Open AccessPosted Content
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
TL;DR: A new simulator built on Unreal Engine that offers physically and visually realistic simulations for autonomous vehicles in real world and that is designed from the ground up to be extensible to accommodate new types of vehicles, hardware platforms and software protocols.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Parameter Sharing Method for Reinforcement Learning Model between AirSim and UAVs
Shau Yin Tseng,Chin-Feng Lai,Ming-Shi Wang,Ching Ju Chen,Chia Yu Ho +4 more
- 06 Dec 2018
TL;DR: In a virtual environment using the Q - learning training unmanned aerial vehicle landing, then transplanted model of virtual environment in which to train good into real environment, makes the realistic environment of unmanned Aerial vehicle can use cheaper and quickly achieve the same task.
9
Aerial Gym - Isaac Gym Simulator for Aerial Robots
Mihir Kulkarni,Kostas Alexis +1 more
TL;DR: The Aerial Gym simulator as mentioned in this paper is a large-scale simulator that can simulate millions of multi-rotor vehicles parallelly with nonlinear geometric controllers for the Special Euclidean Group SE(3) for attitude, velocity and position tracking.
9
•Dissertation
2D-3D scene understanding for autonomous driving
Maximilian Jaritz
- 26 Jun 2020
TL;DR: This thesis addresses the challenges of label scarcity and fusion of heterogeneous 3D point clouds and 2D images, and proposes to perform 2D-3D cross-modal learning via mutual mimicking between image and point cloud networks to address the source-target domain shift.
9
Exploring Deep Reinforcement Learning for Autonomous Powerline Tracking
Panin Pienroj,Sandro Schönborn,Robert Birke +2 more
- 01 Jan 2019
TL;DR: This work uses realtime simulations based on AirSim to test several state-of-the-art DRL algorithms in controlling the flight of a quadrotor, trained on simple and complicated tracks under different landscapes and ambient conditions.
8
A Survey of Integrated Simulation Environments for Connected Automated Vehicles: Requirements, Tools, and Architecture
Vitaly Stepanyants,Aleksandr Y. Romanov +1 more
TL;DR: A survey of integrated simulation environments for connected automated vehicles identifies challenges and proposes an architecture for an integrated simulation environment with full domain coverage.
8
References
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
A survey of transfer learning
TL;DR: This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied toTransfer learning, which can be applied to big data environments.
Design and use paradigms for Gazebo, an open-source multi-robot simulator
Nathan Koenig,Andrew Howard +1 more
- 01 Sep 2004
TL;DR: Gazebo is designed to fill this niche by creating a 3D dynamic multi-robot environment capable of recreating the complex worlds that would be encountered by the next generation of mobile robots.
3.8K
Reinforcement learning in robotics: A survey
TL;DR: This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
•Book
Numerical methods for ordinary differential equations
John C. Butcher
- 01 Jan 2003
TL;DR: This third edition of Numerical Methods for Ordinary Differential Equations will serve as a key text for senior undergraduate and graduate courses in numerical analysis, and is an essential resource for research workers in applied mathematics, physics and engineering.