1.Introduction

The research direction of human machine interaction is one of the main research directions of the School of Electronic, Information, and Electrical Engineering of Shanghai Jiao Tong University. Human machine interaction is the study of interaction between people and machines, a cutting-edge research field with multidisciplinary nature. It covers quite broad of fields from computer science, cognitive sciences, robotics to industrial design disciplines. The basic mission of this direction is to conduct cutting-edge research work and supervise graduate students in the areas of brain-like computing, machine learning, computer vision, brain-computer interface, data mining, bioinformatics, Web search, computer graphics, medical precision engineering and intelligent systems, and service robots in order to satisfy the increasing needs from computer science, neuroscience, cognitive science, information technology, robotics, medicine, and engineering. Our long term goal is to develop a new type of brain-computer interface paradigm that computers will communicate and interaction with human in our own way.

The research work in human machine interaction mainly includes the following 5 areas: (1) brain-like computing and brain-computer interface, (2) data mining and Web search, (3) computer graphics, (4) medical precision engineering and intelligent systems, and (5) perception and control technologies for intelligent service robots. Many high level projects have been obtained in this research direction, such as National Natural Science Foundation of China, National Basic Research Program and National High Technique Program. The research fund of this group is about 2 million USD in recent 3 years. More than 40 international journal papers and 200 international conference (such as NIPS, CVPR, WWWW, ICML) papers have been published in recent 5 years..

In this direction there has been close collaboration with many reputable universities and transnational companies in the world, such as UIUC, Georgia Institute of Technology, Chinese University of Hong Kong, Hong Kong University of Science and Technology, National University of Singapore, Durham University of UK, Nanyang Technological University, Microsoft Research Asia, Google, IBM, Nokia, Motorola, Siemens, NTT, Hitachi, Fujitsu, NICT, Omron, Huawei. The group members are serving or have served as chair, co-chair, program committee member, session chair and invited speakers of dozens international conferences (such as WWW, WCCI, IJCNN, ICONIP, ISNN).

In this direction there are now more than 200 graduate students for Master degree and more than 50 graduate students for Ph. D degree. Most graduate students can publish one or more papers in top international conference and top international journal before graduation. Three of papers were awarded as best student papers in ICONIP2008, PKDD 2007 and APWeb 2005. One paper was awarded as best-student paper candidate in WWW 2007. One Ph.D. thesis is awarded as Excellent Ph.D. Thesis by China Computer Federation.

In this direction, the MOE-Microsoft key laboratory for Intelligent Computing and Intelligent Systems was approved in 2008. In this laboratory there are advanced computing systems, EEG signal acquisition systems and robot development systems.

2.Faculty Members

In this research direction there are 8 full professors and 12 associate professors The resume of some full professors are given below.

Lu Bao-Liang received the B.S. degree in instrument and control engineering from Qingdao University of Science and Technology, China, in 1982, the M. S. degree in computer science and technology from Northwestern Polytechnical University, Xi'an, China, in 1989, and the Dr. Eng. degree in electrical engineering from Kyoto University, Kyoto, Japan, in 1994. From 1982 to 1986, he was with the Qingdao University of Science and Technology. From April 1994 to March 1999, he was a Frontier Researcher at the Bio-Mimetic Control Research Center, the Institute of Physical and Chemical Research (RIKEN), Nagoya, Japan. From April 1999 to August 2002, he was a Research Scientist at the RIKEN Brain Science Institute, Wako, Japan. Since August 2002, he has been a full professor at the Department of Computer Science and Engineering, Shanghai Jiao Tong University, China. He has been an adjunct professor of the Laboratory for Computational Biology, Shanghai Center for Systems Biomedicine since 2005. His research interests include brain-like computing, neural networks, machine learning, pattern recognition, computer vision, brain-computer interface, natural language processing, and computational biology. He has published more than 80 papers in international journals and conferences. He is a project leader and the main participants of 6 research projects including National Natural Science Foundation of China, the National Basic Research Program of China and, and the Hi-Tech Research and Development Program of China. He has served as Special Issue Guest Editor for International Journal of Neural Systems and Neurocomputing. He is serving or has served as program chair and/or member in numerous international conferences, e.g., IJCNN, ICONIP, ISNN etc. He has also served as reviewer for international conferences as well as journals, e.g., IEEE Transactions on Neural Networks, Neural Networks. He is a senior member of IEEE and a governing board member of Asia Pacific Neural Network Assembly (APNNA), 2008–Present.

