Jun Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jun Zhou has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jianguo Guo
Affiliation The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
4 shared publications - Jianguo Guo
Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xi’an 710072, China
3 shared publications - Xiaodong Lu
School of Astronautics, Northwestern Polytechnical University,Xian,China,710072
2 shared publications - Bin Zhao
Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xi’an 710072, China
1 shared publication - Cheng Cheng
Northwestern Polytechnical University
1 shared publication - Dong Sun
Department of Biomedical Engineering, City University of Hong Kong, Kowloon, Hong Kong, China
1 shared publication
Latest Publications
- Open Access
SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation
6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry information, it is still non-trivial how to fully benefit from the two cross-modal data. From the simple yet new observation, when an object rotates, its semantic label is invariant to the pose while its keypoint offset direction is variant to the pose. To this end, we present SO(3)-Pose, a new representation learning network to explore SO(3)-equivariant and SO(3)-invariant features from the depth channel for pose estimation. The SO(3)-invariant features facilitate to learn more distinctive representations for segmenting objects with similar appearance from RGB channels. The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel. Unlike most of existing pose estimation methods, our SO(3)-Pose not only implements the information communication between the RGB and depth channels, but also naturally absorbs the SO(3)-equivariance geometry knowledge from depth images, leading to better appearance and geometry representation learning. Comprehensive experiments show that our method achieves the state-of-the-art performance on three benchmarks.
Open AccessSO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation
6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry information, it is still non-trivial how to fully benefit from the two cross-modal data. From the simple yet new observation, when an object rotates, its semantic label is invariant to the pose while its keypoint offset direction is variant to the pose. To this end, we present SO(3)-Pose, a new representation learning network to explore SO(3)-equivariant and SO(3)-invariant features from the depth channel for pose estimation. The SO(3)-invariant features facilitate to learn more distinctive representations for segmenting objects with similar appearance from RGB channels. The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel. Unlike most of existing pose estimation methods, our SO(3)-Pose not only implements the information communication between the RGB and depth channels, but also naturally absorbs the SO(3)-equivariance geometry knowledge from depth images, leading to better appearance and geometry representation learning. Comprehensive experiments show that our method achieves the state-of-the-art performance on three benchmarks.
- Open Access
- 1 December 2019
- Published by EDP Sciences in Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
- Vol. 37 (6) , 1120-1128
Iterative Learning Control Combination with Adaptive Sliding Mode Technique for a Hypersonic Vehicle
Aiming at the complicated nonlinearities, high uncertainties and strong coupling of hypersonic vehicle, a new adaptive iterative learning control method is put forward. The proposed controller combined iterative learning control with sliding mode control. Firstly, a nonlinear design model for the attitude control is established according to the attitude motion equations of hypersonic vehicle. With regard to a class of nonlinear system, a new iterative learning control combination with sliding mode control is proposed and then applied to the nonlinear design model. Finally, Lyapunov-like function method is used to prove the boundedness of all signals of the closed-loop system and the convergence of the tracking errors to zero over iterations. Simulation results are provided to show the effectiveness and robustness of the proposed control scheme compared with traditional sliding mode control. Furthermore, it also possesses stronger robustness against uncertainties and disturbances. 针对高超声速飞行器再入过程中的强耦合和干扰所带来的非匹配不确定控制问题,提出一种新型自适应迭代学习控制系统的设计方法。研究结合采用先进控制方法与迭代学习控制策略。首先给出面向控制的高超声速飞行器姿态模型。然后针对一类非线性系统,提出一种结合滑模控制的新型迭代学习控制系统设计方法,并将其应用到所提出的面向控制的姿态模型。最后应用Lyapunov泛函来证明闭环系统跟踪误差的收敛性和变量的有界性。仿真展示所提方法能使飞行器快速稳定地跟踪指令,对比传统滑模控制说明本方法具有针对气动不确定项和干扰项的强鲁棒性。
- 1 December 2019
- Published by EDP Sciences in Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
- Vol. 37 (6) , 1120-1128
Open AccessIterative Learning Control Combination with Adaptive Sliding Mode Technique for a Hypersonic Vehicle
Aiming at the complicated nonlinearities, high uncertainties and strong coupling of hypersonic vehicle, a new adaptive iterative learning control method is put forward. The proposed controller combined iterative learning control with sliding mode control. Firstly, a nonlinear design model for the attitude control is established according to the attitude motion equations of hypersonic vehicle. With regard to a class of nonlinear system, a new iterative learning control combination with sliding mode control is proposed and then applied to the nonlinear design model. Finally, Lyapunov-like function method is used to prove the boundedness of all signals of the closed-loop system and the convergence of the tracking errors to zero over iterations. Simulation results are provided to show the effectiveness and robustness of the proposed control scheme compared with traditional sliding mode control. Furthermore, it also possesses stronger robustness against uncertainties and disturbances. 针对高超声速飞行器再入过程中的强耦合和干扰所带来的非匹配不确定控制问题,提出一种新型自适应迭代学习控制系统的设计方法。研究结合采用先进控制方法与迭代学习控制策略。首先给出面向控制的高超声速飞行器姿态模型。然后针对一类非线性系统,提出一种结合滑模控制的新型迭代学习控制系统设计方法,并将其应用到所提出的面向控制的姿态模型。最后应用Lyapunov泛函来证明闭环系统跟踪误差的收敛性和变量的有界性。仿真展示所提方法能使飞行器快速稳定地跟踪指令,对比传统滑模控制说明本方法具有针对气动不确定项和干扰项的强鲁棒性。
- Open Access
- 5 August 2018
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2018, 1-10
New Integrated Guidance and Control of Homing Missiles with an Impact Angle against a Ground Target
A new integrated guidance and control (IGC) law is investigated for a homing missile with an impact angle against a ground target. Firstly, a control-oriented model with impact angle error of the IGC system in the pitch plane is formulated by linear coordinate transformation according to the motion kinematics and missile dynamics model. Secondly, an IGC law is proposed to satisfy the impact angle constraint and to improve the rapidity of the guidance and control system by combining the sliding mode control method and nonlinear extended disturbance observer technique. Thirdly, stability of the closed-loop guidance and control system is proven based on the Lyapunov stability theory, and the relationship between the accuracy of the impact angle and the estimate errors of nonlinear disturbances is derived from stability of the sliding mode. Finally, simulation results confirm that the proposed IGC law can improve the performance of the missile guidance and control system against a ground target.
