Anticipatory Runway Incursion Prevention Systems

Abstract

SUMMARY Avoiding runway incursions is a significant challenge and a top priority in aviation. Due to all causes of runway incursions belong to human factors, runway incursion prevention systems should remove hu- man from the system operation loop as much as possible. Although current runway incursion prevention systems have made big progress on how to obtain accurate and su ffi cient information of aircraft / vehicles, they cannot predict and detect runway incursions as early as experienced air tra ffi c controllers by using the same surveillance information, and cannot give explicit instructions and / or suggestions to prevent runway incursions like real air tra ffi c controllers either. In one word, human still plays an important position in current runway incursion prevention systems. In order to remove human factors from the system operation loop as much as possible, this paper proposes a new type of runway incursion prevention system based on logic-based reasoning. The system predicts and detects runway incursions, then gives explicit instructions and / or suggestions to pilots / drivers to avoid runway incursions / collisions. The features of the system include long-range prediction of incidents, explicit instructions and / or suggestions, and flexible model for di ff erent policies and airports. To evaluate our system, we built a simulation system, and evaluated our system using both real historical scenarios and conventional fictional scenarios. The evaluation showed that our system is e ff ective at providing earlier prediction of incidents than current systems, giving explicit instructions and / or suggestions for handling the incidents e ff ectively, and customizing for specific policies and airports using flexible model.

Authors

• Kai Shi
• Y. Goto
• Zhiliang Zhu
• Jingde Cheng

Keywords

• Computer Science
• Engineering