Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments #39

Open
DeepTecher opened this issue May 21, 2019 · 0 comments
Labels
论文速递 无人驾驶最新相关论文

Comments

@DeepTecher
Copy link
Owner


Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments

提交日期:2019-05-16
团队:挪威科技大学
作者:Hege Haavaldsen, Max Aasboe, Frank Lindseth
摘要:近年来,在车辆无人驾驶的能力方面取得了相当大的进步。端到端方法尝试使用单个、全面的软件组件来实现自动驾驶。最近深度学习的突破显着提高了端到端系统的能力,现在这些系统被认为是当前最先进解决方案的可能替代方案。本文研究了包含其他车辆,交通信号灯和速度限制的模拟城市环境中自动驾驶车辆的端到端学习。此外,本文还探讨了端到端系统执行导航命令的能力,并研究了通过利用后续视觉线索之间的时间依赖性是否可以实现改进的性能。提出了两种端到端架构:传统的卷积神经网络和将卷积神经网络与循环层相结合的扩展设计。使用来自模拟城市环境的专家驾驶数据训练模型,并且通过在看不见的模拟环境中的驾驶性能来评估模型。本文的结果表明,端到端系统可以在简单的城市环境中自主运行。此外,本文发现在后续图像中利用时间信息增强了系统判断运动和距离的能力。

@DeepTecher DeepTecher added the 论文速递 无人驾驶最新相关论文 label May 21, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
论文速递 无人驾驶最新相关论文
Projects
None yet
Development

No branches or pull requests

1 participant