Zhang Liqing received the Ph.D. degree from Zhongshan University, Guangzhou, China, in 1988. He joined South China University of Technology in 1988 and became a full professor in 1995. From 1997.10 to 2002.9, he joined RIKEN Brain Science Institute as a research scientist. He is now a Professor with Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China. He is also a visiting scientist of RIKEN brain science institute, Japan. His current research interests cover computational theory for cortical networks, brain signal processing and brain–computer interface, statistical learning and inference. He has published more than 150 papers in international journals and conferences. He serves as the associate editor of “International Journal of Computational Intelligence and Neuroscience”, the director of the technical committee of biocybernetics and biomedical engineering, Chinese Automation Association, member of Chinese neural network society, member of neuroinformatics and neuroengineering committee, Chinese Neuroscience Association. He is also the reviewer of a number of international journals, such as IEEE Trans. Neural Networks，IEEE Trans. Signal Processing，IEEE Signal Processing Letters

Yu Yong, as a full professor, is the vice chair of the Department of Computer Science and Engineering at Shanghai Jiao Tong University. He is also the director of APEX Lab. As a pioneer scientist of Semantic Web in China, he actively participated in and contributed to the fast advances of Semantic Web technologies in recent years. He and his group have successfully published more than 100 papers on international conferences and journals about semantic search and semantic data management. He has served as a PC member of several past ISWC conferences and a dozen of other conferences (e.g. WWW, ESWC, ASWC, etc) as well. He will serve as a guest editor of the special issue “Semantic Search” of Journal of Web Semantics. Moreover, he will be one of the local chairs of ISWC 2010. Prof. Yu paid much attention to building tight relationships with other research institutes from the Semantic Web community. He was one of the initiator to form the China Semantic Web Association and served as the organizer to host the second China Semantic Web Symposium to impact this growing community.

Ma Lizhuang, born on 28 Feb. 1963, received his B. Sc. and Ph.D. degree at Zhejiang University, China in 1985 and 1991 respectively. He was a post-doctor at the Dept. of Computer Science of Zhejiang University from 1991 to 1993. Dr. Ma was promoted as an Associative Professor and Professor in 1993 and 1995 respectively. He was a visiting Professor at Frounhofer IGD, Darmstadt, Germany from July to Dec. 1998, and at CAMTech, Nanyang Technological University, Singapore from Sept. 1999 to Nov.2000. He is now a Professor, PhD tutor, and the head of Digital Media Technology and Data Reconstruction Lab. at the Department of Computer Science and Engineering, Shanghai Jiao Tong University, China. Dr. Ma has published more than 100 academic research papers including both domestic and international journals Dr. Ma is the recipient of China National Excellent Young Scientist Foundation, first class member of China National Hundred-Thousand-Ten-thousand Talent Plan, China National Award of Science and Technology for Young Scientists and Second Prize of Science and Technology of National Education Bureau. His research interests include computer graphics, computer aided design, computer animation, media technology, medical data processing, and theory and applications for Computer Graphics, CAD/CAM. Prof. Ma was the steering member of the IFIP Entertainment Computing Group. He was the general chair and the program chair of the ICEC2007. He was also the general chair and the program chair of the China CIDE2007.

Yan GuoZheng received Eng. Ph. D degree from Jilin Technological University in 1993. Since 1996, he has been professor in Department of Instrument Science and Engineering, Shanghai Jiaotong University. He is currently the Head of Department of Instrument Science and Engineering. His research interests include Bionic mechanics and micro-mechanics, micro-electro-mechanical systems, precision instruments, medical engineering and robotics, micro-motion systems intelligent control theory and methods. As a project leader and the main participants, he has completed 10 projects, such as: Key Technologies R&D Program, National Natural Science Foundation of China, Hi-Tech Research and Development Program of China. 13 projects from the Ministry of Education, Shanghai and other provincial and ministerial scientific research, more than 10 industry research projects. He has published more than 130 thesis papers.

Su Jianbo, born in Sept. 1969. He received the B. S. degree in control theory and control engineering from Shanghai Jiaotong University, Shanghai, China in 1989, the M.S. degree in Pattern Recognition and Intelligent System from Institute of Automation, Chinese Academy of Sciences, Beijing, China in 1992, and Ph.D in control theory and control engineering from Southeast University, Nanjing, China in 1995. From 1995-1997, he was a postdoctoral research fellow in robotics in Chinese Academy of Sciences.

