OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control

2023/09/22 by Botian Xu, Feng Gao, Xu, Botian +9 · 8 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Robotics (cs.RO) #UAV Applications and Optimization

paper · pdf · doi:10.48550/arxiv.2309.12825

openalex publication_date 2023/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design approach that allows users to easily design and experiment with various application scenarios on top of GPU-parallelized simulations. It also offers a range of benchmark tasks, presenting challenges ranging from single-drone hovering to over-actuated system tracking. In summary, we propose an open-sourced drone simulation platform, equipped with an extensive suite of tools for drone learning. It includes 4 drone models, 5 sensor modalities, 4 control modes, over 10 benchmark tasks, and a selection of widely used RL baselines. To showcase the capabilities of OmniDrones and to support future research, we also provide preliminary results on these benchmark tasks. We hope this platform will encourage further studies on applying RL to practical drone systems.

Cited by

• Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter
• Flow-Aided Flight Through Dynamic Clutters From Point To Motion
• JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
• CrazyMARL: Decentralized Direct Motor Control Policies for Cooperative Aerial Transport of Cable-Suspended Payloads
• Agile in the Face of Delay: Asynchronous End-to-End Learning for Real-World Aerial Navigation
• RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems
• DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
• MoDeSuite: Robot Learning Task Suite for Benchmarking Mobile Manipulation with Deformable Objects

Related

• A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform
• DroneARchery: Human-Drone Interaction through Augmented Reality with Haptic Feedback and Multi-UAV Collision Avoidance Driven by Deep Reinforcement Learning
• Open-World Drone Active Tracking with Goal-Centered Rewards
• Learning Agile, Vision-Based Drone Flight: From Simulation to Reality
• Learning to Fly in Seconds