# Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction

arXiv: https://arxiv.org/abs/2008.00777 · HTML: https://mlsanity.com/paper/2008.00777/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [Stepwise Goal-Driven Networks for Trajectory Prediction](https://mlsanity.com/paper/2103.14107/) (2021)
- [Non-Probability Sampling Network for Stochastic Human Trajectory Prediction](https://mlsanity.com/paper/2203.13471/) (2022)
- [Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction](https://mlsanity.com/paper/2207.09953/) (2022)
- [EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting](https://mlsanity.com/paper/2307.09306/) (2023)
- [SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model](https://mlsanity.com/paper/2403.18452/) (2024)
- [Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction](https://mlsanity.com/paper/2403.18447/) (2024)
- [Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches](https://mlsanity.com/paper/2111.06740/) (2021)
- [Language-Driven Interactive Traffic Trajectory Generation](https://mlsanity.com/paper/2405.15388/) (2024)
- [Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction](https://mlsanity.com/paper/2108.00238/) (2021)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [Continuous Locomotive Crowd Behavior Generation](https://mlsanity.com/paper/2504.04756/) (2025)
- [A Neuro-Symbolic Approach for Enhanced Human Motion Prediction](https://mlsanity.com/paper/2304.11740/) (2023)
- [What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study](https://mlsanity.com/paper/2203.08739/) (2022)
- [Conditional Generative Adversarial Networks for Speed Control in Trajectory Simulation](https://mlsanity.com/paper/2103.11471/) (2021)
- [Qualitative Prediction of Multi-Agent Spatial Interactions](https://mlsanity.com/paper/2307.00065/) (2023)
- [Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review](https://mlsanity.com/paper/2506.14831/) (2025)
- [Frequency Regularization for Improving Adversarial Robustness](https://mlsanity.com/paper/2212.12732/) (2022)
- [NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality](https://mlsanity.com/paper/2408.09511/) (2024)
- [ODG-Q: Robust Quantization via Online Domain Generalization](https://mlsanity.com/paper/2210.08701/) (2022)
- [neuROSym: Deployment and Evaluation of a ROS-based Neuro-Symbolic Model for Human Motion Prediction](https://mlsanity.com/paper/2407.01593/) (2024)
- [Generative Motion In-betweening by Diffusion over Continuous Implicit Representations](https://mlsanity.com/paper/2605.12778/) (2026)

## Abstract (arXiv)

Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (textite.g. pedestrians) simultaneously in a complicated scene. Existing work addressed this challenge by either learning social spatial interactions represented by the positions of a group of pedestrians, while ignoring their temporal coherence (textiti.e. dependencies between different long trajectories), or by understanding the complicated scene layout (textite.g. scene segmentation) to ensure safe navigation. However, unlike previous work that isolated the spatial interaction, temporal coherence, and scene layout, this paper designs a new mechanism, textiti.e., Dynamic and Static Context-aware Motion Predictor (DSCMP), to integrates these rich information into the long-short-term-memory (LSTM). It has three appealing benefits. (1) DSCMP models the dynamic interactions between agents by learning both their spatial positions and temporal coherence, as well as understanding the contextual scene layout.(2) Different from previous LSTM models that predict motions by propagating hidden features frame by frame, limiting the capacity to learn correlations between long trajectories, we carefully design a differentiable queue mechanism in DSCMP, which is able to explicitly memorize and learn the correlations between long trajectories. (3) DSCMP captures the context of scene by inferring latent variable, which enables multimodal predictions with meaningful semantic scene layout. Extensive experiments show that DSCMP outperforms state-of-the-art methods by large margins, such as 9.05% and 7.62% relative improvements on the ETH-UCY and SDD datasets respectively.