（HVS）要求智能体主动探索沉浸式360°环境。以往方法将此视为依赖累积多轮思维链（CoT）的单一任务，带来沉重认知负担并需昂贵轨迹级标注。本文提出全景想象（Imagining in 360°）框架，将探索过程解耦为专用的想象器（Imaginator）与执行器（Actor）。想象器作为空间先验的概率预测器，不维持累积推理链，而是单步推断已观测与未观测区域的语义布局。通过在此语义空间中采样多个假设，为执行器提供有效空间信息分布，增强对主动搜索中不确定性的鲁棒性。该解耦架构大幅降低数据工程成本，无需完整轨迹的CoT标注，可生成超过196万条精心筛选的训练样本。大量实验证明，显式建模语义空间先验能显著提升复杂真实场景中的搜索效率与成功率。
原文摘要 · Abstract (English)
Humanoid Visual Search (HVS) requires agents to actively explore immersive 360$^\circ$ environments. While prior methods treat this as a monolithic task relying on cumulative, multi-turn Chain-of-Thought (CoT) reasoning, they impose heavy cognitive burdens and require expensive trajectory-level annotations. In this paper, we propose Imagining in 360$^\circ$, a novel framework that decouples the exploration process into a specialized Imaginator and an Actor. The Imaginator functions as a probabilistic predictor of spatial priors; instead of maintaining a cumulative reasoning chain, it infers the semantic layout of both observed and unobserved regions in a single step. By sampling multiple hypotheses within this semantic space, we provide the Actor with a distribution of effective spatial information, offering robust guidance that hedges against uncertainty during active search. This decoupled architecture significantly lowers data engineering costs by eliminating the need for full-trajectory CoT annotations, enabling the generation of over 1.96 million curated training samples. Extensive experiments demonstrate that explicitly modeling semantic spatial priors drastically improves search efficiency and success rates in complex, in-the-wild environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。