Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM61807
Volume:
10 |
4 |
April 2026
Pages:
1-11
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Aviation
Vels Institute of Science, Technology & Advanced Studies

Aviation
Vels Institute of Science, Technology & Advanced Studies

Aviation
Vels Institute of Science, Technology & Advanced Studies
Aviation
Vels Institute of Science, Technology & Advanced Studies
Aviation
Vels Institute of Science, Technology & Advanced Studies
This paper presents the development of an Artificial Intelligence-enhanced Aircraft Collision Avoidance and Alert System inspired by the Traffic Collision Avoidance System (TCAS) used in modern aviation. The conventional TCAS operates on transponder-based interrogation and Resolution Advisory (RA) logic which has inherent limitations in complex multi-aircraft scenarios, GPS-denied environments, and situations requiring adaptive decision-making. The proposed system integrates a Long Short-Term Memory (LSTM) neural network for trajectory prediction combined with a rule-based RA engine inspired by TCAS II standards, implemented in TypeScript and Node.js. Seven distinct collision scenarios are simulated: head-on collision, crossing paths, overtaking, climb and descent conflicts, simultaneous multi-aircraft threats, GPS-degraded environments, and near-miss recovery. Results demonstrate a 34% reduction in false alarms, 28% improvement in trajectory prediction accuracy, and adaptive resolution advisories issued 1.8 seconds earlier than traditional TCAS. The system architecture includes real-time ADS-B data parsing, a threat assessment module, an AI prediction engine, and a graphical alert dashboard.
KEYWORDS
The AI-Enhanced Aircraft Collision Avoidance and Alert System successfully addresses critical limitations of conventional TCAS. By integrating an LSTM trajectory prediction engine with TCAS II-inspired coordinated RA logic, the system achieves a 34% reduction in false alarms, 28% improvement in trajectory prediction accuracy, and 1.8-second earlier advisory generation in multi-threat scenarios. Results across seven simulated scenarios demonstrate that AI-enhanced collision avoidance logic significantly outperforms rule-based systems in high-complexity airspace while maintaining equivalent safety in standard conflicts. This validates the feasibility of AI integration in aviation safety-critical applications.
[1] J. K. Kuchar and A. C. Drumm, "The Traffic Alert and Collision Avoidance System," Lincoln Laboratory Journal, vol. 16, no. 2, pp. 277–296, 2007. [2] X. Shi et al., "Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting," Advances in Neural Information Processing Systems, vol. 28, 2015. [3] X. Olive and J. Morio, "Trajectory Clustering of Air Traffic Flows Around Airports," Aerospace Science and Technology, vol. 84, pp. 776–781, 2019. [4] E. D. Kaplan and C. J. Hegarty, Understanding GPS/GNSS: Principles and Applications, 3rd ed., Norwood, MA: Artech House, 2017. [5] N. Durand and J. M. Alliot, "A Neural Network Based Conflict Resolution System," Air Traffic Control Quarterly, vol. 4, no. 4, pp. 325–346, 1996. [6] M. J. Kochenderfer, J. E. Holland, and J. P. Chryssanthacopoulos, "Next Generation Airborne Collision Avoidance System," Lincoln Laboratory Journal, vol. 19, no. 1, pp. 17–33, 2012. [7] M. Schafer et al., "Bringing Up OpenSky: A Large-Scale ADS-B Sensor Network for Research," in Proc. 13th IEEE/ACM IPSN, Berlin, 2014, pp. 83–94. [8] S. Temizer et al., "Collision Avoidance for Unmanned Aircraft Using Markov Decision Processes," in Proc. AIAA Guidance Navigation and Control Conference, 2010. [9] RTCA Inc., Minimum Operational Performance Standards for TCAS II Version 7.1, RTCA DO-185B, Washington, DC, 2008. [10] Eurocontrol, ACAS Guide: Airborne Collision Avoidance System, Eurocontrol Safety Publications, Brussels, 2022.
Publication Date
4/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...