Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Survey of Simulators for Aerial Robots: An Overview and In-Depth Systematic Comparisons

Cora A. Dimmig, Giuseppe Silano, Kimberly McGuire, Chiara Gabellieri, Wolfgang Hönig, Joseph Moore, Marin Kobilarov

TL;DR

This survey addresses the challenge of choosing among a large landscape of UAV simulators by cataloging 44 options and performing in-depth comparisons for 14. It defines a taxonomy and decision factors spanning physics fidelity, visual realism, autopilot compatibility, multi-vehicle support, sensor modeling, and integration with learning frameworks. The paper highlights the balance between standardization and diversity, discusses aerodynamics’ role, and emphasizes benchmarking, data sharing, and sustainability across academic and industry-driven tools. Practically, it guides researchers to begin with robust universal simulators and progressively integrate specialized ones to meet domain-specific needs, while acknowledging the rapid evolution of the simulation ecosystem.

Abstract

Uncrewed Aerial Vehicle (UAV) research faces challenges with safety, scalability, costs, and ecological impact when conducting hardware testing. High-fidelity simulators offer a vital solution by replicating real-world conditions to enable the development and evaluation of novel perception and control algorithms. However, the large number of available simulators poses a significant challenge for researchers to determine which simulator best suits their specific use-case, based on each simulator's limitations and customization readiness. In this paper we present an overview of 44 UAV simulators, including in-depth, systematic comparisons for 14 of the simulators. Additionally, we present a set of decision factors for selection of simulators, aiming to enhance the efficiency and safety of research endeavors.

Survey of Simulators for Aerial Robots: An Overview and In-Depth Systematic Comparisons

TL;DR

This survey addresses the challenge of choosing among a large landscape of UAV simulators by cataloging 44 options and performing in-depth comparisons for 14. It defines a taxonomy and decision factors spanning physics fidelity, visual realism, autopilot compatibility, multi-vehicle support, sensor modeling, and integration with learning frameworks. The paper highlights the balance between standardization and diversity, discusses aerodynamics’ role, and emphasizes benchmarking, data sharing, and sustainability across academic and industry-driven tools. Practically, it guides researchers to begin with robust universal simulators and progressively integrate specialized ones to meet domain-specific needs, while acknowledging the rapid evolution of the simulation ecosystem.

Abstract

Uncrewed Aerial Vehicle (UAV) research faces challenges with safety, scalability, costs, and ecological impact when conducting hardware testing. High-fidelity simulators offer a vital solution by replicating real-world conditions to enable the development and evaluation of novel perception and control algorithms. However, the large number of available simulators poses a significant challenge for researchers to determine which simulator best suits their specific use-case, based on each simulator's limitations and customization readiness. In this paper we present an overview of 44 UAV simulators, including in-depth, systematic comparisons for 14 of the simulators. Additionally, we present a set of decision factors for selection of simulators, aiming to enhance the efficiency and safety of research endeavors.
Paper Structure (16 sections, 1 equation, 3 figures, 7 tables)

This paper contains 16 sections, 1 equation, 3 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Multirotors
  3. Helicopters
  4. Fixed-wings
  5. Aerial manipulators
  6. UAV Simulators
  7. Universal simulators
  8. Sensor-focused simulators
  9. Learning-focused simulators
  10. Dynamics-focused simulators
  11. Swarming simulators
  12. Simulators part of flight stacks
  13. Flight simulators
  14. UAV Simulator Comparison
  15. Discussion
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Examples of simulation environments: (a) 512 quadrotors in Aerial Gym, (b) quadrotor in Flightmare, (c) three quadrotors in gym-pybullet-drones, (d) three quadrotors with a triangular payload in RotorTM, (e) quadrotor with a racing gate in Aerostack2, and (f) Cessna 172P cockpit view in FlightGear.
  • Figure 2: Schematic representations of a multirotor and fixed-wing with global frames $O_W$ and body frames $O_B$.
  • Figure 3: Toy can in Gazebo Classic and Flightmare simulation environments. In (b), the green bounding box denotes a detection by DOPE TremblayBirchfield2018Deep. The comparable image in the Gazebo Classic simulation did not yield detections by DOPE due to its lower visual fidelity. Gazebo Classic utilizes OGRE for rendering, while Flightmare uses Unity.