Zhaoqin Peng

Zhaoqin Peng

Auto-generated profile, based on publicly available information

Zhaoqin Peng

School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 December 2013 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
ZPZhaoqin Peng
Zhaoqin Peng
CCChun Cao
Chun Cao
QLQiusheng Liu
Qiusheng Liu
WPWentao Pan
Wentao Pan
Algorithms based on the ground reflex pressure (GRF) signal obtained from a pair of sensing shoes for human walking pattern recognition were investigated. The dimensionality reduction algorithms based on principal component analysis (PCA) and kernel principal component analysis (KPCA) for walking pattern data compression were studied in order to obtain higher recognition speed. Classifiers based on support vector machine (SVM), SVM-PCA, and SVM-KPCA were designed, and the classification performances of these three kinds of algorithms were compared using data collected from a person who was wearing the sensing shoes. Experimental results showed that the algorithm fusing SVM and KPCA had better recognition performance than the other two methods. Experimental outcomes also confirmed that the sensing shoes developed in this paper can be employed for automatically recognizing human walking pattern in unlimited environments which demonstrated the potential application in the control of exoskeleton robots.

1 October 2006
Verified
Conference Paper
Closed access
ZPZhaoqin Peng
Zhaoqin Peng
YFYongling Fu
Yongling Fu
ZTZhiyong Tang
Zhiyong Tang
QHQiang Huang
Qiang Huang
TATaoxiao
Taoxiao
This paper proposed a method of online walking pattern generation based on key parameters of off-line typical walking patterns for humanoid robot. The key parameters include hip parameters, step length, walking cycle and so on. The offline walking pattern generation method is based on ZMP. The design of the system software of humanoid BHR-2 is also described in this paper, in order to ensure the real task can be finished on time, the process of online walking patterns generation is placed outside the processor which used for real-time control. The effectiveness of the proposed method is confirmed by simulations and experiments with our developed humanoid robot with 32 DOF

1 January 2006
Verified
Conference Paper
Closed access
ZTZhiyong Tang
Zhiyong Tang
ZPZhongcai Pei
Zhongcai Pei
ZPZhaoqin Peng
Zhaoqin Peng
ZWZhanlin Wang
Zhanlin Wang
Rotating arm basin was used to do the hydrodynamic performance simulation experiments of model vessel. As an important parts of the rotating arm basin, the simulation platform is one of the primary factors that effect the accuracy of the experimental result. A kind of simulation platform for performance analyses of model vessel was introduced in this paper. Because this system has a strong disturbance torque, a combined control system was presented to overcome the limitation of traditional disturbance observer. The combined controller is based on predictive neural network (PNN), feedforward control and PD control. If the predictive outputs are much different from real outputs, the PD control and feedforward control are important factors, and when the predictive error is small enough, the PNN control plays important role. In order to prove the effectiveness of this controller, simulations have been done

1 January 2006
Verified
Conference Paper
Closed access
ZPZhaoqin Peng
Zhaoqin Peng
YFYongling Fu
Yongling Fu
ZTZhiyong Tang
Zhiyong Tang
QHQiang Huang
Qiang Huang
Stability balance is a very important issue of the motion planning humanoid robot. Theoretically, the motion which has the higher stability is more stable, so how to evaluate the stability is very important in the motion planning for humanoid robot. Some researchers have proposed stability evaluation method based on ZMP, the stability margin is used to evaluate the stability, however these method can just evaluate the stability of one kind of motion which have the same step length, that is to say the stable region should be the same. This paper proposed a new stability evaluation technique which can evaluate the stability between different walking, the stable region of which are different. The effectiveness of the proposed method is confirmed by simulations and experiments with our developed humanoid robot with 32 DOF.