Zhiwei Hou

Dr. Zhiwei Hou

School of Systems Science and Engineering, Sun Yat-Sen University, Guangzhou 510275, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 March 2020 in Aerospace Science and Technology
Verified
Journal Article
Closed access
Zhiwei HouZhiwei Hou
Zhiwei Hou
PLPeng Lu
Peng Lu
ZTZhangjie Tu
Zhangjie Tu

1 October 2019 in Aerospace Science and Technology
Verified
Journal Article
Closed access
Zhiwei HouZhiwei Hou
Zhiwei Hou
YYYe Yang
Ye Yang
LLLei Liu
Lei Liu
YWYongji Wang
Yongji Wang

11 January 2024 in Drones
Verified
Journal Article
Open access
PDF file
XZXiao ru Zhao
Xiao ru Zhao
RYRennong Yang
Rennong Yang
LZLiangsheng Zhong
Liangsheng Zhong
Zhiwei HouZhiwei Hou
Zhiwei Hou
Dedicated to meeting the growing demand for multi-agent collaboration in complex scenarios, this paper introduces a parameter-sharing off-policy multi-agent path planning and the following approach. Current multi-agent path planning predominantly relies on grid-based maps, whereas our proposed approach utilizes laser scan data as input, providing a closer simulation of real-world applications. In this approach, the unmanned aerial vehicle (UAV) uses the soft actor–critic (SAC) algorithm as a planner and trains its policy to converge. This policy enables end-to-end processing of laser scan data, guiding the UAV to avoid obstacles and reach the goal. At the same time, the planner incorporates paths generated by a sampling-based method as following points. The following points are continuously updated as the UAV progresses. Multi-UAV path planning tasks are facilitated, and policy convergence is accelerated through sharing experiences among agents. To address the challenge of UAVs that are initially stationary and overly cautious near the goal, a reward function is designed to encourage UAV movement. Additionally, a multi-UAV simulation environment is established to simulate real-world UAV scenarios to support training and validation of the proposed approach. The simulation results highlight the effectiveness of the presented approach in both the training process and task performance. The presented algorithm achieves an 80% success rate to guarantee that three UAVs reach the goal points.

27 April 2016 in IEEE Transactions on Control Systems Technology
Verified
Journal Article
Closed access
Zhiwei HouZhiwei Hou
Zhiwei Hou
LLLei Liu
Lei Liu
YWYongji Wang
Yongji Wang
Jian HuangJian Huang
Jian Huang
HFHuijin Fan
Huijin Fan
In this paper, a new guidance law based on the variable structure system theory and an associated model-free target acceleration estimator are proposed. The composite guidance-estimation law is designed to intercept constant-velocity and maneuvering targets by missiles at a desired terminal impact angle. Specifically, the scenario of intercepting the targets with speed-disadvantaged missiles, which has not been studied in detail in the literature available, is considered in this paper. A multiple solution problem for the terminal impact angle and a final line-of-sight angle is clarified in this paper. To solve this problem, the generalized variable structure theory is used and an additional sliding mode surface is introduced in the proposed guidance law, by which missiles can reach a wider range of the final impact angle. In addition, the nonsingular terminal sliding mode control method is applied so that the states of the guidance dynamic system are finite time convergent. In order to intercept maneuvering targets, a Kriging-based model-free finite impulse response filter is employed. Based on this filter, this paper puts forward some improvements, including a data preprocessing method and a parameter offline tuning method by the simulated annealing algorithm. In this way, a model-free target acceleration estimator with strong practicality in engineering is proposed. The stability condition of the proposed composite guidance-estimation law is obtained via the Lyapunov theorem. Finally, simulation results in different initial intercepting scenarios are presented to validate the advantage of the proposed guidance law and target acceleration estimator.

1 December 2017 in Aerospace Science and Technology
Verified
Journal Article
Closed access
Zhiwei HouZhiwei Hou
Zhiwei Hou
LLLei Liu
Lei Liu
YWYongji Wang
Yongji Wang