He is currently a professor in the Department of Automation, Shanghai Jiaotong University. Meanwhile, he is a senior member of IEEE, a council member of the Chinese Association of Automation. He also serves as an associate editor of IEEE Transaction on System, Man and Cybernetics (Part B), an associate editor of International Journal of Social Robotics, a regional editor of International Journal of system, control and communications, a member of the Technical Committee on Networked Robots of IEEE robotics and automation society, the chairman of the Youth Committee of the Chinese Association of Automation (CAA), etc.. In 1999, he visited The Chinese University of Hong Kong with financial support from Hong Kong Croucher Foundation. In 2001, he visited Institute of Automatic Control Engineering, Technical University of Munich with financial supports from Deutsche Forschungsgemeinschaft (DFG) and the Ministry of Education of China. In 2004, he was a visiting research scientist in Bio-Mimetic Control Research Center, RIKEN, Japan. Dr. Su was honored to receive the Overseas Outstanding Young Scientist award from the Chinese National Natural Science Foundation in 2004, be a New Century Excellent Young Investigator in 2006.

Dr. Su has published two books and over 160 papers in journals and international conferences. His research interests include sensor-based robotics, multi-robot coordination, telepresence and network robotics, pattern recognition and computer vision.

Chen Weidong was born in 1968. He received the B.S. and M.S. degrees in Control Engineering in 1990 and 1993, and Ph.D. degree in Mechatronics in 1996, respectively, all from the Harbin Institute of Technology, Harbin, China. Since 2005 he has been a professor of the Department of Automation at the Shanghai Jiao Tong University, Shanghai, China, and director of the Institute of Robotics and Intelligent Processing. From 2003 to 2004, he was a visiting associate professor in the Department of Electrical and Computer Engineering at The Ohio State University. He has authored or co-authored over 90 refereed journal and conference papers, and two book chapters. He received 5 patents and more than 13 pending patents. He is a main participant of a Technology Innovation Award from the Shanghai Municipal Government in 2008. Dr. Chen’s research interests include autonomous mobile robot, multi-robot cooperation, and micro manipulation.

Yang Ming received Eng. Ph. D degree in precision machinery and equipment from Tianjin University in 1996. From1996 to 1998, he was a postdoctoral researcher in the Research Center of Ultrasonic Motors in Nanjing University of Aero./Astro., Nanjing, China. From 2002 to 2005, he was a research fellow in the School of Mechanical Engineering, University of Leeds, Leeds, UK, researching on ultrasonic devices for cardiac assist. He is currently a Professor, Doctoral Advisor in Department of Instrument Science and Engineering, Shanghai Jiaotong University. He has published more than 30 papers. He has been principal investigators or co-investigators for more than 10 research projects such as National Natural Science Foundation of China, Hi-Tech Research and Development Program of China, and other industrial co-operation projects et al. His current research interests include ultrasonic motor, smart artificial heart, detection of weak signals, and non-destructive testing et al.

3. Representative Research Achievements

Achievement 1—Brain-like computing and brain-computer interface

The number of training samples that are available on the internet to train pattern classifiers is increasing rapidly, while traditional pattern classification techniques based on a single computer system are powerless to process these large-scale data sets. In brain-like computing research, we have developed a parallel and modular pattern classification framework for coping with large-scale pattern classification problems. The proposed framework follows a divide-and-conquer strategy that easily assigns a given large-scale problem to an available parallel and distributed computing infrastructure. The framework consists of three independent parts: decomposing training data sets, training component classifiers in a parallel way, and combining trained component classifiers. Various experimental results show that our framework has the following attractive features: (a) The framework is general, and therefore any traditional pattern classification techniques such as support vector machines can be easily embedded in the framework as component classifiers. (b) The framework can incorporate explicit domain or prior knowledge into learning through the process of dividing training data sets. (c) The framework has good scalability and is easily implementable in hardware.

Brain-computer interface (BCI) is emerging technology of establishing direct link between human intentions and devices, allowing people to communicate and control devices in their environment without using the peripheral neural system but instead through the use of signals from the brain. The BCI project is to investigate the fundamental electroneurophysiologic mechanism, communication protocols, cognitive task-related electroencephalogram (EEG) feature analysis, pattern classification, neurofeed-back and typical applications. To develop a natural BCI interfaces, we investigate how the duration of event-related desynchronization/synchronization caused by motor imagery can be modulated and used as an additional control parameter beyond simple binary decisions. Furthermore, using the non-time-locked properties of sustained (de)synchronization, we have developed an asynchronous BCI system for driving a car in 3D virtual reality environment based on cumulative incremental control strategy. The extensive real time experiments confirmed that our new approach is able to drive smoothly a virtual car within challenging VRE only by the MI tasks without involving any muscular activities.

