姓名:邓志东

职称:教授

电话:010-62796830

邮箱:michael@tsinghua.edu.cn

教育背景

工学学士 (计算机与自动化), 四川大学, 中国, 1986;

工学博士 (计算机与自动化), 哈尔滨工业大学, 中国, 1991.

社会兼职

中国自动化学会:会士(2018);理事(2008-2013;2013-2018;2018-);

中国自动化学会:智能自动化专委会主任(2013-2018;2018-);智能制造系统专委会副主任(2017-);

国家863计划:智能机器人主题专家组组长助理(1997-2001);

中国人工智能产业创新联盟:专家委主任委员(2017-).

研究领域

人工智能(深度神经网络、深度强化学习),计算神经科学,无人驾驶汽车,先进机器人等;

曾从事的研究领域:虚拟现实(1998-2001),无线传感器网络(2001-2009),计算生物学(2002-2010).

研究概况

我目前的主要研究方向包括:1)人工智能与计算神经科学(深度卷积神经网络、递归状态池神经网络、模糊神经网络、强化学习、无监督学习及其有机结合,力图发展可理解、有常识、能推理的人工智能新方法);2)自动驾驶技术(基于视觉人工智能的环境感知与自主导航,具有自主学习能力的智能决策与路径规划等);3)移动机器人技术(基于视觉人工智能的室内场景分割、目标与行为感知,认知地图与SLAM自主导航,自然交互,信息深度融合等)。

我曾于1996年至1997年在香港理工大学(Hong Kong Polytechnical University)访问研究一年(对方聘用);2001年至2003年在美国华盛顿大学(Washington University in St. Louis),以客座教授(Visiting Professor)身份工作两年(对方聘用),我曾参加美国NSF和DARPA项目的研究。

自2009年以来,主持研发了4台无人驾驶汽车,其中全线控THU-IV3已完成6,000km的真实道路测试,能够在较复杂城区、高速公路、乡村道路和越野环境进行自主行驶。率队参加了基金委全部9届“中国智能车未来挑战赛”(2009-2017),获“最佳组织贡献奖”。

2013年12月完成载人航天工程地面物料配送第2.5代AGV的研制任务,并投入生产运行。2010年研制开发出脑控机器人。2006-2008年,主持研制了煤矿井下环境探测与搜救机器人4台,并在约214米深的徐州某煤矿井下,完成了863项目的现场验收。2007-2010年,参与组织我国机器人模块化标准体系结构研究发展白皮书(草稿)、蓝皮书(草稿)等国家机器人发展战略报告的撰写。2001年,参与组织“十五”863计划机器人技术主题重大专项“大型全断面隧道掘进机(盾构机)”可行性论证与立项建议工作,推动了国产大型盾构机器人的发展。

2003-2009年,在3项863课题的先后资助下,我们自行设计并试制了具有通用接口的标准化Cicada无线传感器网络硬件节点系列,初步形成了具有自主知识产权的高、中、低档系列工程样品。主持研制的通用虚拟现实软件开发平台,1999年曾参加深圳“首届中国高新技术成果国际交易会”。迄今已发表学术论文250余篇,其中被WOS收录84篇,EI收录123篇。Google学术搜索总引用次数3,359次。参编专著或教材5本。

奖励与荣誉

1、获教育部第二届“高校青年教师奖”(2001.4);

2、获国家863计划智能机器人主题“先进工作者”(2001.3);

3、获第四届霍英东青年教师基金(1999.3);

4、获教育部科技进步奖(基础类)三等奖(排名第1,1998.1);

5、获首届“清华大学优秀博士后”奖(1997.11);

6、获国家教委科技进步奖二等奖(1997.1);

7、获航空航天部科技进步奖三等奖(1992.1);

8、国家自然科学基金委创新研究群体成员(2007-2009;2004-2006);

9、获世界机器人大赛“无人驾驶挑战赛”优秀团队奖(2016.10);

10、获国际自动驾驶KITTI四项评测任务冠军(2016-2018);

11、获中国智能车未来挑战赛最佳组织贡献奖(2017.11).

学术成果

[1] Shida Liu, Zhongsheng Hou, Taotao Tian, Zhidong Deng, and Zhenxuan Li. A Novel Dual Successive Projection-based Model-Free Adaptive Control Method and Application to an Autonomous Car, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019. DOI: 10.1109/TNNLS.2019.2892327

[2] Guorun Yang, Xiao Song, Chaoqing Huang, Zhidong Deng, Jianping Shi, and Bolei Zhou. DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios, IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2019), Long Beach, CA, USA, June 16 - June 21, 2019.

[3] Zhidong Deng, Lipu Zhou. Detection and Recognition of Traffic Planar Objects Using Colorized Laser Scan and Perspective Distortion Rectification, IEEE Transactions on Intelligent Transportation Systems (TITS ), vol.19, no.5, pp. 1485-1495, May 2018.

