# Spatiotemporal Capsule Neural Network for Vehicle Trajectory Prediction

arXiv: https://arxiv.org/abs/2303.02880 · HTML: https://mlsanity.com/paper/2303.02880/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 6 Mar 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Review](https://mlsanity.com/paper/1912.11676/) (2019)
- [Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and Solutions](https://mlsanity.com/paper/2012.06992/) (2020)
- [Time-Series Regeneration with Convolutional Recurrent Generative Adversarial Network for Remaining Useful Life Estimation](https://mlsanity.com/paper/2101.03678/) (2021)
- [A Transfer Learning-based State of Charge Estimation for Lithium-Ion Battery at Varying Ambient Temperatures](https://mlsanity.com/paper/2101.03704/) (2021)
- [Slow-varying Dynamics Assisted Temporal Capsule Network for Machinery Remaining Useful Life Estimation](https://mlsanity.com/paper/2203.16373/) (2022)
- [Subspace Capsule Network](https://mlsanity.com/paper/2002.02924/) (2020)
- [Securing Vehicle-to-Everything (V2X) Communication Platforms](https://mlsanity.com/paper/2003.07191/) (2020)
- [Intelligent Task Offloading for Heterogeneous V2X Communications](https://mlsanity.com/paper/2006.15855/) (2020)
- [IIoT-Enabled Health Monitoring for Integrated Heat Pump System Using Mixture Slow Feature Analysis](https://mlsanity.com/paper/2104.09876/) (2021)
- [Lithium-ion Battery State of Health Estimation based on Cycle Synchronization using Dynamic Time Warping](https://mlsanity.com/paper/2109.13448/) (2021)
- [Vehicle Trajectory Prediction on Highways Using Bird Eye View Representations and Deep Learning](https://mlsanity.com/paper/2207.01407/) (2022)
- [Attention-based Recurrent Neural Network for Urban Vehicle Trajectory Prediction](https://mlsanity.com/paper/1812.07151/) (2018)
- [Communication and Computing Resource Optimization for Connected Autonomous Driving](https://mlsanity.com/paper/2006.15875/) (2020)
- [Intelligent Spectrum Learning for Wireless Networks with Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2103.01531/) (2021)
- [Collaborative Driving: Learning- Aided Joint Topology Formulation and Beamforming](https://mlsanity.com/paper/2203.09915/) (2022)

## Built on by (most cited first, 3 of 3)

- [FollowGen: A Scaled Noise Conditional Diffusion Model for Car-Following Trajectory Prediction](https://mlsanity.com/paper/2411.16747/) (2024)
- [SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks](https://mlsanity.com/paper/2512.00834/) (2025)
- [A Slow-Shifting Concerned Machine Learning Method for Short-term Traffic Flow Forecasting](https://mlsanity.com/paper/2303.17782/) (2023)

## Abstract (arXiv)

Through advancement of the Vehicle-to-Everything (V2X) network, road safety, energy consumption, and traffic efficiency can be significantly improved. An accurate vehicle trajectory prediction benefits communication traffic management and network resource allocation for the real-time application of the V2X network. Recurrent neural networks and their variants have been reported in recent research to predict vehicle mobility. However, the spatial attribute of vehicle movement behavior has been overlooked, resulting in incomplete information utilization. To bridge this gap, we put forward for the first time a hierarchical trajectory prediction structure using the capsule neural network (CapsNet) with three sequential components. First, the geographic information is transformed into a grid map presentation, describing vehicle mobility distribution spatially and temporally. Second, CapsNet serves as the core model to embed local temporal and global spatial correlation through hierarchical capsules. Finally, extensive experiments conducted on actual taxi mobility data collected in Porto city (Portugal) and Singapore show that the proposed method outperforms the state-of-the-art methods.