# EANet: Expert Attention Network for Online Trajectory Prediction

arXiv: https://arxiv.org/abs/2309.05683 · HTML: https://mlsanity.com/paper/2309.05683/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints](https://mlsanity.com/paper/1806.01482/) (2018)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Social Attention: Modeling Attention in Human Crowds](https://mlsanity.com/paper/1710.04689/) (2017)
- [From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting](https://mlsanity.com/paper/2012.01526/) (2020)
- [SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2104.01528/) (2021)
- [EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning](https://mlsanity.com/paper/2303.10876/) (2023)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [TPNet: Trajectory Proposal Network for Motion Prediction](https://mlsanity.com/paper/2004.12255/) (2020)
- [Continual Learning with Adaptive Weights (CLAW)](https://mlsanity.com/paper/1911.09514/) (2019)
- [PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrians](https://mlsanity.com/paper/1805.11833/) (2018)
- [Personalized Trajectory Prediction via Distribution Discrimination](https://mlsanity.com/paper/2107.14204/) (2021)
- [Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction](https://mlsanity.com/paper/2108.00238/) (2021)
- [Improving Pedestrian Prediction Models with Self-Supervised Continual Learning](https://mlsanity.com/paper/2202.07606/) (2022)

## Built on by (most cited first, 1 of 1)

- [Online Residual Learning from Offline Experts for Pedestrian Tracking](https://mlsanity.com/paper/2409.04069/) (2024)

## Abstract (arXiv)

Trajectory prediction plays a crucial role in autonomous driving. Existing mainstream research and continuoual learning-based methods all require training on complete datasets, leading to poor prediction accuracy when sudden changes in scenarios occur and failing to promptly respond and update the model. Whether these methods can make a prediction in real-time and use data instances to update the model immediately(i.e., online learning settings) remains a question. The problem of gradient explosion or vanishing caused by data instance streams also needs to be addressed. Inspired by Hedge Propagation algorithm, we propose Expert Attention Network, a complete online learning framework for trajectory prediction. We introduce expert attention, which adjusts the weights of different depths of network layers, avoiding the model updated slowly due to gradient problem and enabling fast learning of new scenario's knowledge to restore prediction accuracy. Furthermore, we propose a short-term motion trend kernel function which is sensitive to scenario change, allowing the model to respond quickly. To the best of our knowledge, this work is the first attempt to address the online learning problem in trajectory prediction. The experimental results indicate that traditional methods suffer from gradient problems and that our method can quickly reduce prediction errors and reach the state-of-the-art prediction accuracy.