# SceneAware: Scene-Constrained Pedestrian Trajectory Prediction with LLM-Guided Walkability

arXiv: https://arxiv.org/abs/2506.14144 · HTML: https://mlsanity.com/paper/2506.14144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints](https://mlsanity.com/paper/1806.01482/) (2018)
- [Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2005.08514/) (2020)
- [Social Attention: Modeling Attention in Human Crowds](https://mlsanity.com/paper/1710.04689/) (2017)
- [PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings](https://mlsanity.com/paper/1905.01296/) (2019)
- [Peeking into the Future: Predicting Future Person Activities and Locations in Videos](https://mlsanity.com/paper/1902.03748/) (2019)
- [TPNet: Trajectory Proposal Network for Motion Prediction](https://mlsanity.com/paper/2004.12255/) (2020)
- [Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans](https://mlsanity.com/paper/2001.00735/) (2020)
- [Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation](https://mlsanity.com/paper/2010.01114/) (2020)
- [BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation](https://mlsanity.com/paper/2007.14558/) (2020)
- [Non-Probability Sampling Network for Stochastic Human Trajectory Prediction](https://mlsanity.com/paper/2203.13471/) (2022)
- [Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction](https://mlsanity.com/paper/2403.18447/) (2024)
- [Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Grids](https://mlsanity.com/paper/1909.07507/) (2019)
- [Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion](https://mlsanity.com/paper/2111.00993/) (2021)

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

- [Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking](https://mlsanity.com/paper/2608.30899/) (2026)

## Abstract (arXiv)

Accurate prediction of pedestrian trajectories is essential for applications in robotics and surveillance systems. While existing approaches primarily focus on social interactions between pedestrians, they often overlook the rich environmental context that significantly shapes human movement patterns. In this paper, we propose SceneAware, a novel framework that explicitly incorporates scene understanding to enhance trajectory prediction accuracy. Our method leverages a Vision Transformer~(ViT) scene encoder to process environmental context from static scene images, while Multi-modal Large Language Models~(MLLMs) generate binary walkability masks that distinguish between accessible and restricted areas during training. We combine a Transformer-based trajectory encoder with the ViT-based scene encoder, capturing both temporal dynamics and spatial constraints. The framework integrates collision penalty mechanisms that discourage predicted trajectories from violating physical boundaries, ensuring physically plausible predictions. SceneAware is implemented in both deterministic and stochastic variants. Comprehensive experiments on the ETH/UCY benchmark datasets show that our approach outperforms state-of-the-art methods, with more than 50% improvement over previous models. Our analysis based on different trajectory categories shows that the model performs consistently well across various types of pedestrian movement. This highlights the importance of using explicit scene information and shows that our scene-aware approach is both effective and reliable in generating accurate and physically plausible predictions. Code is available at: https://github.com/juho127/SceneAware.