A prior information informed learning architecture for flying trajectory prediction

TL;DR

This paper presents a novel, hardware-efficient trajectory prediction framework that combines environmental priors with a Dual-Transformer-Cascaded architecture to accurately predict flying object landing points, demonstrated on tennis ball trajectories.

Contribution

The paper introduces a new DTC architecture integrating environmental priors for improved trajectory prediction, especially in real-world outdoor sports scenarios.

Findings

Outperforms existing trajectory prediction methods in accuracy

Effectively predicts tennis ball landing points using minimal hardware

Demonstrates robustness with ablation and comparative experiments

Abstract

Trajectory prediction for flying objects is critical in domains ranging from sports analytics to aerospace. However, traditional methods struggle with complex physical modeling, computational inefficiencies, and high hardware demands, often neglecting critical trajectory events like landing points. This paper introduces a novel, hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture. We demonstrate this approach by predicting the landing points of tennis balls in real-world outdoor courts. Using a single industrial camera and YOLO-based detection, we extract high-speed flight coordinates. These coordinates, fused with structural environmental priors (e.g., court boundaries), form a comprehensive dataset fed into our proposed DTC model. A first-level Transformer classifies the trajectory, while a second-level Transformer synthesizes these features to precisely predict the landing point. Extensive ablation and comparative experiments demonstrate that integrating environmental priors within the DTC architecture significantly outperforms existing trajectory prediction frameworks