# DE-TGN: Uncertainty-Aware Human Motion Forecasting using Deep Ensembles

arXiv: https://arxiv.org/abs/2307.03610 · HTML: https://mlsanity.com/paper/2307.03610/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2023.

## Built on by (most cited first, 6 of 6)

- [Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting](https://mlsanity.com/paper/2407.09475/) (2024)
- [Warm-Starting Optimization-Based Motion Planning for Robotic Manipulators via Point Cloud-Conditioned Flow Matching](https://mlsanity.com/paper/2510.03460/) (2025)
- [Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction](https://mlsanity.com/paper/2409.12456/) (2024)
- [Recent Advances in Deterministic Human Motion Prediction: A Review](https://mlsanity.com/paper/2312.06184/) (2023)
- [Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees](https://mlsanity.com/paper/2604.15221/) (2026)
- [Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction](https://mlsanity.com/paper/2608.21093/) (2026)

## Abstract (arXiv)

Ensuring the safety of human workers in a collaborative environment with robots is of utmost importance. Although accurate pose prediction models can help prevent collisions between human workers and robots, they are still susceptible to critical errors. In this study, we propose a novel approach called deep ensembles of temporal graph neural networks (DE-TGN) that not only accurately forecast human motion but also provide a measure of prediction uncertainty. By leveraging deep ensembles and employing stochastic Monte-Carlo dropout sampling, we construct a volumetric field representing a range of potential future human poses based on covariance ellipsoids. To validate our framework, we conducted experiments using three motion capture datasets including Human3.6M, and two human-robot interaction scenarios, achieving state-of-the-art prediction error. Moreover, we discovered that deep ensembles not only enable us to quantify uncertainty but also improve the accuracy of our predictions.