# TrajLearn: Trajectory Prediction Learning using Deep Generative Models

arXiv: https://arxiv.org/abs/2501.00184 · HTML: https://mlsanity.com/paper/2501.00184/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 94 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction](https://mlsanity.com/paper/1802.08714/) (2018)
- [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://mlsanity.com/paper/2004.10240/) (2020)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [PiP: Planning-informed Trajectory Prediction for Autonomous Driving](https://mlsanity.com/paper/2003.11476/) (2020)
- [Deep AutoRegressive Networks](https://mlsanity.com/paper/1310.8499/) (2013)
- [MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction](https://mlsanity.com/paper/2110.01401/) (2021)
- [A Survey on Trajectory Data Management, Analytics, and Learning](https://mlsanity.com/paper/2003.11547/) (2020)
- [Spectral Temporal Graph Neural Network for Trajectory Prediction](https://mlsanity.com/paper/2106.02930/) (2021)
- [STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes](https://mlsanity.com/paper/2204.01026/) (2022)
- [Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving](https://mlsanity.com/paper/2109.01510/) (2021)
- [A Survey on Map-Matching Algorithms](https://mlsanity.com/paper/1910.13065/) (2019)
- [Spatiotemporal Data Mining: A Survey on Challenges and Open Problems](https://mlsanity.com/paper/2103.17128/) (2021)
- [Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians](https://mlsanity.com/paper/2010.09056/) (2020)
- [Destination Prediction Based on Partial Trajectory Data](https://mlsanity.com/paper/2004.07473/) (2020)
- [(Blue) Taxi Destination and Trip Time Prediction from Partial Trajectories](https://mlsanity.com/paper/1509.05257/) (2015)

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

- [Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing](https://mlsanity.com/paper/2510.26089/) (2025)

## Abstract (arXiv)

Trajectory prediction aims to estimate an entity's future path using its current position and historical movement data, benefiting fields like autonomous navigation, robotics, and human movement analytics. Deep learning approaches have become key in this area, utilizing large-scale trajectory datasets to model movement patterns, but face challenges in managing complex spatial dependencies and adapting to dynamic environments. To address these challenges, we introduce TrajLearn, a novel model for trajectory prediction that leverages generative modeling of higher-order mobility flows based on hexagonal spatial representation. TrajLearn predicts the next k steps by integrating a customized beam search for exploring multiple potential paths while maintaining spatial continuity. We conducted a rigorous evaluation of TrajLearn, benchmarking it against leading state-of-the-art approaches and meaningful baselines. The results indicate that TrajLearn achieves significant performance gains, with improvements of up to ~40% across multiple real-world trajectory datasets. In addition, we evaluated different prediction horizons (i.e., various values of k), conducted resolution sensitivity analysis, and performed ablation studies to assess the impact of key model components. Furthermore, we developed a novel algorithm to generate mixed-resolution maps by hierarchically subdividing hexagonal regions into finer segments within a specified observation area. This approach supports selective detailing, applying finer resolution to areas of interest or high activity (e.g., urban centers) while using coarser resolution for less significant regions (e.g., rural areas), effectively reducing data storage requirements and computational overhead. We promote reproducibility and adaptability by offering complete code, data, and detailed documentation with flexible configuration options for various applications.