Competition Highlight: Visually-guided Gluing Chaser in “Siemens Cup”

“Siemens Cup” China Intelligent Manufacturing Challenge is one of the important competitions that Zhejiang University Smart Factory Innovation Association participates in every year. In the 2020 “Siemens Cup” China Intelligent Manufacturing Challenge, the Visually-guided Gluing Chaser, designed by three members from the association―REN Yixin, HU Jiayi and CHEN Lu―clinched first prize thanks to their perspicacious marketing analysis and innovative design.This system is designed for respirator masks with immense attention paid to tackling the most difficult and time-consuming gluing process during the outbreak of COVID-19. At present, virtually every mask gluing process is still operated manually in a non-standard manner and only a few factories adopt semi-automatic production lines. Against this backdrop, the team designs the Visually-guided Gluing Chaser to improve the efficiency of the gluing process and reduce human-to-human contact in industrial production in an effort to prevent and control the spread of the novel coronavirus.The Gluing Chaser consists of three parts: intelligent sensing, on-the-fly gluing, and dynamic assembly and sorting. It can apply glue to the external periphery of an object in any shape on the assembly line and use such algorithms as machine vision and trajectory planning to ensure an efficient and accurate gluing process. Furthermore, the gluing action can automatically align itself with the speed of the conveyor belt. After a specified drying time, the robot arm will carry out immediate assembly and sorting. This production line eliminates the need to stop the conveyor and saves 4 to 5 seconds in every step.Meanwhile, the Gluing Chaser can realize the blended production of different mask models, thereby precluding the need for pre-sorting and shortening the process. When changes are made to the product plan or the production environment, it can be quickly adjusted to meet the needs of producing customized respirator masks. In order to achieve market-oriented intelligent manufacturing, the team also develops a big data system for production planning, which can predict the trend of the epidemic in each region and estimate the demand for different types of respiratory masks through modeling, enabling early production and instant response.With the rising demand for robotic equipment in the manufacturing industry and the mounting concern of enterprises about environmental protection and the improvement of the working environment for workers, more intelligent, automatic and flexible gluing technology is in great need in the gluing process. The three students from Zhejiang University Smart Factory Innovation Association detect flaws with the production line and design their own product through their research, which enables them to get to the core of intelligent manufacturing and intelligent factory.Reprinted from:  ZJU Newsroom

MySweet Canteen opens in East Teaching Building 2 on Zijingang Campus

ZJU and Cornell University sign an agreement online

ZJU alumna CHEN Wei receives national honorary title—“the People's Hero”

ZJU jumps in the THE World University Rankings

A special cohort of students set foot on ZJU’s International Campus

Self-driving van delivers packages on Zijingang Campus

Virtual tour around 7 ZJU campuses

Paper on RGB-D SLAM of Dr. ZHANG Yu's group accepted by TPAMI

"RGB-D SLAM in Dynamic Environments Using Point Correlations" (DSLAM), a paper of Dr. ZHANG Yu’s group has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). The work focuses on the simultaneous localization and mapping (SLAM) in dynamic environment. It is the first paper accepted by TPAMI whose first author affiliation is the College of Control Science and Engineering, Zhejiang University. Moreover, it is also the first SLAM paper accepted by TPAMI whose first author affiliation is domestic university or research institution.In this paper, a simultaneous localization and mapping (SLAM) method that eliminates the influence of moving objects in dynamic environments is proposed. This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups. A sparse graph is first created from all map points. In this graph, the vertices represent map points, and each edge represents the correlation between adjacent points. If the relative position between two points remains consistent over time, there is correlation between them, and they are considered to be moving together rigidly. If not, they are considered to have no correlation and to be in separate groups. After the edges between the uncorrelated points are removed, the remaining graph separates the map points of moving objects from the static scene. The largest group is assumed to be the group of reliable static map points. Experimental results demonstrate that robust and accurate performance can be achieved by the proposed SLAM method in both slightly and highly dynamic environments. Compared to other state-of-the-art methods, the proposed method can provide competitive accuracy with good real-time performance.To read the paper:https://ieeexplore.ieee.org/document/9145704Reporter: YU HongxiangEditor: WANG Jing

DMT clinches championship at 2020 iQIYI iCartoonFace Challenge

Under the umbrella of the College of Control Science and Engineering, a partnership between the the College and Alibaba DAMO Academy, a team of Zhejiang University students participated in and won the championship at the 2020 iQIYI iCartoonFace Challenge, an integral part of IJCAI PRICAI 2020.The team representing Zhejiang University was comprised of three students: HE Shuting (BA22), ZHANG Miao (BA21), and ZENG Zhaoyang (BA22). They came in first place in the iCartoonFace Recognition Challenge. This year iQIYI iCartoonFace Challenge attracted about 500 teams in China, such as Shanghai Jiao Tong University, the Chinese Academy of Sciences, the University of Science and Technology of China, Tencent and Dahua Technology.  The DMT team is under the guidance of Dr. LUO Hao, Prof. JIANG Wei and Prof. LIU Xinggao, as well as researchers from Alibaba DAMO Academy. It has been actively engaging in several competitions in the field of computer vision and achieved excellent records.  In the AI City Challenge 2020，DMT team innovatively integrated multi-domain learning and identity mining into vehicle city-Scale multi-Camera re-identification questions and was the third-place winner in the leader board of this track.This January the DMT team also participated in the 1st National Artificial Intelligence Challenge, co-hosted by Shenzhen Municipal Government and Shenzhen Tencent Information Technology Co., Ltd and won the third place in person re-identification track with a handsome sum of prize money (500,000 yuan).Reprinted from:  ZJU Newsroom