X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction

2025/10/31 by Aanchal Rajesh Chugh, Chugh, Aanchal Rajesh, Marion Neumeier +4 · 1 voice
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO) #Traffic control and management #Vehicle Dynamics and Control Systems #cs.LG #cs.RO

paper · pdf · doi:10.48550/arxiv.2511.00266

openalex publication_date 2025/10/31 · arxiv published 2025/10/31 · openalex created_date 2025/11/05 · arxiv updated 2026/05/22 · openalex updated_date 2026/07/28

Abstract

Accurate trajectory prediction is crucial for safe and reliable autonomous driving systems, requiring models that capture long-term temporal dependencies while accounting for social interactions among neighboring vehicles in highway driving scenarios. While Long Short Term Memory (LSTM) networks have been widely used in the domain of trajectory prediction, they have limitations such as limited memory capacity and scalar cell state. The recently introduced Extended Long Short Term Memory (xLSTM) addresses these limitations of traditional LSTMs by introducing exponential gating and enhanced memory structures, making them better suited for modeling long-term temporal dependencies. Despite their potential, xLSTM-based models remain underexplored in the context of vehicle trajectory prediction. This paper introduces a novel xLSTM-based highway trajectory prediction framework, X-TRAJ, as the first application of xLSTM, and its physics-aware variant, X-TRACK (eXtended LSTM for TRAjectory prediction Constraint by Kinematics), which explicitly integrates vehicle motion kinematics into the model learning process. By introducing physical constraints, the proposed model generates realistic and feasible highway trajectories. A comprehensive evaluation on the publicly available highway datasets, highD and NGSIM, demonstrates that X-TRACK outperforms state-of-the-art baselines on highD and is among the state-of-the-art models on the NGSIM dataset.

Citations

• TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
• xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
• An Evaluation of Deep Learning Models for Stock Market Trend Prediction
• xLSTMTime : Long-term Time Series Forecasting With xLSTM
• Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
• xLSTM: Extended Long Short-Term Memory
• Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain
• Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directions
• Vehicle trajectory prediction works, but not everywhere
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• Fast Graph Representation Learning with PyTorch Geometric
• A critical evaluation of the Next Generation Simulation (NGSIM) vehicle trajectory dataset
• Graph Attention Networks
• Adam: A Method for Stochastic Optimization
• Long Short-Term Memory

Discussions

• xLSTM for Vehicle Trajectory Prediction: arxiv.org/abs/2511.00266 X-TRACK based on xLSTM achieves SOTA. “Compared to state-of-the-art baselines, X-TRACK achieves performance improvement by 79% at the [bsky, 3 points, 0 comments]

Related

• An LSTM Network for Highway Trajectory Prediction
• Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Network
• Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks
• Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM\n Encoder-Decoder Architecture
• Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction