论文/arXiv 2610.15274·17 天前

人形机器人重定向中用于人类反应选择的具身感知推理时搜索

针对人形交互数据与专用反应模型训练成本高的问题，提出具身感知推理时搜索，并在不同人形具身形态的反应重定向中验证。

AI 整理

• 本体 SDK 与控制
• 数据与采集
• 端侧部署

原文链接：Embodiment-Aware Inference-Time Search for Human Reaction Selection in Humanoid Retargeting（arXiv 2610.15274 · 发布日期：2026-10-11）

Embodiment-Aware Inference-Time Search for Human Reaction Selection in Humanoid Retargeting

针对人形交互数据与专用反应模型训练成本高的问题，提出具身感知推理时搜索，并在不同人形具身形态的反应重定向中验证。

核心要点

• 动机是人类动作空间中偏好的反应，未必适合特定人形机器人执行。
• 方法从冻结的生成式反应模型随机采样候选，并重定向到目标人形机器人。
• 框架联合评估交互质量与具身可行性，在目标物理约束下选择反应。
• 实验显示保持总体人类反应质量，并将重定向可行性提升1.61%；代码将发布。

验证范围与局限：验证范围为不同人形具身形态上的反应重定向，摘要未说明真机验证或具体任务。

英文摘要 (Abstract)

Training humanoid robots to learn human behaviors requires expensive data collection, and human-robot interaction data can be even more difficult and costly to collect. Training a specialized reaction model for each humanoid embodiment can also be time-consuming and resource-intensive. Human-to-humanoid motion retargeting provides a more scalable alternative, allowing human-human reaction data to serve as a common motion representation for different humanoid embodiments. However, due to morphological and kinematic differences between humans and humanoid robots, a reaction preferred in human motion space may not be the most suitable one for execution on a particular robot embodiment. In this work, we propose an inference-time reaction search framework that leverages stochastic sampling from a generative reaction model and jointly considers reaction quality and humanoid embodiment feasibility. Given the observed interaction, our framework generates multiple plausible reaction candidates. Each candidate is retargeted to the target humanoid and evaluated using complementary interaction and embodiment-specific feasibility criteria, allowing candidate selection under the physical constraints of the target embodiment. Since the reaction generator remains frozen, the framework can adapt to different humanoid embodiments at inference time without retraining. Experimental results demonstrate that the proposed framework maintains overall human reaction quality while improving the feasibility of retargeted humanoid reactions across different embodiments. The proposed pipeline improves humanoid retargeting feasibility by 1.61%. Moreover, human-space and G1 best-candidate selections disagree in 78.98% of samples, demonstrating substantial embodiment dependence. Code will be released.

作者：Yongpeng Cao, Masahiro Hirano, Yuji Yamakawa

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.15274：Embodiment-Aware Inference-Time Search for Human Reaction Selection in Humanoid Retargeting访问 2026-10-21