Miao Zheng

Miao Zheng

Auto-generated profile, based on publicly available information

Miao Zheng

State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Heilongjiang, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 May 2024 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
HQHuanan Qi
Huanan Qi
Liang DingLiang Ding
Liang Ding
MZMiao Zheng
Miao Zheng
LHLan Huang
Lan Huang
HGHaibo Gao
Haibo Gao
ZDZongquan Deng
Zongquan Deng
Wheeled mobile robots (WMRs) with variable wheelbases are capable of traveling on deformable terrains and handling complex detection tasks. While the variable wheelbase length of WMR allows it to interact with the terrains adaptively, enhancing its mobility, it brings a control challenge. Inspired by the worm's movement of stretching body at different lengths under different environmental resistance, a creeping gait (CG) strategy is proposed in this work to enable the WMR to be controlled in dual modes: wheeled following mode (WFM) and specified length mode (SLM). WFM adjusts the wheelbase's length by the wheels' movements freely to minimize the internal force and torque between wheels. SLM adjusts the wheelbase's length using a proposed fuzzy logic based algorithm to stabilize the body's posture on rough terrain and overcome specific motion challenges, like escaping wheel sinking. A state-adaptive mode-switching controller is then developed using the dwell time approach to smooth the output velocities during the switching phase, and a Lyapunov analysis is performed to verify its stability. According to the results of physical experiments, three-wheeled mobile robot movements with CG enable more precise path following by 37% and faster response by 11% compared to fixed wheelbase movements, and the dwell time approach achieves smoother speed transitions between the modes than the direct switching method, especially when moving from flat to slope terrain.

3 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SLShu Li
Shu Li
Liang DingLiang Ding
Liang Ding
MZMiao Zheng
Miao Zheng
ZLZixuan Liu
Zixuan Liu
XLXinyu Li
Xinyu Li
ZDZongquan Deng
Zongquan Deng
Based on actor-critic neural networks (NNs), an optimal controller is proposed for solving the constrained control problem of an affine nonlinear discrete-time system with disturbances. The actor NNs provide the control signals and the critic NNs work as the performance indicators of the controller. By converting the original state constraints into new input constraints and state constraints, the penalty functions are introduced into the cost function, and then the constrained optimal control problem is transformed into an unconstrained one. Further, the relationship between the optimal control input and worst-case disturbance is obtained using the Game theory. With Lyapunov stability theory, the control signals are ensured to be uniformly ultimately bounded (UUB). Finally, the effectiveness of the control algorithms is tested through a numeral simulation using a third-order dynamic system.

1 January 2022
Verified
Conference Paper
Closed access
LYLong Yan
Long Yan
ZMZheng Miao
Zheng Miao
WZWei Zhang
Wei Zhang
With the development of intelligent agriculture, farm intelligence urgently needs to be improved. In view of the problems that traditional identification methods in pig management are easy to fall off and cause infection, this paper proposes an improved CenterNet pig face detection algorithm. ResNet18 is used as the backbone feature extraction network, dilated conversion is introduced to improve the convolution layer structure of the network, increase the receptive field of the network, and improve the accuracy of network detection. The final experiment shows that this method has strong robustness and stability in various environments, and can complete the target detection quickly and accurately. The detection time is only 27ms, and the average accuracy mAP can reach 93.61%. The algorithm provides technical support for the follow-up research of pig individual recognition.

15 August 2023 in Asian Journal of Control
Verified
Journal Article
Closed access
Liang DingLiang Ding
Liang Ding
MZMiao Zheng
Miao Zheng
SLShu Li
Shu Li
HYHuaiguang Yang
Huaiguang Yang
HGHaibo Gao
Haibo Gao
ZDZongquan Deng
Zongquan Deng