E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
作者: Wen Ye, Peiyan Li, Tingyu Yuan, Yuan Xu, Xiangnan Wu, Chaoyang Zhao, Jing Liu, Nianfeng Liu, Yan Huang, Liang Wang
分类: cs.RO, cs.AI
发布日期: 2026-06-25
备注: Accepted to ECCV 2026. 44 pages, 11 figures. Project page: https://27yw.github.io/E-TTS-Web/
💡 一句话要点
提出E-TTS框架以解决机器人操作中的测试时间缩放问题
🎯 匹配领域: 支柱一:机器人控制 (Robot Control) 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 具身任务 测试时间缩放 机器人操作 历史信息 推理机制 模块化设计 闭环优化
📋 核心要点
- 现有方法在推理机制的研究上不足,且对历史信息的利用不够,影响了机器人操作的性能。
- E-TTS框架通过历史感知的迭代优化,结合推理与动作缩放,提升了机器人操作的适应性和效率。
- 在多个基准测试中,E-TTS在不需要额外专家数据或重训练的情况下,显著提升了性能。
📝 摘要(中文)
近年来,针对具身任务的测试时间缩放进行了初步研究,但仍面临两个主要挑战:一是推理机制对策略性能的提升尚未深入研究;二是具身任务的历史信息利用不足,导致仅依赖当前观察进行动作缩放的效果不佳。为此,本文提出了E-TTS,一个模块化的具身测试时间缩放框架,通过历史感知的迭代优化与视觉-语言验证器,统一了推理与动作缩放。E-TTS采用历史缓冲区存储历史上下文,并在采样过程中引入反馈生成,形成闭环迭代机制,显著提升推理效率和环境适应性。实验结果表明,E-TTS在多个基准测试中表现优异,模拟环境下性能提升达33.14%,真实场景下提升26.62%。
🔬 方法详解
问题定义:本文旨在解决具身任务中测试时间缩放的不足,尤其是推理机制与历史信息利用的缺失,导致性能提升受限。
核心思路:E-TTS框架通过模块化设计,结合历史信息与推理机制,采用迭代优化的方法来提升动作缩放的效果。这样的设计使得框架能够灵活适应不同任务需求。
技术框架:E-TTS的整体架构包括历史缓冲区、推理验证器和动作验证器。框架通过历史信息的存储与利用,进行推理与动作的联合采样与评分,形成闭环的迭代优化过程。
关键创新:E-TTS的主要创新在于引入了反馈生成机制,使得采样过程形成闭环,显著提升了推理效率和环境适应性,这与传统的开放式测试时间缩放方法有本质区别。
关键设计:E-TTS的设计中,历史缓冲区用于存储上下文信息,推理与动作验证器通过评分机制评估候选动作,确保在不同环境中均能有效应用。
🖼️ 关键图片
📊 实验亮点
实验结果显示,E-TTS在四个不同基准、六个环境、三个具身模型及四个基础视觉-语言-动作模型上均表现出色,模拟环境下性能提升达33.14%,真实场景下提升26.62%,展现了其在实际应用中的显著优势。
🎯 应用场景
E-TTS框架在机器人操作、自动化生产线及智能家居等领域具有广泛的应用潜力。通过提升机器人在复杂环境中的适应能力,该框架能够有效支持长时间的任务执行,进而推动智能机器人技术的进步与普及。
📄 摘要(原文)
Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reasoning can effectively improve the performance of the policy, but its scaling mechanism has seldom been studied; (2) historical information is essential, as embodied tasks are inherently long-horizon and sequential, making sole reliance on current observations for action scaling inadequate due to the lack of historical context utilization. To address these challenges, we introduce E-TTS, a modular and plug-and-play Embodied Test-Time Scaling framework that unifies reasoning and action scaling for robotic manipulation via history-aware iterative refinement with vision-language verifiers. To support joint reasoning-action scaling, E-TTS performs reasoning-action joint sampling and scoring in a pairwise manner. To better utilize historical information, E-TTS uses a history buffer to store historical context, which is then used by reasoning and action verifiers to evaluate the sampled candidates. Unlike conventional open-loop TTS methods, E-TTS introduces feedback generation into the sampling process to form a closed-loop iterative refinement mechanism, enhancing both inference efficiency and environmental adaptability. Each component functions as an independent and composable module, allowing flexible and adaptive configuration depending on task requirements. To evaluate the advantages of our framework, we conduct experiments across 4 different benchmarks, 6 environments, 3 embodiments, and 4 base vision-language-action models. The experimental results demonstrate that, without requiring additional expert data collection or retraining, E-TTS consistently improves performance, achieving up to a 33.14% increase in simulation and 26.62% in real-world scenarios.