UNav-Sim: A Visually Realistic Underwater Robotics Simulator and Synthetic Data-generation Framework

Abdelhakim Amer,Olaya Alvarez-Tunon,Halil Ibrahim Ugurlu,Jonas le Fevre Sejersen, Yury Brodskiy,Erdal Kayacan

2023 21ST INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS, ICAR（2023）

引用 0|浏览6

暂无评分

摘要

Underwater robotic surveys can be costly due to the complex working environment and the need for various sensor modalities. While underwater simulators are essential, many existing simulators lack sufficient rendering quality, restricting their ability to transfer algorithms from simulation to real-world applications. To address this limitation, we introduce UNav-Sim, which, to the best of our knowledge, is the first simulator to incorporate the efficient, high-detail rendering of Unreal Engine 5 (UE5). UNav-Sim is open-source(1) and includes an autonomous vision-based navigation stack. By supporting standard robotics tools like ROS, UNav-Sim enables researchers to develop and test algorithms for underwater environments efficiently.

查看译文

关键词

Simulated Robot,Unmanned Underwater Vehicles,Undersea,Robot Operating System,Unreal Engine,Actuator,Equations Of Motion,Activation Maps,Monocular,Imaging Conditions,Model Predictive Control,Deep Reinforcement Learning,Artificial Intelligence Algorithms,Image Synthesis,Vision Algorithms,Learning-based Algorithms,Physical Simulation,Underwater Vehicles,Visual Localization,Coriolis Force,Underwater Image,Vehicle Body,Body-fixed Frame,Robotics Community,Physics Engine,Rigid Body,Software Architecture,Linear Trajectory,Phase Function,Position Error

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要