Jun Gu

Jun Gu

Auto-generated profile, based on publicly available information

Jun Gu

China North Artificial Intelligence & Innovation Research Institute Beijing China

Research Focus & Metrics

Academic Career Length

33Years (1994-Present)

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

Representative Publications

View All Publications

13 November 2002
Verified
Conference Paper
Closed access
WHWenting Hou
Wenting Hou
HYHong Yu
Hong Yu
XHXianlong Hong
Xianlong Hong
YCYici Cai
Yici Cai
WWWeimin Wu
Weimin Wu
WKW.H. Kao
W.H. Kao
We describe a new congestion-driven placement based on cell inflation. In our approach, we have used the method of probability-estimation to evaluate the routing of nets. We also take use of the strategy of cell inflation to eliminate the routing congestion. Further reduction in congestion is obtained by the scheme of cell moving. We have tested our algorithm on a set of sample circuits from American industry and the results obtained have shown great improvement of routability.

25 June 2003
Verified
Conference Paper
Closed access
JTJing Tong
Jing Tong
XHXian-Long Hong
Xian-Long Hong
HBHai-Yun Bao
Hai-Yun Bao
YCYi-Ci Cai
Yi-Ci Cai
JXJing-Yu Xu
Jing-Yu Xu
JGJun Gu
Jun Gu

13 November 2002
Verified
Conference Paper
Closed access
SDSheqin Dong
Sheqin Dong
XHXianlong Hong
Xianlong Hong
YWYouliang Wu
Youliang Wu
YLYizhou Lin
Yizhou Lin
JGJun Gu
Jun Gu
A deterministic algorithm for VLSI block placement was developed through human's accumulated experience in solving “packing” problem. Rectangle packing problem is just a simplified case of the polygon-shape stone plate packing problem that the ancient masons needed to face. Several “packing” principles derived from the so-called “less flexibility first” experience of the masons. A k-d tree data structure is used for manipulating the packed rectangles under the derived packing principles. Experiment results demonstrate that the algorithm is effective and promising in building block layout application

1 January 2026 in IET Intelligent Transport Systems
Verified
Journal Article
Open access
JGJun Gu
Jun Gu
YWYang Wang
Yang Wang
SLShengfei Li
Shengfei Li
ZLZiang Lin
Ziang Lin
NZNaisi Zhang
Naisi Zhang
XSXiangyang Su
Xiangyang Su
Deep reinforcement learning (DRL) based autonomous driving vehicles (ADVs) has attracted numerous researchers in recent years. Many DRL‐based urban traffic scenarios ADVs have been studied. However, there still remains a notable gap in the literature regarding the incorporation of dynamic passenger preferences. For instance, the passenger dynamic preferences between safety, comfort and efficiency change as traffic changes. Existing researches often overlook the dynamic nature of passenger preferences, which can significantly impact the overall passenger experience. Therefore, to improve driving personality and efficiency, in this paper, we deal with the challenge of incorporating dynamic passenger preferences into ADVs using DRL. We propose an innovative DRL method that first leverages prior knowledge to reduce the preference space which can speed up the training process. Then we apply homotopy optimization to make DRL optimization problem gradually transition from non‐preference to dynamic preference. We validate our approach utilizing a simulated merge environment. Experimental results show that our approach has faster convergence and better performance when dealing with dynamic preference.

8 December 2023
Verified
Conference Paper
Closed access
XYXingang Yang
Xingang Yang
YWYuqi Wen
Yuqi Wen
JGJun Gu
Jun Gu
LCLiang Cao
Liang Cao
Nowadays, with the continuous increase in the proportion of renewable energy sources in the power grid, black start, as a critical technology for system restoration, is receiving increasingly more attention. Black start procedures play a crucial role in mitigating the risk of major blackouts in modern power systems relying on new energy sources. Utilizing inverters with self-synchronous voltage source control can significantly enhance the speed of system recovery. During the black start process, units with self-starting ability are susceptible to experiencing a significant inrush current within the self-starting process after the power failure. In this paper, a voltage control mode with zero lifting voltage is employed to mitigate the inrush current. Also, a strategy to change the reference value of active power of inverters is also proposed to solve the mismatch problems of the real-time power during the zero-lift boost of the voltage. All theoretical analyses and the effectiveness of the control mode and control strategy are verified by time simulations.