Sheng ru Ju

Sheng ru Ju


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 April 2020
Verified
Conference Paper
Closed access
ZCZimin Cai
Zimin Cai
SJSheng ru Ju
Sheng ru Ju
YZYunxiu Zeng
Yunxiu Zeng
XXXu Xie
Xu Xie
Deceptive path planning is an important part of military simulation, which is mainly applied to the static environment now. However, it is very necessary to consider how to generate the deceptive path in dynamic environment because elements in the real battlefield change constantly. This paper proposes a phased planning method, which combines static planning results with dynamic data, so that the attacker can eventually find a feasible deceptive path in dynamic environment, which can avoid the moving obstacles. Some simulation experiments prove that the method is really useful for planning deceptive paths in dynamic environment.

5 August 2020
Verified
Conference Paper
Open access
JZJinhui Zhao
Jinhui Zhao
SJSheng ru Ju
Sheng ru Ju
XXXu Xie
Xu Xie
YYYanqing Ye
Yanqing Ye
Aiming at the characteristics of multivariate time series, such as high dimensionality, the strong correlation of variables, and unequal length of sequences, this paper proposes the MSN-WDTW similarity measure for multivariate time series based on multi-dimensional segmentation norm representation and weighted dynamic time warping. First, a hierarchical detection algorithm is proposed to gradually detect the important points of the multivariate time series, and uniformly segment the sequences through an error rate-based method. On the basis of the obtained segmentation, the Frobenius norm is introduced to uniformly represent each segmentation matrix and its covariance matrix, then the multivariate time series is transformed into a univariate time series. Besides, the weighted dynamic time warping algorithm is used to measure the similarity of the compressed sequences of unequal length. Finally, both the similarity search and nearest neighbor classification experiments are carried out and verify the effectiveness and feasibility of the proposed MSN-WDTW similarity measure for MTS.

8 December 2025 in Drones
Verified
Journal Article
Open access
PDF file
力郑力 郑
力 郑
JZJunjie Zeng
Junjie Zeng
LQLong Qin
Long Qin
SJSheng ru Ju
Sheng ru Ju
Autonomous multi-UAV formation control in cluttered urban environments remains challenging due to partial observability, dense and dynamic obstacles, and conflicting objectives (task efficiency, energy use, and safety). Yet many MARL-based approaches still collapse vector-valued objectives into a single hand-tuned reward and lack selective information fusion, leading to brittle trade-offs and poor scalability in urban clutter. We introduce a model-agnostic MARL framework—instantiated on MADDPG for concreteness—that augments a CTDE backbone with three lightweight attention modules (self, inter-agent, and entity) for selective information fusion, and a Pareto optimization module that maintains a compact archive of non-dominated policies to adaptively guide objective trade-offs using simple, interpretable rewards rather than fragile weightings. On city-scale navigation tasks, the approach improves final team success by 13–27 percentage points for N = 2–5 while simultaneously reducing collisions, tightening formation, and lowering control effort. These gains require no algorithm-specific tuning and hold consistently across the tested team sizes (N = 2–5), underscoring a stronger safety–efficiency trade-off and robust applicability in cluttered, partially observable settings.

30 November 2024
Verified
Book Chapter
Closed access
PDF file
DCDongdong Chen
Dongdong Chen
SJSheng ru Ju
Sheng ru Ju
XLXiaoyang Liu
Xiaoyang Liu
JLJiyuan Liu
Jiyuan Liu
ZJZhang Jun
Zhang Jun
SQSihang Qiu
Sihang Qiu

16 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
力郑力 郑
力 郑
JZJunjie Zeng
Junjie Zeng
LQLong Qin
Long Qin
SJSheng ru Ju
Sheng ru Ju
Autonomous multi-UAV formation control in cluttered urban environments remains challenging due to partial observability, dense and dynamic obstacles, and conflicting objectives (task efficiency, energy use, and safety). Yet many MARL-based approaches still collapse vector-valued objectives into a single hand-tuned reward and lack selective information fusion, leading to brittle trade-offs and poor scalability in urban clutter. We introduce a model-agnostic MARL framework—instantiated on MADDPG for concreteness—that augments a CTDE backbone with three lightweight attention modules (self, inter-agent, and entity) for selective information fusion, and a Pareto optimization module that maintains a compact archive of non-dominated policies to adaptively guide objective tradeoffs using simple, interpretable rewards rather than fragile weightings. On city-scale navigation tasks, the approach improves final team success by 13–27 percentage points for N=2–5 while simultaneously reducing collisions, tightening formation, and lowering control effort. These gains require no algorithmspecific tuning and scale smoothly beyond two agents, underscoring a stronger safety–efficiency trade-off and robust applicability in cluttered, partially observable settings.

15 May 2026 in Neural Networks
Verified
Journal Article
Closed access
XLXiaoyang Liu
Xiaoyang Liu
XXXu Xie
Xu Xie
BYBanghu Yin
Banghu Yin
SJSheng ru Ju
Sheng ru Ju