Institution
National University of Defense Technology
Education•Changsha, China•
About: National University of Defense Technology is a education organization based out in Changsha, China. It is known for research contribution in the topics: Computer science & Radar. The organization has 39430 authors who have published 40181 publications receiving 358979 citations. The organization is also known as: Guófáng Kēxuéjìshù Dàxué & NUDT.
Topics: Computer science, Radar, Laser, Synthetic aperture radar, Fiber laser
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this article, the geometric structure of unit dual quaternions and its approximate logarithmic mapping are investigated and a generalized proportional control law with unit dual quadratic descriptors is developed.
81 citations
••
TL;DR: All three-photon entangled states are used to transmit the secret message except those chosen for eavesdropping check and the present scheme has a high source capacity because Greenberger–Horne–Zeilinger state forms a large Hilbert space.
81 citations
••
TL;DR: The concept of an Internet-based Virtual Computing Environment (iVCE), which aims to provide Cloud services by a dynamic combination of data centers and other multi-scale computing resources on the Internet, is introduced.
81 citations
••
TL;DR: A data-driven longitudinal control method is presented for ALVs to obtain near-optimal control policies which adaptively tune the fuel/brake control signals to track different speeds and illustrate the superiority of the PBAC-based self-learning controller over conventional longitudinal control methods such as proportional-integral control and learning-based PI control.
Abstract: This paper presents a parameterized batch reinforcement learning algorithm for near-optimal longitudinal control of autonomous land vehicles (ALVs). The proposed approach uses an actor-critic architecture, where parameterized feature vectors based on kernels are learned from collected samples for approximating the value functions and policies. One difference between the parameterized batch actor-critic (PBAC) algorithm and previous actor-critic learning approaches is that the critic and actor in PBAC share the same linear features, which has been theoretically proved to be a beneficial property for the convergence of actor-critic learning approaches. In order to obtain better learning efficiency, least-squares-based batch updating rules are designed for the critic and actor, respectively. Based on the PBAC learning algorithm, a data-driven longitudinal control method is presented for ALVs to obtain near-optimal control policies which adaptively tune the fuel/brake control signals to track different speeds. A multiobjective reward function is designed so that both tracking precision and driving smoothness are considered. Extensive experiments were conducted on a real ALV platform while driving on flat, slippery, sloping, and bumpy roads. The experimental results illustrate the superiority of the PBAC-based self-learning controller over conventional longitudinal control methods such as proportional-integral (PI) control and learning-based PI control.
81 citations
••
TL;DR: In this paper, a new result about permutation binomials and several new classes of permutation trinomials are presented, some of which are generalizations of known ones.
81 citations
Authors
Showing all 39659 results
Name | H-index | Papers | Citations |
---|---|---|---|
Rui Zhang | 151 | 2625 | 107917 |
Jian Li | 133 | 2863 | 87131 |
Chi Lin | 125 | 1313 | 102710 |
Wei Xu | 103 | 1492 | 49624 |
Lei Liu | 98 | 2041 | 51163 |
Xiang Li | 97 | 1472 | 42301 |
Chang Liu | 97 | 1099 | 39573 |
Jian Huang | 97 | 1189 | 40362 |
Tao Wang | 97 | 2720 | 55280 |
Wei Liu | 96 | 1538 | 42459 |
Jian Chen | 96 | 1718 | 52917 |
Wei Wang | 95 | 3544 | 59660 |
Peng Li | 95 | 1548 | 45198 |
Jianhong Wu | 93 | 726 | 36427 |
Jianhua Zhang | 92 | 415 | 28085 |