---
title: "MyoMechanix：基于生物力学与组合推理的技能动作理解与指导框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.26094v1"
permalink: "https://feed.astralor.com/items/itm_1354d2ba66f54f9c952a5f67"
published: "2026-08-26T17:56:33.000Z"
score: 73
channel: "ai"
tags: ["CUBIST","MyoMechanix","Physical AI","动作质量评估","多模态学习","表面肌电"]
---

# MyoMechanix：基于生物力学与组合推理的技能动作理解与指导框架

## AI 点评

> 这篇论文真正吸引人的地方在于把生理信号（sEMG）塞进了动作理解框架，还配了知识图谱和组合推理，一下子把AQA从“看视频打分”拉到了“懂肌肉发力”的层面。对做健身、康复、机器人操作的人来说，这套数据和CUBIST推理逻辑很值得研究，尤其是Video2EMG那一条，可能直接降低肌电设备门槛。不过论文还只是预印本，数据规模有限，后续如果开源码和数据集，我会第一时间跟进。

## 速览

MyoMechanix是一个面向负重动作的多模态数据集与基准，包含38名受试者、20种动作、7500余条样本，同步采集多视角RGB视频、3D姿态、表面肌电及生理信号，是迄今为止最大的多模态动作质量评估（AQA）基准。同时构建了健身知识图谱（FKG），将专家标注组织为动作、阶段、关键步骤、错误与纠正反馈的结构化关系。基于此开发了组合本体推理引擎CUBIST，通过分解-分析-重组实现细粒度错误归因与反馈生成。实验表明多模态感知与结构化表示可提升可解释性与错误归因能力，CUBIST达到SOTA水平，并探索视频到肌电信号预测任务，为Physical AI在健身、康复与医疗领域应用奠定基础。

## 关键点

- MyoMechanix数据集包含7500+样本、20个动作、38名受试者，同步多视角RGB、3D姿态、sEMG及生理信号，为最大规模多模态AQA基准。
- 构建健身知识图谱FKG，将专家知识结构化，支持组合式评分与可解释评估。
- 提出CUBIST组合本体推理引擎，实现细粒度错误归因与反馈生成，达到SOTA效果。
- 新增VideoQA与Video2EMG任务，探索语言理解与视频替代低成本EMG传感的可行性。

## 全文

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic patterns. These limitations hinder fine-grained, biomechanically grounded feedback. We introduce MyoMechanix, a multimodal ecosystem for weight-loaded actions that aligns motion with muscle activity. Expert-annotated, it contains 7,500+ samples of 20 actions from 38 subjects, with synchronized multiview RGB video, 3D pose, sEMG, and additional physiological signals, forming the largest multimodal AQA benchmark to date. We further construct the Fitness Knowledge Graph (FKG), which organizes expert annotations into structured relationships among actions, phases, key steps, errors, and corrective feedback, enabling compositional scoring and interpretable assessment. Building on these representations, we develop CUBIST (Compositional Ontological Reasoning Engine), which performs decomposition-analysis-recomposition for fine-grained error attribution and feedback generation. We also establish MyoMechanix-AQA, MyoMechanix-VideoQA, and a novel MyoMechanix-Video2EMG task. Experiments show that multimodal sensing and structured representations improve performance, interpretability, and error attribution, with CUBIST achieving state-of-the-art results; VideoQA enhances language-grounded action understanding; and Video2EMG suggests video-based alternatives to costly EMG sensing. MyoMechanix advances skilled activity understanding toward biomechanically grounded, multimodal, and compositional reasoning for Physical AI applications in fitness, rehabilitation, healthcare, and machine learning. Project page: https://haoyin116.github.io/MyoMechanix/

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1354d2ba66f54f9c952a5f67