专栏首页CreateAMindEnd-to-end Driving via Conditional Imitation Learning

End-to-end Driving via Conditional Imitation Learning

https://arxiv.org/abs/1710.02410

End-to-end Driving via Conditional Imitation Learning

Felipe Codevilla, Matthias Müller, Alexey Dosovitskiy, Antonio López, Vladlen Koltun

(Submitted on 6 Oct 2017)

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands. Experimental results demonstrate that the presented approach significantly outperforms a number of baselines. The supplementary video can be viewed at this https URL

使用模拟器 carla也进行了训练,真实环境测试视频也有。

机器之心对carla的介绍: https://baijiahao.baidu.com/s?id=1586489273374923446&wfr=spider&for=pc

本文分享自微信公众号 - CreateAMind(createamind)

原文出处及转载信息见文内详细说明,如有侵权,请联系 yunjia_community@tencent.com 删除。

原始发表时间:2018-01-27

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 99行深度学习代码训练自动驾驶游戏

    deep learning in 2017 is magical. We get to apply immensely complex algorithms t...

    用户1908973
  • 模仿学习 比较图

    ONE-SHOT HIGH-FIDELITY IMITATION: TRAINING LARGE-SCALE DEEP NETS WITH RL

    用户1908973
  • Tracking Emerges by Colorizing Videos

    Carl Vondrick , Abhinav Shrivastava , Alireza Fathi , Sergio Guadarrama ,Kevin M...

    用户1908973
  • NodeJS 各websocket框架性能分析

    For a current project at WhoScored, I needed to learn JavaScript, Node.js and We...

    庞小明
  • 数据是未来工厂的关键

    大数据文摘
  • 克服神经网络灾难性遗忘的自然方法(CS LG)

    不久前,人们发现了一种成功克服神经网络灾难性遗忘的方法。虽然我们知道,针对特定任务,可以用这种方法将预先训练好的神经网络应用于该特定任务,并且通过这种方法来保存...

    奥斯特洛夫斯萌
  • 原文|21世纪地理大数据

    By Jeff de La Beaujardière 25 November 2019

    气象学家
  • 数据仓库,就不是数据库了吗?

    A database is a collection of related data which represents some elements of the...

    Lenis
  • 银行业的大数据:银行如何从客户数据中获得更大的价值?

    36大数据专稿,原文作者:Vaishnavi Agrawal 本文由36大数据翻译组-欧显东翻译。

    华章科技
  • 2017年大数据的十大发展趋势

    研究人员称,会有越来越多的公司加速采用大数据技术。互联网数据中心(IDC)预测,到2020年大数据和分析技术市场,将从今年的1301亿美元增加至2030亿美元。...

    华章科技

扫码关注云+社区

领取腾讯云代金券