- 5 August 2018
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2018, 1-10
Open AccessNew Integrated Guidance and Control of Homing Missiles with an Impact Angle against a Ground Target
A new integrated guidance and control (IGC) law is investigated for a homing missile with an impact angle against a ground target. Firstly, a control-oriented model with impact angle error of the IGC system in the pitch plane is formulated by linear coordinate transformation according to the motion kinematics and missile dynamics model. Secondly, an IGC law is proposed to satisfy the impact angle constraint and to improve the rapidity of the guidance and control system by combining the sliding mode control method and nonlinear extended disturbance observer technique. Thirdly, stability of the closed-loop guidance and control system is proven based on the Lyapunov stability theory, and the relationship between the accuracy of the impact angle and the estimate errors of nonlinear disturbances is derived from stability of the sliding mode. Finally, simulation results confirm that the proposed IGC law can improve the performance of the missile guidance and control system against a ground target.
- 5 July 2018
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 41 (5) , 1301-1312
Model reference adaptive attitude control for near space hypersonic vehicle with mismatched uncertainties
In this paper, a new model reference adaptive attitude control based on backstepping approach is presented for near space hypersonic vehicle with mismatched uncertainties. Firstly, the attitude dynamic model of near space hypersonic vehicle is divided into two control loops, which is composed of an attitude angle control loop and an attitude angular rate control loop. Secondly, a novel model reference adaptive attitude control approach is proposed by introducing reference model to avoid the calculating expansion problem in backstepping technique. Meanwhile, the reference models for every loop are independently designed to improve the tracking performance. The stability of attitude control system is strictly proven by using Lyapunov stability theory. Finally, the simulation results demonstrate that the attitude control system by applying the proposed method has good stability, dynamic property and strong robustness in the presence of input constraints and parameters perturbation.
- 5 July 2018
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 41 (5) , 1301-1312
Model reference adaptive attitude control for near space hypersonic vehicle with mismatched uncertainties
In this paper, a new model reference adaptive attitude control based on backstepping approach is presented for near space hypersonic vehicle with mismatched uncertainties. Firstly, the attitude dynamic model of near space hypersonic vehicle is divided into two control loops, which is composed of an attitude angle control loop and an attitude angular rate control loop. Secondly, a novel model reference adaptive attitude control approach is proposed by introducing reference model to avoid the calculating expansion problem in backstepping technique. Meanwhile, the reference models for every loop are independently designed to improve the tracking performance. The stability of attitude control system is strictly proven by using Lyapunov stability theory. Finally, the simulation results demonstrate that the attitude control system by applying the proposed method has good stability, dynamic property and strong robustness in the presence of input constraints and parameters perturbation.
- Open Access
- 21 February 2018
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2018, 1-19
Nonlinear Disturbance Observer-Based Adaptive Sliding Mode Control for a Generic Hypersonic Vehicle
In this paper, a new adaptive sliding mode control method is presented for the longitudinal model of a generic hypersonic vehicle subject to uncertainties and external disturbance. Firstly, an oriented-control model with mismatched uncertainties is built for a generic hypersonic vehicle. Secondly, the back-stepping technique is introduced to design a sliding mode controller with an adaptive law to adapt to the disturbance and uncertainty. Thirdly, a set of nonlinear disturbance observers are designed to estimate the lumped disturbance and compensate the sliding mode controller, and the stability of the proposed controller is analyzed by utilizing Lyapunov stability theory. Finally, simulation results show that the effectiveness of the proposed controller is validated by the nonlinear model and the proposed method exhibits promising robustness to mismatched uncertainties.
