检索结果-南通市图书馆

Car-following behavior modeling driven by small data sets based on mnemonic extreme gradient boosting framework

Science China(Information Sciences) 2022年第6期65卷 271-272页

作者： Baichuan LOU Yufang LI Xiaoding LU Zhe XU Department of Vehicle Engineering Nanjing University of Aeronautics and Astronautics Key Laboratory of Advanced Manufacture Technology for Automobile Parts (Chongqing University of Technology) Ministry of Education

Dear editor,In recent years, data-driven car-following models have been developed based on their ability to drill down to information in driving data and their flexibility. According to a study by Fleming et al. [1], the main limitation of existing methods is an insufficient amount of natural driving data. In addition,there are many situations during actual driving processes,such as those under extreme conditions [2] and in the early stages of car-following behavior modeling. In these cases,sparse data learning algorithms are indispensable.

关键词： car-following model sparse data learning XGBoost LSTM dynamic constraints

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Unified dynamic Control Method for a Redundant Dual Arm Robot

引用

Journal of Bionic Engineering 2015年第3期12卷 361-371页

作者： Meiling Wang Minzhou Luo Tao Li Marco Ceccarelli Department of Automation University of Science and Technology of China Hefei 230026 China Institute of Advanced Manufacturing Technology Hefei Institute of Physical Science Chinese Academy of Sciences Changzhou 213164 China LARM Laboratory of Robotics and Meehatronies DiMSAT-University of Cassino Via Di Biasio 43 03043 Cassino (Fr) Italy

Compared to single arm robot system, dual arm robot has the ability of performing human-like dexterity and cooperation. Dual arm cooperative operation has attracted more and more attention in industrial applications, such as in assembly of complex parts, manufacturing tasks and handling objects. A unified dynamic control method, which is divided into three modes, namely, independent mode, dependent mode, and half dependent mode, is proposed for a redundant dual arm robot with focus on the movement and force of the desired task being operated. Attention is devoted to develop a unified formulation of the above three modes. In addition, a closed form of inverse kinematic solution instead of numerical integration approach is proposed with the aim to guarantee position accuracy. Different from traditional dynamic controllers, where the independent redundancy resolution is obtained based on particular velocity or acceleration levels, here the two dynamic controllers are improved by combining a closed form of inverse kinematic solution with velocity and acceleration levels. Furthermore, the theoretical results of the proposed control method are validated by simulations and experiments.

关键词： unified control method dual arm robot dynamic constraints intemal force

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimal Flight Paths for Engine-Out Emergency Landing

Optimal Flight Paths for Engine-Out Emergency Landing

引用

第24届中国控制与决策会议

作者： Avishai Adler Aharon Bar-Gill Nahum Shimkin Department of Electrical Engineering Technion Haifa 32000 Israel Department of Aerospace Engineering Technion Haifa 32000 Israel

Loss of engine power constitutes a major emergency situation in General Aviation （GA） aircraft, requiring the location of a safe-to-land strip within reach, and thereupon planning and executing an effective gliding path towards it. These critical tasks are currently entrusted with the pilot. In recent years, technological advances in avionics （GPS, GIS and computing capabilities） have reached the GA cockpit - clearing the way for safety enhancements that utilize these resources. In this paper we consider the problem of 3D trajectory planning for an engine-cut GA aircraft towards a specified airstrip, while avoiding natural or man-made obstacles. We emphasize energy efficiency, which allows the aircraft to maximally extend its reach. To that end we employ a dynamic model of the aircraft, which leads to a six- dimensional optimal control problem. We propose a computation approach that is aimed at approximating the globally optimal solution in real-time. Our approach is based on motion primitives, or basic maneuvers, which are parameterized flight segments of specified shapes which are locally optimized for energy efficiency. These basic maneuvers enable a coarse discretization of the search space, and the planning problem is reduced to a graph-search problem of tractable size which may be efficiently solved using an optimal graph search algorithm. Important computational enhancements include the use of pre-compiled basic maneuver dictionaries. The effectiveness of the proposed solution is demonstrated via simulation results.

关键词： Aircraft trajectory planning dynamic constraints motion primitives engine-off emergency

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Double Arc Path Tracking Control of Driverless Vehicle Based on Time Delay dynamic Prediction

Double Arc Path Tracking Control of Driverless Vehicle Based...

引用

第37届中国控制会议

作者： Yiqun Zou Lu Li Xiafei Tang Jingtian Ye Lingli Yu School of Information Science and Engineering Central South University School of Electrical and Information Engineering Changsha University of Science and Technology

In the process of path tracking, the pure pursuit（PP） algorithm can easily cause the vehicle to oscillate under the scene of lane changing and turning, and produce larger heading error and lateral position error. To solve these problems, a double circular arc tracking algorithm is proposed in this paper. The algorithm uses the preview point, the position and posture of the vehicle to get the equal radius of circular arcs that can ensure smooth transition of the vehicle at the critical turning point when it changes the lane or makes the turns. Numerical experiments show that the algorithm can guarantee the vehicle to track the desired path smoothly and accurately.

关键词： Double arc dynamic constraints Front wheel declination dynamic delay Path tracking

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：