To develop robust feature extraction method for single trial EEG classification, we propose a novel tensor-based scheme which performs well without using the prior neurophysiologic knowledge. In this scheme, EEG signals are represented in the spatial-spectral-temporal domain by the wavelet transform, the multilinear discriminative subspace is reserved by the general tensor discriminant analysis, redundant indiscriminative patterns are removed by Fisher score, and the classification is conducted by the support vector machine.

The following 5 representative papers published in recent 5 years support the Achievement 1

1. Jie Li, Liqing Zhang, Dacheng Tao, Han Sun and Qibin Zhao, A Prior Neurophysiologic Knowledge Free Tensor-based Scheme for Single Trial EEG Classification, IEEE Transactions on Neural Systems and Rehabilitation Engineering，17(2):107-115, 2009

2. Jing Li, Bao-Liang Lu, An Adaptive Image Euclidean Distance, Pattern Recognition, vol. 42, pp. 349-357, 2009

3. Qibin Zhao, Liqing Zhang and Andrzej Cichocki, EEG-based asynchronous BCI control of a car in 3D virtual reality environments, Chinese Science Bulletin, Vol.54, No. 1, pp.78-87, 2009

4. Bao-Liang Lu, J. H. Shin, M. Ichikawa,. Massively parallel classification of single-trial EEG signals using a min-max modular neural network. IEEE Transactions on Biomedical Engineering, vol. 51 no. 3, pp. 551-558, 2004

5. L. Zhang, A. Cichocki and S. Amari, Self-Adaptive Blind Source Separation Based on Activation function Adaptation, IEEE Transactions on Neural Networks, Vol.15, No.2, pp.233-244, 2004

Achievement 2—Data Mining and Web Search

Traditional machine learning techniques make a basic assumption that the training and test data should be under the same distributions. However, in many cases, this identical distribution assumption does not hold. The violation of the assumption might happen when the training data are out of date, but new data are expensive to label. This leaves plenty of labeled examples that are under a similar but different distribution, which is a waste throw away entirely. In this situation, transfer learning becomes important to take the role of leveraging these existing data knowledge. Transfer learning aims at using learned knowledge from one context to benefit further learning tasks in other contexts. Thus, transfer learning does not make the identical distribution assumption as traditional machine learning algorithms.

In Web search area, we focused on how to do personalized Web search in this area. We propose to use social behavior to solve the two critical issues in personalization: sparseness and cold-start. A novel statistical smoothing algorithm was proposed. We applied the proposed smoothing algorithm to collaborative filtering and the experimental results show that our approach can help to alleviate the two challenge issues. Furthermore, we extended the algorithm with language model and apply to the personalized search area. A user language model is proposed to solve the difficult issue of user modeling. Finally, with the emerged of Web 2.0, we proposed the effective algorithms by integrating the social behaviors into the general Web search.

In recent years, the amount of structured data available on the Web has been increasing rapidly. In order to collect more high-quality structured data, we mainly focus on knowledge extraction. In particular, we pay much attention to automatically extract such data from Web 2.0 social corpus like Del.icio.us, Flickr and Wikipedia. In order to efficiently manage large amounts data, we consider to leverage the strengths of both database and information retrieval to build scalable triple stores. In addition, in order to attract more casual users to use semantic search engines, we further developed natural language interface as well as keyword query interface to improve the usability.

In Web mining research, most of mining researches were focused on homogenous data objects. Actually, heterogeneous Web objects are more representative in current Web environment. In such environment, we propose heterogeneous Web mining research. Three research directions on heterogeneous Web mining were proposed: content based heterogeneous Web mining, structure based heterogeneous Web mining and usage based heterogeneous Web mining. Furthermore, we consider the relations from different aspects: hyperlink relation, click relation, hierarchical relation. Several novel algorithms are proposed, such as topic-sensitive(bridged) PLSA, structured learning and structured modeling.

The following 5 representative papers published in recent 3 years support the Achievement 2:

1. Wenyuan Dai, Yuqiang Chen, Gui-Rong Xue, Qiang Yang, and Yong Yu. Translated Learning. In Proceedings of Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008), December 8, 2008, Vancouver, British Columbia, Canada.

