TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seong, Hyunki, Shim, David Hyunchul
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912044199968768
author Seong, Hyunki
Shim, David Hyunchul
author_facet Seong, Hyunki
Shim, David Hyunchul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_03257
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer
Seong, Hyunki
Shim, David Hyunchul
Robotics
Artificial Intelligence
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.
title TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2308.03257