arXiv cs.AI· Aalap D. Shah, Basil Saeed, Joshua B. Tenenbaum, Tobias Gerstenberg, Hyowon Gweon, Ilker Yildirim·· 2 小时前AI 评分44
GenEA：一个理解具身计划的计算框架
A computational framework for understanding embodied plans
AI 导读
研究者提出 GenEA，一种可推理多步骤长时程具身计划的智能体表征，核心是多层级状态空间，将机器人任务与运动规划框架与基于仿真的直觉物理结合，并对目标与计划给出联合概率分布。在物体操作与导航等多个领域的实验中，GenEA 重现了人类对具身计划的推理方式，并持续优于启发式方法、标准任务与运动规划及一个最先进的视觉语言模型。
正文 · 原文
Abstract:Reasoning about people's plans and goals based on their actions is fundamental to human social interaction and essential for cooperative, embodied artificial intelligence. Formalizing this capacity in naturalistic, embodied settings has been a longstanding challenge. Here, we present GenEA, a novel agent representation capable of reasoning over multi-step, long-horizon embodied plans. At the heart of GenEA lies a multilevel state-space that couples the coarse biomechanics of an articulated body and its interactions with nearby objects by extending the task-and-motion planning framework from robotics with simulation-based intuitive physics. By embedding this state-space in a generative model, GenEA yields a joint probability distribution over goals and embodied plans. Across several experiments spanning the qualitatively distinct domains of object manipulation and navigation, featuring diverse tasks and multiple behavioral measures, we show that GenEA, through simple transformations of this joint distribution, recapitulates how humans reason about embodied plans. Crucially, GenEA consistently outperforms strong alternative models, including plausible heuristics, standard task-and-motion planning, and a state-of-the-art vision-language model. GenEA thereby offers a new perspective on the architecture of human reasoning and social cognition, suggesting that embodied artificial intelligence systems seeking to seamlessly interact with humans should adopt GenEA-like generative models of action planning.
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Robotics (cs.RO) |
| Cite as: | arXiv:2611.13669 [cs.AI] |
| (or arXiv:2611.13669v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13669 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aalap D Shah [view email]
[v1]
Tue, 10 Nov 2026 07:15:38 UTC (47,846 KB)
来源：arXiv cs.AI · arxiv.org