Mind2Act World:一个用于机器人操作中具身智能、物理动作和心智-动作组合的诊断基准
Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation
Mind2Act World基准包含180个模拟操作配置,评估具身系统结合历史推理、精确执行和环境反馈的能力,揭示单视图能力不适用于组合任务。该基准包含30个任务,分为心智(基于历史观察做决策)、行动(精确执行)和心智-行动组合(闭环任务)三视图,用于诊断系统是缺乏某项能力还是无法组合已有能力。
Published on Nov 19
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
A diagnostic benchmark of 180 simulated manipulation configurations evaluates whether embodied systems can combine history-based reasoning, precise execution, and closed-loop environmental feedback, revealing that single-view competence does not transfer to composed tasks.
Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.
View arXiv page View PDF Project page GitHub 21 Add to collection
Get this paper in your agent:
hf papers read 2611.26444
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.26444 in a model README.md to link it from this page.
Datasets citing this paper 1
Mind2Act-World/mind2act-train
Updated about 2 hours ago • 5.91k • 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.26444 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源: Hugging Face Daily Papers · huggingface.co