2. Guangcan Liu, Zhouchen Lin, Xiaoou Tang, Yong Yu, "Unsupervised Object Segmentation with A Hybrid Graph Model (HGM)," IEEE Transactions on Pattern Analysis and Machine Intelligence, 10 Feb. 2009. IEEE computer Society Digital Library. IEEE Computer Society, <http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.40>

3. Gui-Rong Xue, Jie Han, Qiang Yang, Yong Yu, User Language Model for Collaborative Personalized Search. ACM Transaction on Information Systems (TOIS). 27, 2 (Feb. 2009), 1-28.

4. Ke Zhou, Xue Gui-Rong, Qiang Yang, Yong Yu, "Learning with Positive and Unlabeled Examples Using Topic Sensitive PLSA," IEEE Transactions on Knowledge and Data Engineering, 18 Feb. 2009. IEEE computer Society Digital Library. IEEE Computer Society, <http://doi.ieeecomputersociety.org/10.1109/TKDE.2009.56>

5. Shen Huang, Zheng Chen, Yong Yu, and Wei-Ying Ma. Multitype Features Coselection for Web Document Clustering. IEEE Transactions on Knowledge and Data Engineering, Vol 18, Issue 4 (Apr. 2006), 448-459.

Achievement 3—Computer graphics

We study on the image based reconstruction and rendering techniques, the measurement of BRDF, digital geometry, the composition of videos from different sources and virtual and augmented reality. Based on the scanned CT data of on the teeth, we proposed an efficient motion path planning system for automatic tooth alignment, in which collision detection for teeth movement are considered well. New algorithms are also proposed for accurate segmentation of teeth. We introduce a novel mesh cutout system to efficiently extract meaningful object from a triangular mesh. We propose an efficient method for reconstruction of 3D objects with high specular light and finish a measurement system for obtaining BRDF value of minor object. We propose a robust watermarking scheme called Double-Layer Spread-Transform Dither Modulation (DL-STDM) for watermarking motion data. We propose a modified Laplacian smoothing approach with mesh saliency. Unlike the classical Laplacian smoothing, where every new vertex of the mesh is moved to the barycenter of its neighbors, we set every new vertex position to be the linear interpolation between its primary position and the barycenter of its neighbors.

We also study on the interactive design and invention of animation. Starting from a novel or opera, we create the scenes and branch-scenes based on natural language reasoning, design actors or different roles, generate 3d geometric objects based on constraints and reasoning, produce computer animation, rendering the scenes and composition of different source videos. In the whole procedure and system, an material database plays an important role through out. We also do research on motion capture animation. An efficient algorithm is obtained for motion edit based on analytic IK and multi-resolution motion curve fitting. We solve the human body IK analytically combining with the multi-resolution B-spline curve edit, and real time motion edit can be reached. Motion path editing and modification tool are obtained for animation. Some new algorithms are obtained for image and video segmentation, and composition of different source videos. Some new style of art productions are well applied in the art museum.We have published more than 55 papers and have applied more than 16 national invention patents, in which two patents are awarded.

The following 5 representative papers published in recent 5 years support the Achievement 3:

1. Zhong Li, Lizhuang Ma, Xiaogang Jin, Zuoyong Zheng, A New feature-preserving mesh-smoothing algorithm, Visual Computer, 25: 139-148, 2009

2. Xiaomao Wu, Lizhuang Ma and , Robust Watermarking Motion Data with DL-STDM，Computers & Graphics 32(3)，320-329, 2008.

3. Nie Dongdong, Ma Qinyong, Ma Lizhuang, Xiao Shuangjiu. Optimization Based Grayscale Image Colorization. Pattern Recognition Letters, Vol. 28(12), 2007, Pages: 1445-1451.

4. Zhihong Mao, Lizhuang Ma, Mingxi Zhao, Xuezhong Xiao, SUSAN Structure Preserving Filtering for Mesh Denoising, Visual Computer, 22(4): 276-284, 2006.

5. Mingxi Zhao,Lizhuang Ma, and Zhou Yong, Mesh Cutout, IEICE Transactions on Information and Systems 2006 E89-D(7):2207-2213. 2006.

