TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer
- 9 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (12) , 10803-10810
Abstract
Dogfighting is a challenging scenario in aerial applications that requires a comprehensive understanding of both strategic maneuvers and the aerodynamics of agile aircraft. The aerial agent needs to not only understand tactically evolving maneuvers of fighter jets from a long-term perspective but also react to rapidly changing aerodynamics of aircraft from a short-term viewpoint. In this paper, we introduce TempFuser, a novel long short-term temporal fusion transformer architecture that can learn agile, tactical, and acrobatic flight maneuvers in complex dogfight problems. Our approach integrates two distinct temporal transition embeddings into a transformer-based network to comprehensively capture both the long-term tactics and short-term agility of aerial agents. By incorporating these perspectives, our policy network generates end-to-end flight commands that secure dominant positions over the long term and effectively outmaneuver agile opponents. After training in a high-fidelity flight simulator, our model successfully learns to execute strategic maneuvers, outperforming baseline policy models against various types of opponent aircraft. Notably, our model exhibits human- like acrobatic maneuvers even when facing adversaries with superior specifications, all without relying on prior knowledge. Moreover, it demonstrates robust pursuit performance in challenging supersonic and low-altitude situations. Demo videos are available at https://sites.google.com/view/tempfuser .Keywords
All Related Versions
Funding Information
- Agency for Defence Development (UE191120RD)
This publication has 26 references indexed in Scilit:
- Deep Reinforcement Learning-Based Air-to-Air Combat Maneuver Generation in a Realistic EnvironmentIEEE Access, 2023
- Learning to Drive at Unsignalized Intersections using Attention-based Deep Reinforcement Learning2021
- Application of Deep Reinforcement Learning in Maneuver Planning of Beyond-Visual-Range Air CombatIEEE Access, 2021
- Beyond-Visual-Range Air Combat Tactics Auto-Generation by Reinforcement Learning2020
- Evasive Maneuver Strategy for UCAV in Beyond-Visual-Range Air Combat Based on Hierarchical Multi-Objective Evolutionary AlgorithmIEEE Access, 2020
- Influence of unmanned combat aerial vehicle agility on short-range aerial combat effectivenessAerospace Science and Technology, 2020
- Maneuver Decision of UAV in Short-Range Air Combat Based on Deep Reinforcement LearningIEEE Access, 2019
- UAV Air Combat Autonomous Maneuver Decision Based on DDPG Algorithm2019
- An autonomous aerial combat framework for two-on-two engagements based on basic fighter maneuversAerospace Science and Technology, 2018
- Measuring technological trends: A comparison between U.S. and U.S.S.R./Russian jet fighter aircraftTechnological Forecasting and Social Change, 2014