Baofu Fang

Dr. Baofu Fang


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
12 October 2022 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
BFBaofu Fang
Baofu Fang
CZCaiming Zheng
Caiming Zheng
HWHao Wang
Hao Wang
TYTingting Yu
Tingting Yu
In multi-agent reinforcement learning, multi-layer fully connected neural network(MLP) is used for value function approximation, which solves large-scale or continuous space problems. However, it is easy fall into a local optimal and overfitting under partially observed environments. Because each agent lacks the information that plays a key role in decision-making beyond the observation field. Even if communication is allowed, the received informations in communication channel have large noise due to the observations of other agents and strong uncertainty if the agnet's policy is used as the communication information. To tackle this problem, two-stream fused fuzzy deep neural network(2s-FDNN) was proposed to reduce the uncertainty and noise of information in communication channel. It is a parallel structure in which fuzzy inference module reduce the uncertainty of information and deep neural module reduce the noise of information. Then, we presented Fuzzy MA2C which integrate 2s-FDNN into multi-agent deep reinforcement learning to deal with uncertain communication informations for improving the robustness and generalization under partially observed environments. We empirically evaluate our methods in two large-scale traffic signal control environments using SUMO simulator. Results demonstrate that our methods can achieve superior performance against existing reinforcement learning algorithms.

19 May 2016 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Open access
PDF file
HWHao Wang
Hao Wang
YFYuanyuan Fan
Yuanyuan Fan
BFBaofu Fang
Baofu Fang
SDShuanglu Dai
Shuanglu Dai
One of the key issues in gait recognition is how to extract the low dimensional feature. Linear Discriminant Analysis (LDA) is a commonly used method for linear dimension reduction. This paper proposed a generalized LDA based on Euclidean norm (ELDA) for gait recognition. By redefining a better between-class scatter matrix to separate the neighboring samples that overcome the drawbacks existing in the traditional LDA method. Firstly, the contour is unwrapped counterclockwise by the distance from the uppermost pixel to transformed 2D features into 1D. Secondly, we use ELDA to obtain more discriminative feature space. Finally, multi-class Support Vector Machine (SVM) is applied to implement gait classification. Experimental results show that this algorithm achieves better results in terms of accuracy and efficiency than other gait recognition methods at present.

1 March 2020 in International Journal of Advanced Robotic Systems
Verified
Journal Article
Open access
PDF file
BFBaofu Fang
Baofu Fang
ZZZhiqiang Zhan
Zhiqiang Zhan
Visual simultaneous localization and mapping (SLAM) is well-known to be one of the research areas in robotics. There are many challenges in traditional point feature-based approaches, such as insufficient point features, motion jitter, and low localization accuracy in low-texture scenes, which reduce the performance of the algorithms. In this article, we propose an RGB-D SLAM system to handle these situations, which is named Point-Line Fusion (PLF)-SLAM. We utilize both points and line segments throughout the process of our work. Specifically, we present a new line segment extraction method to solve the overlap or branch problem of the line segments, and then a more rigorous screening mechanism is proposed in the line matching section. Instead of minimizing the reprojection error of points, we introduce the reprojection error based on points and lines to get a more accurate tracking pose. In addition, we come up with a solution to handle the jitter frame, which greatly improves tracking success rate and availability of the system. We thoroughly evaluate our system on the Technische Universität München (TUM) RGB-D benchmark and compare it with ORB-SLAM2, presumably the current state-of-the-art solution. The experiments show that our system has better accuracy and robustness compared to the ORB-SLAM2.

12 April 2017 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Closed access
PDF file
BFBaofu Fang
Baofu Fang
QZQuan Zhang
Quan Zhang
HWHao Wang
Hao Wang
XYXiaohui Yuan
Xiaohui Yuan

1 January 2014 in The Scientific World Journal
Verified
Journal Article
Open access
PDF file
BFBaofu Fang
Baofu Fang
LCLu Chen
Lu Chen
HWHao Wang
Hao Wang
SDShuanglu Dai
Shuanglu Dai
QZQiubo Zhong
Qiubo Zhong
Multirobot task allocation is a hot issue in the field of robot research. A new emotional model is used with the self-interested robot, which gives a new way to measure self-interested robots’ individual cooperative willingness in the problem of multirobot task allocation. Emotional cooperation factor is introduced into self-interested robot; it is updated based on emotional attenuation and external stimuli. Then a multirobot pursuit task allocation algorithm is proposed, which is based on emotional cooperation factor. Combined with the two-step auction algorithm recruiting team leaders and team collaborators, set up pursuit teams, and finally use certain strategies to complete the pursuit task. In order to verify the effectiveness of this algorithm, some comparing experiments have been done with the instantaneous greedy optimal auction algorithm; the results of experiments show that the total pursuit time and total team revenue can be optimized by using this algorithm.

19 January 2022 in Sensors
Verified
Journal Article
Open access
PDF file
WDWeizhong Ding
Weizhong Ding
QZQiubo Zhong
Qiubo Zhong
YWYan Wang
Yan Wang
CGChao Guan
Chao Guan
BFBaofu Fang
Baofu Fang
A new positioning algorithm based on RSS measurement is proposed. The algorithm adopts maximum likelihood estimation and semi-definite programming. The received signal strength model is transformed to a non-convex estimator for the positioning of the target using the maximum likelihood estimation. The non-convex estimator is then transformed into a convex estimator by semi-definite programming, and the global minimum of the target location estimation is obtained. This algorithm aims at the L0 known problem and then extends its application to the case of L0 unknown. The simulations and experimental results show that the proposed algorithm has better accuracy than the existing positioning algorithms.