Flightmare: A Flexible Quadrotor Simulator

2020/09/01 by Yunlong Song, Song, Yunlong, Selim Naji +7 · 21 citations
Computer Science · Engineering · #Advanced Vision and Imaging #Robotic Path Planning Algorithms #Robotics and Sensor-Based Localization #cs.AI #cs.RO

paper · pdf · doi:10.48550/arxiv.2009.00563

Accepted for publication at 4th Conference on Robot Learning (CoRL), Cambridge MA, USA. 2020

arxiv created 2021/05/09 · arxiv updated 2021/05/11

Abstract

State-of-the-art quadrotor simulators have a rigid and highly-specialized structure: either are they really fast, physically accurate, or photo-realistic. In this work, we propose a novel quadrotor simulator: Flightmare. Flightmare is composed of two main components: a configurable rendering engine built on Unity and a flexible physics engine for dynamics simulation. Those two components are totally decoupled and can run independently of each other. This makes our simulator extremely fast: rendering achieves speeds of up to 230 Hz, while physics simulation of up to 200,000 Hz on a laptop. In addition, Flightmare comes with several desirable features: (i) a large multi-modal sensor suite, including an interface to extract the 3D point-cloud of the scene; (ii) an API for reinforcement learning which can simulate hundreds of quadrotors in parallel; and (iii) integration with a virtual-reality headset for interaction with the simulated environment. We demonstrate the flexibility of Flightmare by using it for two different robotic tasks: quadrotor control using deep reinforcement learning and collision-free path planning in a complex 3D environment.

Cited by

• Drift-Corrected Monocular VIO and Perception-Aware Planning for Autonomous Drone Racing
• Neural NMPC through Signed Distance Field Encoding for Collision Avoidance
• Perception-aware Exploration for Consumer-grade UAVs
• Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing
• SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions
• A Simulation Evaluation Suite for Robust Adaptive Quadcopter Control
• PA-MPPI: Perception-Aware Model Predictive Path Integral Control for Quadrotor Navigation in Unknown Environments
• A Survey on LiDAR-based Autonomous Aerial Vehicles
• DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
• Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach
• Zero-Shot Metric Depth Estimation via Monocular Visual-Inertial Rescaling for Autonomous Aerial Navigation
• Quadrotor Navigation using Reinforcement Learning with Privileged Information
• Learning Real-World Acrobatic Flight from Human Preferences
• CAMAR: Continuous Actions Multi-Agent Routing
• The Open Motion Planning Library 2.0
• Dynamics and Control of Vision-Aided Multi-UAV-tethered Netted System Capturing Non-Cooperative Target
• Reactive Aerobatic Flight via Reinforcement Learning
• YOPO-Rally: A Sim-to-Real Single-Stage Planner for Off-Road Terrain
• Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation
• Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
• GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction

Related

• VisFly: An Efficient and Versatile Simulator for Training Vision-based Flight
• DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
• Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robots
• AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
• FalconGym: A Photorealistic Simulation Framework for Zero-Shot Sim-to-Real Vision-Based Quadrotor Navigation