Achievement 4—Medical precision engineering and intelligent systems

The research of medical precision engineering and intelligent systems is to combine traditional medical devices with advanced electronic information, microelectronics, computers, automation, new materials, precision engineering, which can achieve modeling and digital expression of the human body, minimally invasive and non-invasive diagnosis and treatment, improvement of the accuracy of medical diagnostic and treatment quality. The research includes the following three areas. (1) Medical information sensing and processing technology consist of new sensor technology, human gastrointestinal tract non-invasive detection of physiological information technology and human gastrointestinal function modeling. Relative research achievements include three National 863 projects, 4 provincial and ministerial scientific research projects and more than 60 papers. (b) Precision medical technologies and systems consist of non-invasive and minimally Invasive treatment robot technology for the body cavity, intelligent artificial heart technology and artificial anal sphincter technology. Relative research achievements include three National 863 projects, three National Natural Science Funds projects, 5 provincial and ministerial scientific research projects and more than 50 research papers. (3) Key technologies for medicine and health consist of wireless power transmission technology based on the human bio-electromagnetic energy security, human biological tissue compatibility, high intensity focused ultrasound treatment technology, etc. Relative research results include 2 national 863 projects, 3 provincial and ministerial scientific research projects and more than 30 papers.

The following 5 representative papers published in recent 2 years support the Achievement 4:

1. Wang, KD; Yan, GZ. Research on measurement and modeling of the gastro intestine's frictional characteristics. MEASUREMENT SCIENCE & TECHNOLOGY, 20 (1): Art. No. 015803 JAN 2009

2. Li, HE; Yan, GZ; Ma, GY. An active endoscopic robot based on wireless power transmission and electromagnetic localization. INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY, 4 (4): 355-367 DEC 2008

3. Kundong Wang, Guozheng Yan, Pingping Jiang, Dongdong Ye. A wireless robotic endoscope for gastrointestine. IEEE TRANSACTIONS ON ROBOTICS. Vol.24, No.1, 2008: 1-5

4. Li SY, Yang M， Particle swarm optimization combined with finite element method for design of ultrasonic motors， SENSORS AND ACTUATORS A-PHYSICAL，2008，Volume:148 Issue: 1 Pages: 285-28

5. Ma Guanying, Yan Guozheng and He Xiu. Power Transmission for Gastrointestinal Microsystems Using Inductive Coupling. Physiol. Meas. 28. 2007. N9–N18

Achievement 5—Perception and Control Technologies for Intelligent Service Robots

This investigation focuses on the perception and control technologies of intelligent service robots that advance the application of robotics for assisting humans in daily life or in hazardous environments. A hierarchical architecture with hybrid maps (grid map and topological map) is developed for localization, motion planning and navigation of mobile robots, and the implemented hardware and software of the architecture is tested in real robots successfully. To address the issues of self-healing and scalability for coordination and cooperation tasks of mobile robot networks, we proposed a novel modeling and distributed control method based on motion synchronization of dynamic network. In the applications of service robotics for elderly, disabled, and urban transportation, the above mentioned technologies are implemented and integrated in several service robot prototypes such as intelligent wheelchair, mobile manipulator, intelligent vehicle, biped walking robot, and coordination and cooperation system of multiple mobile robots. The results of experiments and application demonstrations conducted in real environments verified the effectiveness and applicability of the developed technologies and robots. This study has been successively funded by the National Natural Science Foundation and the National High Technology Research and Development Program of China. The research group published more than 10 papers in IEEE Transactions, Autonomous Robots and other international journals authorized 5 state patents and 4 software copyrights. Our robot team won several champions in international and domestic robot competitions such as RoboCup China Open and FIRA.

The following 5 representative papers published in recent 3 years support the achievement 5:

1. Fei Zhang, Yugeng Xi, Zongli Lin, and Weidong Chen, “Constrained Motion Model of Mobile Robots and Its Applications,” IEEE Transactions on Systems, Man, and Cybernetics: Part B, Accepted.

2. Jianbo Su, Yanjun Zhang, “Integration of a Plug-and-Play Desktop Robotic System”, Robotica， Vol. 27, No. 3, pp. 403-409, 2009.

3. Zhijun Li, Weidong Chen and Jun Luo, “Adaptive Compliant Force-Motion Control of Coordinated Nonholonomic Mobile Manipulators Interacting With Unknown Non-rigid Environments,” Neurocomputing, 71(7-9): 1330-1344, March, 2008.

4. Haigui Xu, Chunxiang Wang, Ming Yang, Ruqing Yang, “Position Estimation for Intelligent Vehicles using an Unscented Kalman Filter,” International Journal of Vehicle Autonomous Systems, 6(1/2): 186-194, 2008.

5. Jianbo Su ,“Camera Calibration Based on Receptive Fields”， Pattern Recognition，Vol.40, No. 10, pp. 2837-2845, Oct. 2007.