arXiv 2510.225682025-10-26cs.ROcs.AIcs.MAcs.SYeess.SY

SPIRAL：基于自博弈增量竞赛算法的多无人机竞赛学习

SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions

Department of Mechatronics Engineering Faculty of Engineering Turkish-German University（机械工程系工程学院德土大学）

Onur Akgün

备注：: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
DOI：: 10.1109/ASYU67174.2025.11208263

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

SPIRAL通过自博弈机制实现多无人机竞赛中的自主学习，提供灵活且可扩展的学习框架，提升竞赛策略的稳健性和适应性。

摘要：

本文介绍SPIRAL（Self-Play Incremental Racing Algorithm for Learning），一种用于训练多智能体竞赛中自主无人机的新方法。SPIRAL独特地采用自博弈机制，逐步培养复杂的竞赛行为，以应对具有挑战性和动态性的环境。通过这一自博弈核心，无人机会持续与日益熟练的自身版本竞争，自然提升竞争互动的难度。这种渐进学习过程引导智能体从掌握基本飞行控制到执行复杂的多无人机竞赛策略。我们的方法设计灵活，允许在自博弈框架内整合任何最先进的深度强化学习（DRL）算法。仿真显示了SPIRAL的显著优势，并对各种在其中运行的DRL算法的性能进行了基准测试。因此，我们为自主无人机竞赛领域贡献了一个灵活、可扩展且自我改进的学习框架。SPIRAL通过其自博弈动态自主生成合适且递增的挑战，为在多智能体环境中开发稳健和适应性强的竞赛策略提供了新的方向。本研究为在日益复杂和竞争性场景中提升自主竞赛无人机的性能和可靠性开辟了新的途径。

英文摘要：

This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism to incrementally cultivate complex racing behaviors within a challenging, dynamic environment. Through this self-play core, drones continuously compete against increasingly proficient versions of themselves, naturally escalating the difficulty of competitive interactions. This progressive learning journey guides agents from mastering fundamental flight control to executing sophisticated cooperative multi-drone racing strategies. Our method is designed for versatility, allowing integration with any state-of-the-art Deep Reinforcement Learning (DRL) algorithms within its self-play framework. Simulations demonstrate the significant advantages of SPIRAL and benchmark the performance of various DRL algorithms operating within it. Consequently, we contribute a versatile, scalable, and self-improving learning framework to the field of autonomous drone racing. SPIRAL's capacity to autonomously generate appropriate and escalating challenges through its self-play dynamic offers a promising direction for developing robust and adaptive racing strategies in multi-agent environments. This research opens new avenues for enhancing the performance and reliability of autonomous racing drones in increasingly complex and competitive scenarios.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。