Zhenqiang Mi

Prof. Zhenqiang Mi


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
23 May 2018 in IEEE Systems Journal
Verified
Journal Article
Closed access
YGYu Guo
Yu Guo
ZMZhenqiang Mi
Zhenqiang Mi
YYYang Yang
Yang Yang
MOMohammad S. Obaidat
Mohammad S. Obaidat
Cloud robotic network (CRN) normally contains multiple mobile robots and a cloud computing center providing feasible solutions for many multiagent applications. One of the most critical issues in CRN and its application is how to effectively assign/offload computational tasks. This paper presents a novel energy sensitive task offloading strategy to answer the question particularly for CRN. First, we propose a novel strategy to offload tasks to cloud center, as well as other robots to greatly improve the computing ability and execution efficiency. Second, an energy sensitive model is developed to balance the energy level of the robots and eventually prolong the lifetime of the robot network. A modified genetic algorithm (GA), named energy sensitive GA, is finally developed and integrated into the strategy to get the optimized task offloading result as soon as possible, which is critical to most CRN applications. The correctness, efficiency, and scalability of the proposed strategy are proved with both theoretical analysis and experimental simulations. The evaluation results show that the proposed method can effectively assign tasks and prolong the lifetime of the network to a certain extent.

18 August 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YXYuanyan Xie
Yuanyan Xie
YGYu Guo
Yu Guo
ZMZhenqiang Mi
Zhenqiang Mi
YYYang Yang
Yang Yang
MOMohammad S. Obaidat
Mohammad S. Obaidat
Instance segmentation exploits the potential of Internet of Things (IoT) devices to perceive environmental semantic information and achieve complex interactions with the physical world. However, IoT devices usually have limited computing and storage resources and cannot afford the intensive computational costs of instance segmentation networks. This article proposes an edge-assisted instance segmentation method for resource-limited IoT devices; it selectively offloads some computation-intensive tasks from IoT devices to edge servers to accelerate the inference processes of instance segmentation networks. To reduce the communication cost caused by computation offloading, a data compression method is proposed to adaptively adjust the downsampling interval based on an attention mechanism. Considering the susceptibility of the computation offloading scheme to network conditions, an adaptive computation offloading strategy that can jointly optimize the offloading point and the data compression ratio is proposed so that the edge-assisted instance segmentation can meet the preset latency requirements while achieving maximal accuracy under volatile network conditions. Extensive experiments are conducted to verify the feasibility and efficiency of our method. The experimental results show that our method induces less latency than existing instance segmentation methods with a slight drop in accuracy.

1 June 2019 in Ad Hoc Networks
Verified
Journal Article
Closed access
YGYu Guo
Yu Guo
YZYun Zhang
Yun Zhang
ZMZhenqiang Mi
Zhenqiang Mi
YYYang Yang
Yang Yang
MOMohammad S. Obaidat
Mohammad S. Obaidat

16 April 2018 in International Journal of Communication Systems
Verified
Journal Article
Closed access
PDF file
MFMingzhe Fang
Mingzhe Fang
DWDandan Wang
Dandan Wang
ZMZhenqiang Mi
Zhenqiang Mi
MOMohammad S. Obaidat
Mohammad S. Obaidat

1 June 2011
Verified
Conference Paper
Closed access
ZMZhenqiang Mi
Zhenqiang Mi
YYYang Yang
Yang Yang
Restoring connectivity subjected to the failure of mobile node(s) is an important research challenge in mobile ad hoc networks. To achieve this objective, a Connectivity Restoration Strategy (CRS) is developed, aiming at restoring the connectivity of mobile network whenever it is partitioned from multiple simultaneous node failures. The proposed strategy is fully distributed and requires only local information of k-hop neighbors. Furthermore, with respect to the fact that connectivity may not be restorable without accessing network-wide information of neighbor status, an extensive investigation of connectivity restorability is conducted through computer simulations.

24 June 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YGYu Guo
Yu Guo
JSJinsheng Sun
Jinsheng Sun
RZRuiheng Zhang
Ruiheng Zhang
ZJZhiqi Jiang
Zhiqi Jiang
ZMZhenqiang Mi
Zhenqiang Mi
MOMohammad S. Obaidat
Mohammad S. Obaidat
Efficiently navigating to a specific kind of objects in an unknown environment is an important and challenging research topic in Embodied AI. Existing methods, such as end-to-end learning ones and modular ones still struggle at this task as they have poor efficiency, interpretability and/or generalization. This paper proposes an object-driven navigation strategy for robots based on active perception and semantic association. Specifically, this strategy enables robots to explore the environment and complete object-driven navigation tasks by endowing them with the ability to explore areas, infer associations, remember scenes, continue navigation, and so on. On this basis, this paper designs a semantic association model based on a graph convolution network using rich information hidden in the environment, including geometric and semantic information, to dynamically predict the association between objects, providing more accurate and effective prior knowledge for object-driven navigation. Experimental results prove that the proposed strategy can help robots better perceive and understand the environment and it is superior to similar strategies in terms of success rate and navigation efficiency.