Generative AI-Driven High-Fidelity Human Motion Simulation
Not on the map. Why?
Abstract (arXiv)
Human motion simulation (HMS) supports cost-effective evaluation of worker behavior, safety, and productivity in industrial tasks. However, existing methods often suffer from low motion fidelity. This study introduces Generative-AI-Enabled HMS (G-AI-HMS), which integrates text-to-text and text-to-motion models to enhance simulation quality for physical tasks. G-AI-HMS tackles two key challenges: (1) translating task descriptions into motion-aware language using Large Language Models aligned with MotionGPT's training vocabulary, and (2) validating AI-enhanced motions against real human movements using computer vision. Posture estimation algorithms are applied to real-time videos to extract joint landmarks, and motion similarity metrics are used to compare them with AI-enhanced sequences. In a case study involving eight tasks, the AI-enhanced motions showed lower error than human created descriptions in most scenarios, performing better in six tasks based on spatial accuracy, four tasks based on alignment after pose normalization, and seven tasks based on overall temporal similarity. Statistical analysis showed that AI-enhanced prompts significantly (p < 0.0001) reduced joint error and temporal misalignment while retaining comparable posture accuracy.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 67 references that are in the map. First posted on arXiv 18 Jul 2025.
Builds on
30 of 67 references.
References · 30
- 2017Attention Is All You Needcited by 60,361
- 2023GPT-4 Technical Reportcited by 18,396
- 2017Neural Discrete Representation Learningcited by 4,712
- 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
- 2022Diffusion Models in Vision: A Surveycited by 1,015
- 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
- 2023Instruction Tuning with GPT-4cited by 686
- 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
- 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
- 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
- 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
- 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
18 more
- 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
- 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 287
- 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
- 2019Human Motion Trajectory Prediction: A Surveycited by 232
- 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
- 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
- 2021Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoderscited by 109
- 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
- 2021An Introduction to Deep Generative Modelingcited by 104
- 2023Human Motion Generation: A Surveycited by 96
- 2023Online Clustered Codebookcited by 55
- 2020Structure-Aware Human-Action Generationcited by 28
- 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
- 2022When, Why, and Which Pretrained GANs Are Useful?cited by 14
- 2023ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Taskcited by 13
- 2021End-to-end translation of human neural activity to speech with a dual-dual generative adversarial networkcited by 6
- 2023Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generationcited by 5
- 2024Computer-Vision-Enabled Worker Video Analysis for Motion Amount Quantificationcited by 1
Built on by
Not cited yet.