Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A prior information informed learning architecture for flying trajectory prediction

Xianda Huang, Zidong Han, Ruibo Jin, Zhenyu Wang, Wenyu Li, Xiaoyang Li, Yi Gong

TL;DR

A novel, hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture is introduced, demonstrated by predicting the landing points of tennis balls in real-world outdoor courts.

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

A prior information informed learning architecture for flying trajectory prediction

TL;DR

A novel, hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture is introduced, demonstrated by predicting the landing points of tennis balls in real-world outdoor courts.

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
Paper Structure (20 sections, 24 equations, 7 figures, 6 tables)

This paper contains 20 sections, 24 equations, 7 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Kinematic Model-based Trajectory Prediction
  4. Data-driven Trajectory Prediction
  5. Flying Trajectory Dataset Construction
  6. Data Acquisition System
  7. Dataset Construction Method
  8. Trajectory Prediction Model
  9. Prior Information Extraction Module
  10. Trajectory Classification Module
  11. Landing Point Prediction Module
  12. Experimental Results
  13. Implementation Details
  14. Evaluation Metrics
  15. Dataset Preprocessing
  16. ...and 5 more sections

Figures (7)

  • Figure 1: (a) The schematic overview of the trajectory data acquisition system. (b) Schematic diagram of the experimental scene.
  • Figure 2: Flowchart of dataset construction.
  • Figure 3: Overview of the trajectory prediction model - PIDTC.
  • Figure 4: (a) Structure of the trajectory classification module. (b) Structure of the landing point prediction module.
  • Figure 5: The loss during training and testing processes. (a) The BCE loss of classification module. (b) The MSE loss of prediction module.
  • ...and 2 more figures