Knowledge Commons of Institute of Automation,CAS
面向智能驾驶视觉控制的深度强化学习方法 | |
李栋 | |
2019-05-22 | |
页数 | 158 |
学位类型 | 博士 |
中文摘要 | 智能驾驶技术可以将人类驾驶员从复杂单调的驾驶任务中解放出来,由于其智能性和高效性,被认为是引领新一代智能交通系统的革命技术。现有的智能驾驶感知与控制方案在借助摄像机传感器的同时,还依赖于激光雷达和毫米波雷达等传感器,采用人工设计的驾驶规则来完成控制。但由于激光雷达和毫米波雷达昂贵的价格以及传感器本身的局限性,延缓了智能驾驶的大规模商用。此外基于规则的控制方案在系统的自适应性和智能性方面也有所不足。基于视觉的控制方案在实现车辆智能化控制的同时减少了对昂贵传感器的依赖,现已成为智能驾驶领域最新的研究热点。然而,如何高效准确地从图像数据中感知周围的交通环境,设计出数据高效利用的智能驾驶控制策略仍存在着许多困难与挑战。 本文在综述当前研究现状的基础上,针对智能驾驶视觉控制问题,围绕深度学习和强化学习方法展开深入研究。首先聚焦于车辆前方远距离的交通标志识别问题和近距离的关键道路特征提取问题,随后根据视觉感知结果基于强化学习方法研究车辆的横向控制和换道决策等问题。此外,针对强化学习控制策略收敛缓慢的问题,分别基于高斯过程和图神经网络理论提出了数据高效利用的深度强化学习方法,加快了算法的收敛速度,提高了算法的控制性能。论文的主要章节包含以下工作和贡献:
|
英文摘要 | Due to the intelligence and high efficiency, the autonomous driving can free the human driver from the complex and tedious driving work and is thought to be the next revolution of the intelligent transportation system. The current autonomous driving perception methods not only depend on the camera but also the LiDAR and millimeter-wave radar. The rule-based control strategy is then employed in the control module. Due to the high cost of the radar sensors, it is hard to realize large-scale commercial application. Additionally, the rule-based control methods have limitations on adaptability and intelligence. In contrast, the vision-based control methods only depend on the low-cost onboard camera and have attracted great research attention. However, how to accurately perceive the environment from the visual input and design the intelligent control policy still remain many difficulties and challenges. In this thesis, we first review the current research status and related works, then conduct our autonomous driving visual control policy based on deep learning and reinforcement learning methods. In details, firstly, we focus on the long-distance range traffic sign recognition problem and the short-distance range key track feature extraction problem. Then, the reinforcement learning methods with the visual feature input are proposed to tackle the vehicle lateral control and the lane change decision-making problems. Moreover, for the low data efficiency in the model-free deep reinforcement learning methods, we propose two novel algorithms to accelerate the learning process and improve the data efficiency, i.e. the Gaussian process based and the graph attention network based deep reinforcement learning methods. The main contributions of this thesis are as follows:
|
关键词 | 深度强化学习 智能驾驶 视觉控制 目标检测 图注意力网络 |
语种 | 中文 |
七大方向——子方向分类 | 强化与进化学习 |
文献类型 | 学位论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23944 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
推荐引用方式 GB/T 7714 | 李栋. 面向智能驾驶视觉控制的深度强化学习方法[D]. 中国科学院自动化研究所. 中国科学院大学,2019. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
自动化所李栋博士学位论文.pdf(6681KB) | 学位论文 | 开放获取 | CC BY-NC-SA |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[李栋]的文章 |
百度学术 |
百度学术中相似的文章 |
[李栋]的文章 |
必应学术 |
必应学术中相似的文章 |
[李栋]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论