# Human Motion Prediction under Unexpected Perturbation

arXiv: https://arxiv.org/abs/2403.15891 · HTML: https://mlsanity.com/paper/2403.15891/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 78 references that are in the map.
- First posted on arXiv 23 Mar 2024.

## Builds on (most cited first, 30 of 34)

- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Back to MLP: A Simple Baseline for Human Motion Prediction](https://mlsanity.com/paper/2207.01567/) (2022)
- [Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow](https://mlsanity.com/paper/1802.10123/) (2018)
- [EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning](https://mlsanity.com/paper/2303.10876/) (2023)
- [Physics-based Human Motion Estimation and Synthesis from Videos](https://mlsanity.com/paper/2109.09913/) (2021)
- [Human Trajectory Prediction via Neural Social Physics](https://mlsanity.com/paper/2207.10435/) (2022)
- [Multi-Person 3D Motion Prediction with Multi-Range Transformers](https://mlsanity.com/paper/2111.12073/) (2021)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact](https://mlsanity.com/paper/2103.16021/) (2021)
- [Differentiable Physics Simulation of Dynamics-Augmented Neural Objects](https://mlsanity.com/paper/2210.09420/) (2022)
- [Differentiable Dynamics for Articulated 3d Human Motion Reconstruction](https://mlsanity.com/paper/2205.12256/) (2022)
- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling](https://mlsanity.com/paper/1908.07214/) (2019)
- [High-order Differentiable Autoencoder for Nonlinear Model Reduction](https://mlsanity.com/paper/2102.11026/) (2021)
- [Real-time Controllable Motion Transition for Characters](https://mlsanity.com/paper/2205.02540/) (2022)
- [Stochastic Multi-Person 3D Motion Forecasting](https://mlsanity.com/paper/2306.05421/) (2023)
- [Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting](https://mlsanity.com/paper/2303.05095/) (2023)
- [RSMT: Real-time Stylized Motion Transition for Characters](https://mlsanity.com/paper/2306.11970/) (2023)
- [Joint-Relation Transformer for Multi-Person Motion Prediction](https://mlsanity.com/paper/2308.04808/) (2023)
- [Dynamic Future Net: Diversified Human Motion Generation](https://mlsanity.com/paper/2009.05109/) (2020)

## Built on by (most cited first, 5 of 5)

- [Large-Scale Multi-Character Interaction Synthesis](https://mlsanity.com/paper/2505.14087/) (2025)
- [Human Motion Prediction, Reconstruction, and Generation](https://mlsanity.com/paper/2502.15956/) (2025)
- [Ego-Human Motion Prediction with 3D-Aware LLM](https://mlsanity.com/paper/2607.07001/) (2026)
- [Wearable-informed generative digital avatars predict task-conditioned post-stroke locomotion](https://mlsanity.com/paper/2512.14329/) (2025)
- [Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsals](https://mlsanity.com/paper/2605.11463/) (2026)

## Abstract (arXiv)

We investigate a new task in human motion prediction, which is predicting motions under unexpected physical perturbation potentially involving multiple people. Compared with existing research, this task involves predicting less controlled, unpremeditated and pure reactive motions in response to external impact and how such motions can propagate through people. It brings new challenges such as data scarcity and predicting complex interactions. To this end, we propose a new method capitalizing differential physics and deep neural networks, leading to an explicit Latent Differential Physics (LDP) model. Through experiments, we demonstrate that LDP has high data efficiency, outstanding prediction accuracy, strong generalizability and good explainability. Since there is no similar research, a comprehensive comparison with 11 adapted baselines from several relevant domains is conducted, showing LDP outperforming existing research both quantitatively and qualitatively, improving prediction accuracy by as much as 70%, and demonstrating significantly stronger generalization.