[4] Shiyao Wang, Minlie Huang, and Zhidong Deng. Densely Connected CNN with Multi-scale Feature Attention for Text Classification, In Proc. the 27th International Joint Conference on Artificial Intelligence (IJCAI-2018), Stockholm, Sweden, pp. 4468-4474, July 13-19, 2018.

[5] Shiyao Wang, Yucong Zhou, Junjie Yan, and Zhidong Deng. Fully Motion-Aware Network for Video Object Detection, In Proc. 15th European Conference on Computer Vision (ECCV-2018), Munich, Germany, pp. 542-557, September 8-14, 2018.

[6] Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, and Jiaya Jia. SegStereo: Exploiting Semantic Information for Disparity Estimation, In Proc. 15th European Conference on Computer Vision (ECCV-2018), Munich, Germany, pp. 660-676, September 8-14, 2018.

[7] Xiaolong Liu, Zhidong Deng, Hongchao Lu, Lele Cao. Benchmark for Road Marking Detection: Dataset Specification and Performance Baseline, In Proc. IEEE 20th International Conference on Intelligent Transportation Systems (ITSC-2017), Yokohama, Japan, October 16-19, 2017.

[8] Zhidong Deng, Zhenyang Wang, and Shiyao Wang. Stochastic Area Pooling for Generic Convolutional Neural Network, In Proc. 22nd European Conference on Artificial Intelligence (ECAI-2016), The Hague, Netherlands, pp. 1760 -1761, Aug. 29 - Sept. 02, 2016.

[9] Zhenyang Wang, Zhidong Deng, and Shiyao Wang. Accelerating convolutional neural networks with dominant convolutional kernel and knowledge pre-regression, In Proc. 14th European Conference on Computer Vision (ECCV-2016), Amsterdam, The Netherlands, pp. 533-548, October 11-14, 2016.

[10] Zhenbo Cheng, Zhidong Deng, Xiaolin Hu, Bo Zhang, and Tianming Yang. Efficient reinforcement learning of a reservoir network model of parametric working memory achieved with a cluster population winner-take-all readout mechanism, Journal of Neurophysiology, vol.114, no.6, pp.3296–3305, October, 2015.

[11] Lipu Zhou, Zhidong Deng. LIDAR and Vision-Based Real-Time Traffic Sign Detection and Recognition Algorithm for Intelligent Vehicle, In Proc. the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC-2014), Hyatt Regency Qingdao, Qingdao, China, October 8-11, 2014, pp.578-583.

[12] Lipu Zhou, Zhidong Deng. Perspective Distortion Rectification for the Planar Object Based on LIDAR and Camera Data Fusion, In Proc. the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC- 2014), Hyatt Regency Qingdao, Qingdao, China, October 8-11, 2014, pp.270-275.

[13] Lipu Zhou, Zhidong Deng. Extrinsic Calibration of a Camera and a Lidar Based on Decoupling the Rotation from the Translation, In Proc. the 2012 IEEE Intelligent Vehicles Symposium (IV-2012), Alcal de Henares, Spain, pp.642-648, June 3-7, 2012.

[14] Wentao Yao, Zhidong Deng, and Zhenhua Chen. A Global and Local Condensation for Lane Tracking, In Proc. the 15th International IEEE Annual Conference on Intelligent Transportation Systems (ITSC-2012), Anchorage, Alaska, USA, pp. 276-281, Sep. 16-19, 2012.

[15] Dandan Song, Yang, Bin Yu, Binglian Zheng, Zhidong Deng, Bao-Liang Lu, Xuemei Chen, and Tao Jiang. Computational prediction of novel non-coding RNAs in Arabidopsis thaliana, BMC Bioinformatics, vol.10, suppl.1, pp. (S36) 1-12, 2009.

[16] Zhidong Deng and Yi Zhang. Collective behavior of a small-world recurrent neural system with scale-free distribution, IEEE Transactions on Neural Networks (TNN), vol.18, no.5, pp.1364-1375, 2007.

[17] Zhidong Deng,Jianjun Niu, and Jingdan Zhang. A realistic 3-d reverse modeling system based on real-world sampling dataset, In Proc. the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2006), Beijing, China, pp. 5327-5332, Oct. 9-15, 2006.

[18] Z. D. Deng and W. X. Zhang. Localization and dynamic tracking using wireless-networked sensors and multi-agent technology: First Steps, IEICE Trans. on Fundamentals of Electronics, Communications and Computer Sciences, vol.E85-A, no.11, pp.2386-2395, 2002.

[19] 孙增圻,邓志东,张再兴,智能控制理论与技术(第2版),清华大学出版社,2011年9月(1997年首版).

[20] 张钹,王田苗(主编),邓志东,魏洪兴,王洪光(副主编),机器人发展战略研究报告—历程、技术、产业、标准与政策(上、下册),兵器工业出版社,2009年12月.