- 21 February 2018
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2018, 1-19
Open AccessNonlinear Disturbance Observer-Based Adaptive Sliding Mode Control for a Generic Hypersonic Vehicle
In this paper, a new adaptive sliding mode control method is presented for the longitudinal model of a generic hypersonic vehicle subject to uncertainties and external disturbance. Firstly, an oriented-control model with mismatched uncertainties is built for a generic hypersonic vehicle. Secondly, the back-stepping technique is introduced to design a sliding mode controller with an adaptive law to adapt to the disturbance and uncertainty. Thirdly, a set of nonlinear disturbance observers are designed to estimate the lumped disturbance and compensate the sliding mode controller, and the stability of the proposed controller is analyzed by utilizing Lyapunov stability theory. Finally, simulation results show that the effectiveness of the proposed controller is validated by the nonlinear model and the proposed method exhibits promising robustness to mismatched uncertainties.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4876-4880
Drag free control system design based on the relative motion description
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4876-4880
Drag free control system design based on the relative motion description
- Open Access
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Strictly Finite‐Time‐Convergent Missile Guidance Law Based on Adaptive‐Gain Observer
In the absence of the upper bound of time‐varying target acceleration, the finite‐time‐convergent guidance (FTCG) problem for missile is addressed in this paper. Firstly, a novel adaptive finite‐time disturbance observer (AFDO) is developed based on adaptive‐gain super twisting (ASTW) algorithm to estimate the unknown target acceleration. Subsequently, a new FTCG law is proposed by using the output of AFDO. The newly proposed FTCG law has several advantages over existing FTCG laws. First, for time‐varying target acceleration, the proposed method can strictly guarantee the trajectory of the closed‐loop system is driven onto the sliding surface rather than a neighbourhood of sliding surface in the extended‐state‐observer‐based FTCG (ESOFTCG) law. Second, the proposed method requires no upper bound information on the target acceleration. Third, the chattering problem in the conventional FTCG (CFTCG) law is completely avoided in this paper. Simulation result demonstrates the effectiveness of the proposed AFDO and the proposed FTCG law.
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Open AccessStrictly Finite‐Time‐Convergent Missile Guidance Law Based on Adaptive‐Gain Observer
In the absence of the upper bound of time‐varying target acceleration, the finite‐time‐convergent guidance (FTCG) problem for missile is addressed in this paper. Firstly, a novel adaptive finite‐time disturbance observer (AFDO) is developed based on adaptive‐gain super twisting (ASTW) algorithm to estimate the unknown target acceleration. Subsequently, a new FTCG law is proposed by using the output of AFDO. The newly proposed FTCG law has several advantages over existing FTCG laws. First, for time‐varying target acceleration, the proposed method can strictly guarantee the trajectory of the closed‐loop system is driven onto the sliding surface rather than a neighbourhood of sliding surface in the extended‐state‐observer‐based FTCG (ESOFTCG) law. Second, the proposed method requires no upper bound information on the target acceleration. Third, the chattering problem in the conventional FTCG (CFTCG) law is completely avoided in this paper. Simulation result demonstrates the effectiveness of the proposed AFDO and the proposed FTCG law.
- Open Access
- 1 January 2016
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2016, 1-19
Smooth Adaptive Finite Time Guidance Law with Impact Angle Constraints
A smooth guidance law for intercepting a maneuvering target with impact angle constraints is documented based on the nonsingular fast terminal sliding mode control scheme and adaptive control scheme. Different from the traditional adaptive law which is used to estimate the unknown upper bound of the target acceleration, a new adaptive law is proposed to estimate the square of target acceleration bound, which avoids the use of the nonsmooth signum function and therefore ensures the smoothness of the guidance law. The finite time convergence of the guidance system is guaranteed based on the Lyapunov method and the finite time theory. Simulation results indicate that under the proposed guidance law the missile can intercept the target with a better accuracy at a desired impact angle in a shorter time with a completely smooth guidance command compared with the existing adaptive fast terminal sliding mode guidance laws, which shows the superiority of this method.
- 1 January 2016
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2016, 1-19
Open AccessSmooth Adaptive Finite Time Guidance Law with Impact Angle Constraints
A smooth guidance law for intercepting a maneuvering target with impact angle constraints is documented based on the nonsingular fast terminal sliding mode control scheme and adaptive control scheme. Different from the traditional adaptive law which is used to estimate the unknown upper bound of the target acceleration, a new adaptive law is proposed to estimate the square of target acceleration bound, which avoids the use of the nonsmooth signum function and therefore ensures the smoothness of the guidance law. The finite time convergence of the guidance system is guaranteed based on the Lyapunov method and the finite time theory. Simulation results indicate that under the proposed guidance law the missile can intercept the target with a better accuracy at a desired impact angle in a shorter time with a completely smooth guidance command compared with the existing adaptive fast terminal sliding mode guidance laws, which shows the superiority of this method.