# Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning

arXiv: https://arxiv.org/abs/2602.22791 · HTML: https://mlsanity.com/paper/2602.22791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2003.08111/) (2020)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2104.01528/) (2021)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition](https://mlsanity.com/paper/1911.12409/) (2019)
- [Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition](https://mlsanity.com/paper/2112.03590/) (2021)
- [Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World](https://mlsanity.com/paper/1803.08319/) (2018)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition](https://mlsanity.com/paper/2008.00188/) (2020)
- [Future Person Localization in First-Person Videos](https://mlsanity.com/paper/1711.11217/) (2017)
- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [Social-Transmotion: Promptable Human Trajectory Prediction](https://mlsanity.com/paper/2312.16168/) (2023)
- [TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2112.03587/) (2021)
- [SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2209.02399/) (2022)
- [Robots That Can See: Leveraging Human Pose for Trajectory Prediction](https://mlsanity.com/paper/2309.17209/) (2023)
- [Multi-Transmotion: Pre-trained Model for Human Motion Prediction](https://mlsanity.com/paper/2411.02673/) (2024)
- [AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention](https://mlsanity.com/paper/2101.05682/) (2021)
- [Social-Pose: Enhancing Trajectory Prediction with Human Body Pose](https://mlsanity.com/paper/2507.22742/) (2025)
- [STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences](https://mlsanity.com/paper/2407.10935/) (2024)

## Abstract (arXiv)

Human trajectory prediction plays a crucial role in applications such as autonomous navigation and video surveillance. While recent works have explored the integration of human skeleton sequences to complement trajectory information, skeleton data in real-world environments often suffer from missing joints caused by occlusions. These disturbances significantly degrade prediction accuracy, indicating the need for more robust skeleton representations. We propose a robust trajectory prediction method that incorporates a self-supervised skeleton representation model pretrained with masked autoencoding. Experimental results in occlusion-prone scenarios show that our method improves robustness to missing skeletal data without sacrificing prediction accuracy, and consistently outperforms baseline models in clean-to-moderate missingness regimes.