迈向运动图灵测试：评估人形机器人的类人程度
Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots
提供以 SMPL-X 运动学参数为输入的「人类相似度」自动评分任务与基准，可用于评估动作生成/人体动作合成模型输出是否像人，并给出一个优于 LLM 类方法的简单回归基线可作对照。
原文依据 we propose the Motion Turing Test, a framework that evaluates whether human observers can discriminate between humanoid robot and human poses using only kinematic information
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人形机器人在运动生成与控制方面已取得显著进展，其动作看起来越来越自然、越来越像人。受图灵测试启发，我们提出运动图灵测试（Motion Turing Test），该框架评估人类观察者能否仅凭运动学信息区分人形机器人与人类的姿态。为便于开展这一评估，我们提出 Human-Humanoid Motion（HHMotion）数据集，包含 1,000 段运动序列，覆盖 15 个动作类别，由 11 个人形机器人模型和 10 名人类受试者完成。所有运动序列均转换为 SMPL-X 表示，以消除视觉外观的影响。我们招募了 30 名标注者，对每个姿态的类人程度按 0–5 分进行评分，累计获得超过 500 小时的标注。对采集数据的分析表明，人形机器人的动作与人类动作之间仍存在明显偏差，在跳跃、拳击和奔跑等动态动作中尤为突出。基于 HHMotion，我们构建了一个类人程度评估任务，旨在从运动数据中自动预测类人程度分数。尽管多模态大语言模型近期取得了进展，但我们发现它们仍不足以评估动作的类人程度。为此，我们提出了一个简单的基线模型，并证明其优于若干当前基于 LLM 的方法。数据集、代码与基准已在 http://www.lidarhumanmotion.net/mtt/ 公开。
英文原文摘要 1496 字符
Humanoid robots have achieved significant progress in motion generation and control, exhibiting movements that appear increasingly natural and human-like. Inspired by the Turing Test, we propose the Motion Turing Test, a framework that evaluates whether human observers can discriminate between humanoid robot and human poses using only kinematic information. To facilitate this evaluation, we present the Human-Humanoid Motion (HHMotion) dataset, which consists of 1,000 motion sequences spanning 15 action categories, performed by 11 humanoid models and 10 human subjects. All motion sequences are converted into SMPL-X representations to eliminate the influence of visual appearance. We recruited 30 annotators to rate the human-likeness of each pose on a 0-5 scale, resulting in over 500 hours of annotation. Analysis of the collected data reveals that humanoid motions still exhibit noticeable deviations from human movements, particularly in dynamic actions such as jumping, boxing, and running. Building on HHMotion, we formulate a human-likeness evaluation task that aims to automatically predict human-likeness scores from motion data. Despite recent progress in multimodal large language models, we find that they remain inadequate for assessing motion human-likeness. To address this, we propose a simple baseline model and demonstrate that it outperforms several contemporary LLM-based methods. The dataset, code, and benchmark release publicly at http://www.lidarhumanmotion.net/mtt/