Changyun Wei

Dr. Changyun Wei


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
10 February 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CWChangyun Wei
Changyun Wei
ZJZe Ji
Ze Ji
BCBoliang Cai
Boliang Cai
This paper presents a new Multi-Objective Particle Swarm Optimization (MOPSO) approach to a Cooperative Multi-Robot Task Allocation (CMRTA) problem, where the robots have to minimize the total team cost and, additionally, balance their workloads. We formulate the CMRTA problem as a more complex variant of multiple Travelling Salesman Problems (mTSP) and, in particular, address how to minimize the total travel distance of the entire robot team, as well as how to minimize the highest travel distance of an individual robot. The proposed approach extends the standard single-objective Particle Swarm Optimization (PSO) to cope with the multiple objectives, and its novel feature lies in a Pareto front refinement strategy and a probability-based leader selection strategy. To validate the proposed approach, we first use three benchmark functions to evaluate the performance of finding the true Pareto fronts in comparison with four existing well-known algorithms in continuous spaces. Afterwards, we use six datasets to investigate the task allocation mechanisms in dealing with the CMRTA problem in discrete spaces.

10 March 2016 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
CWChangyun Wei
Changyun Wei
Koen HindriksKoen Hindriks
Koen Hindriks
CJCatholijn M. Jonker
Catholijn M. Jonker

20 August 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Xiaobin XuXiaobin Xu
Xiaobin Xu
FPFenglin Pang
Fenglin Pang
YRYingying Ran
Yingying Ran
YBYonghua Bai
Yonghua Bai
LZLei Zhang
Lei Zhang
MLMinzhou Luo
Minzhou Luo
In order to avoid the problem of inaccurate positioning of single indoor sensor, an adaptive federated Kalman filter (AFKF) algorithm is proposed in this paper. According to the error covariance matrix, residual, trace and other information of each subfilter, the sharing factors of information fusion and distribution in federated Kalman filter are adaptively adjusted. And the fault detector is added to detect extreme abnormal condition. The simulation was performed and the experiment was carried out in indoor environment. The results show that the AFKF is not affected by abnormal signals of the subfilter, and the accuracy compared with other AFKF algorithms is improved by 10.76% and 10.84% in ${X}$ and ${Y}$ directions. And even if the subfilter fails the proposed AFKF can also work normally. All of these indicates the feasibility and effectiveness of the proposed AFKF.

4 September 2022 in Drones
Verified
Journal Article
Open access
PDF file
LWLizhen Wu
Lizhen Wu
CWChang Wang
Chang Wang
PZPengpeng Zhang
Pengpeng Zhang
CWChangyun Wei
Changyun Wei
Autonomous Unmanned Aerial Vehicle (UAV) landing remains a challenge in uncertain environments, e.g., landing on a mobile ground platform such as an Unmanned Ground Vehicle (UGV) without knowing its motion dynamics. A traditional PID (Proportional, Integral, Derivative) controller is a choice for the UAV landing task, but it suffers the problem of manual parameter tuning, which becomes intractable if the initial landing condition changes or the mobile platform keeps moving. In this paper, we design a novel learning-based controller that integrates a standard PID module with a deep reinforcement learning module, which can automatically optimize the PID parameters for velocity control. In addition, corrective feedback based on heuristics of parameter tuning can speed up the learning process compared with traditional DRL algorithms that are typically time-consuming. In addition, the learned policy makes the UAV landing smooth and fast by allowing the UAV to adjust its speed adaptively according to the dynamics of the environment. We demonstrate the effectiveness of the proposed algorithm in a variety of quadrotor UAV landing tasks with both static and dynamic environmental settings.

11 July 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
CWChang Wang
Chang Wang
JWJiaqing Wang
Jiaqing Wang
ZMZhaowei Ma
Zhaowei Ma
MXMingjin Xu
Mingjin Xu
KQKailei Qi
Kailei Qi
CWChangyun Wei
Changyun Wei
Autonomous unmanned aerial vehicle (UAV) landing on a moving unmanned ground vehicle (UGV) remains a challenge as it is difficult for the UAV to track the real-time state of the UGV and adjust its landing policy accordingly. This paper proposes a learning framework for a quadrotor UAV to land on a moving UGV without knowing its motion dynamics. Specifically, the learning framework consists of two main systems: a Landing Vision System (LVS) using deep learning and a Landing Control System (LCS) using deep reinforcement learning. The LVS enables the UAV to recognize and localize the UGV in real time to estimate the relative position and velocity between them. Besides, the location of the UGV is tracked in the field of view of the UAV using consecutive images, alleviating the tracking failure problem. We propose a Memory Consolidated TD3 (MCTD3) algorithm to generate optimal policies to enable precise tracking and landing control of the UAV. In addition, we propose an adaptive COACH (ACOACH) algorithm that allows human intervention in the action space of the UAV to speed up the training process. We demonstrate the effectiveness of the proposed method in both simulation and real-world experiments.

26 September 2024 in Computers in Industry
Verified
Journal Article
Closed access
CWChangyun Wei
Changyun Wei
HHHui Han
Hui Han
YXYu Xia
Yu Xia
ZJZe Ji
Ze Ji