AirSim: High-Fidelity Visual and Physical Simulation for Autonomous
Vehicles
S. Shah, D. Dey, C. Lovett, and A. Kapoor. (2017)cite arxiv:1705.05065Comment: Accepted for Field and Service Robotics conference 2017 (FSR 2017).
Abstract
Developing and testing algorithms for autonomous vehicles in real world is an
expensive and time consuming process. Also, in order to utilize recent advances
in machine intelligence and deep learning we need to collect a large amount of
annotated training data in a variety of conditions and environments. We present
a new simulator built on Unreal Engine that offers physically and visually
realistic simulations for both of these goals. Our simulator includes a physics
engine that can operate at a high frequency for real-time hardware-in-the-loop
(HITL) simulations with support for popular protocols (e.g. MavLink). The
simulator is designed from the ground up to be extensible to accommodate new
types of vehicles, hardware platforms and software protocols. In addition, the
modular design enables various components to be easily usable independently in
other projects. We demonstrate the simulator by first implementing a quadrotor
as an autonomous vehicle and then experimentally comparing the software
components with real-world flights.
Description
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
%0 Generic
%1 shah2017airsim
%A Shah, Shital
%A Dey, Debadeepta
%A Lovett, Chris
%A Kapoor, Ashish
%D 2017
%K ML simulation
%T AirSim: High-Fidelity Visual and Physical Simulation for Autonomous
Vehicles
%U http://arxiv.org/abs/1705.05065
%X Developing and testing algorithms for autonomous vehicles in real world is an
expensive and time consuming process. Also, in order to utilize recent advances
in machine intelligence and deep learning we need to collect a large amount of
annotated training data in a variety of conditions and environments. We present
a new simulator built on Unreal Engine that offers physically and visually
realistic simulations for both of these goals. Our simulator includes a physics
engine that can operate at a high frequency for real-time hardware-in-the-loop
(HITL) simulations with support for popular protocols (e.g. MavLink). The
simulator is designed from the ground up to be extensible to accommodate new
types of vehicles, hardware platforms and software protocols. In addition, the
modular design enables various components to be easily usable independently in
other projects. We demonstrate the simulator by first implementing a quadrotor
as an autonomous vehicle and then experimentally comparing the software
components with real-world flights.
@misc{shah2017airsim,
abstract = {Developing and testing algorithms for autonomous vehicles in real world is an
expensive and time consuming process. Also, in order to utilize recent advances
in machine intelligence and deep learning we need to collect a large amount of
annotated training data in a variety of conditions and environments. We present
a new simulator built on Unreal Engine that offers physically and visually
realistic simulations for both of these goals. Our simulator includes a physics
engine that can operate at a high frequency for real-time hardware-in-the-loop
(HITL) simulations with support for popular protocols (e.g. MavLink). The
simulator is designed from the ground up to be extensible to accommodate new
types of vehicles, hardware platforms and software protocols. In addition, the
modular design enables various components to be easily usable independently in
other projects. We demonstrate the simulator by first implementing a quadrotor
as an autonomous vehicle and then experimentally comparing the software
components with real-world flights.},
added-at = {2019-12-20T11:27:01.000+0100},
author = {Shah, Shital and Dey, Debadeepta and Lovett, Chris and Kapoor, Ashish},
biburl = {https://www.bibsonomy.org/bibtex/2dd7d6e34c66e1c98c00e9d5d0201a65a/rpennec},
description = {AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles},
interhash = {79e0ccee0f8eede2f9e3f3f55f4141ab},
intrahash = {dd7d6e34c66e1c98c00e9d5d0201a65a},
keywords = {ML simulation},
note = {cite arxiv:1705.05065Comment: Accepted for Field and Service Robotics conference 2017 (FSR 2017)},
timestamp = {2019-12-20T11:27:01.000+0100},
title = {AirSim: High-Fidelity Visual and Physical Simulation for Autonomous
Vehicles},
url = {http://arxiv.org/abs/1705.05065},
year = 2017
}