End-to-end learning for off-road terrain navigation using the Chrono open-source simulation platform

End-to-end learning for off-road terrain navigation using the Chrono open-source simulation platform
复制标题

使用 Chrono 开源仿真平台进行越野地形导航的端到端学习

DOI:
10.1007/s11044-022-09816-1
复制
发表时间:
2022
影响因子:
3.4
通讯作者:
Negrut, Dan
Negrut, Dan
中科院分区:
工程技术2区
文献类型:
--
作者:
Benatti, Simone;Young, Aaron;Elmquist, Asher;Taves, Jay;Tasora, Alessandro;Serban, Radu;Negrut, Dan

文献摘要

参考文献

被引文献

相似文献

本贡献 () 描述了一个开源的、基于物理的模拟基础设施,可用于学习和测试越野导航中的控制策略; () 演示了在依赖于模拟传感器数据融合(相机、GPS 和 IMU)的端到端学习练习中使用模拟平台。对于(),50万行开源代码支持车辆动力学(轮式/履带式车辆、漫游车)、可变形和不可变形地形以及虚拟传感。该库有一个 Python API,用于与现有机器学习框架连接。为此,我们使用 Gator 越野车来演示在丘陵条件下使用在不可变形地形上学习的策略,同时在可变形地形上随机放置的障碍物周围导航时的表现。丘陵地形覆盖了 80×80 m 的区域,用户可以控制土壤以呈现各种行为,例如不可变形、可变形硬体(淤泥状)、可变形软体(雪状)等。据我们所知,没有其他基于物理的开源引擎可用于模拟在可变形地形上运行的自主代理的越野移动性。本文报告的结果可以使用公共存储库中提供的模型和数据进行重现(威斯康星大学麦迪逊分校基于模拟的工程实验室,支持模型、脚本、数据,https://go.wisc.edu/arflqq,)。与测试运行相关的动画可在线获取(威斯康星大学麦迪逊分校基于模拟的工程实验室,支持模拟,https://go.wisc.edu/256xb9,)。
This contribution () describes an open-source, physics-based simulation infrastructure that can be used to learn and test control policies in off-road navigation; and () demonstrates the use of the simulation platform in an end-to-end learning exercise that relies on simulated sensor data fusion (camera, GPS and IMU). For (), the 0.5 million lines of open-source code support vehicle dynamics (wheeled/tracked vehicles, rovers), deformable & non-deformable terrains, and virtual sensing. The library has a Python API for interfacing with existing Machine Learning frameworks. For, we use a Gator off-road vehicle to demonstrate how a policy learned on non-deformable terrain performs when used in hilly conditions while navigating around a course of randomly placed obstacles on deformable terrain. The hilly terrain covers an 80×80 m patch and the soil can be controlled by the user to assume various behavior, e.g. non-deformable, deformable hard (silt-like), deformable soft (snow-like), etc. To the best of our knowledge, there is no other open-source, physics-based engine that can be used to simulate off-road mobility of autonomous agents operating on deformable terrains. The results reported herein can be reproduced with models and data available in a public repository (UW-Madison Simulation Based Engineering Laboratory, Supporting models, scripts, data, https://go.wisc.edu/arflqq, ). Animations associated with the tests run are available online (UW-Madison Simulation Based Engineering Laboratory, Supporting simulations, https://go.wisc.edu/256xb9, ).
DOI: 10.1109/iros.2017.8206048
发表时间: 2017-03
期刊: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子: --
作者:
Steven Bohez;Tim Verbelen;E. D. Coninck;B. Vankeirsbilck;P. Simoens;B. Dhoedt
通讯作者: Steven Bohez;Tim Verbelen;E. D. Coninck;B. Vankeirsbilck;P. Simoens;B. Dhoedt
DOI: 10.15607/rss.2018.xiv.056
发表时间: 2017-09
期刊: Robotics: Science and Systems XIV
影响因子: --
作者:
Yunpeng Pan;Ching-An Cheng;Kamil Saigol;Keuntaek Lee;Xinyan Yan;Evangelos A. Theodorou;Byron Boots
通讯作者: Yunpeng Pan;Ching-An Cheng;Kamil Saigol;Keuntaek Lee;Xinyan Yan;Evangelos A. Theodorou;Byron Boots
DOI: 10.1109/tip.2017.2686001
发表时间: 2017-06-01
影响因子: 10.6
作者:
Tang, Zhongwei;von Gioi, Rafael Grompone;Morel, Jean-Michel
通讯作者: Morel, Jean-Michel
DOI: --
发表时间: 2018-06
期刊: ArXiv
影响因子: --
作者:
J. Matas;Stephen James;A. Davison
通讯作者: J. Matas;Stephen James;A. Davison
Chrono::Vehicle:基于模板的地面车辆建模和仿真
DOI: --
发表时间: 2019
影响因子: --
作者:
R. Serban;Michael Taylor;D. Negrut;A. Tasora
通讯作者: A. Tasora