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

TL;DR

SPIRAL is a self-play based incremental learning algorithm that enables autonomous drones to develop complex racing strategies through progressively challenging competitions, enhancing multi-agent drone racing performance.

Contribution

It introduces a versatile self-play framework that integrates with deep reinforcement learning to improve autonomous drone racing in dynamic multi-agent environments.

Findings

SPIRAL effectively trains drones to master complex racing behaviors.

Self-play leads to progressively more challenging and adaptive drone strategies.

Benchmark results show improved performance of various DRL algorithms within SPIRAL.

Abstract

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.