Precision in 3D positional forecasting with machine learning and deep temporal architectures

Abstract

We present a comparative analysis of traditional machine learning (ML) models, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB), and deep learning (DL) architectures, convolutional neural networks (CNN), and bidirectional long short-term memory (BiLSTM) for high-precision 3D positional forecasting. Conventional approaches often underperform when modeling complex spatiotemporal dependencies, limiting their use in dynamic systems such as robotics and autonomous vehicles. This study highlights BiLSTM's advantage in learning bidirectional temporal features, achieving superior R² scores and stable prediction intervals compared to both classical ML and spatially-focused CNN models. Uncertainty metrics, prediction interval coverage probability (PICP), and mean prediction interval width (MPIW) provide additional insight into model reliability. Experiments on a 22-hour GPS dataset confirm that BiLSTM achieves both high accuracy and predictive confidence, underscoring its suitability for real-world trajectory forecasting.