个人信息

刘驰，教授、博士生导师、bat365中国在线平台官方网站副院长，智能信息技术北京市重点实验室主任，国家级青年人才、国家重点研发计划首席科学家、青年北京学者、计算机科学与技术学科责任教授、校信息与电子学部委员、中国电子学会会士、英国工程技术学会会士（Fellow of IET）、英国计算机学会会士（Fellow of British Computer Society）。2006年本科于清华大学电子工程系，2010年博士毕业于英国帝国理工学院（Imperial College, UK）电气和电子工程系，后在德国电信研究总院（Deutsche Telekom Laboratories, Berlin）任博士后研究员，及在美国IBM TJ Watson研究中心和IBM中国研究院任研究主管。主要研究方向是：物联网大数据处理技术。主持国家重点研发计划“工业软件”重点专项项目、国家重点研发计划“战略性科技创新合作“重点专项项目共2项，国家自然科学基金联合重点项目2项以及青年/面上/优青3项，科技部高端外国专家引进计划4项，国家重点研发计划课题2项，以及科技委X73、XX6等。发表CCF-A类论文72篇、ESI高被引论文8篇，授权国内外发明专利49项，登记软件著作权60项，参与编著中英文书籍16本/节，谷歌引用1万余次，H index为48。

获2023年中国电子学会自然科学一等奖（排名第一）、2023年北京理工大学教育教学成果特等奖（排名第一）、CCF青年科技奖、ACM SigKDD 2021最佳论文亚军（Best Paper Runner-up Award）、ACM MobiCom 2021最佳社区论文亚军（Best Community Paper Runner-up Award）、中国高校计算机教育大会优秀论文奖，及省部级一等奖1项、二等奖2项。编写的物联网和强化学习教材入选工信部工程硕博士精品教材、工信部“十四五”规划教材、北京理工大学“十四五”规划教材、北京理工大学精品教材；培养的多名学生获得北京市优秀本科毕业设计论文、中国电子学会优秀硕士论文、北京理工大学最高奖学金徐特立奖学金等；作为指导教师带领学生获得2022年中国高校计算机大赛——人工智能创意赛全国总决赛特等奖。

现任国家信息产业“十四五”规划专家顾问组成员、第四届全国信标委技术委员会委员、科技创新2030—大数据重大项目领军专家、中国电子学会理事、中国计算机学会杰出会员，IEEE Transactions on Mobile Computing编委（CCF-A类），北京润丰中学科学副校长等。曾任中国工程院“十三五”战略性新兴领域高级咨询专家，IEEE Transactions on Network Science and Engineering编委并于2021年和2023年两次获得获杰出编委奖（Excellent Editor Award），CCF-A类会议SIGKDD、IJCAI、INFOCOM TPC（并获评2021年杰出程序委员，Distinguished TPC），IEEE ICC 2020 Symposium on Next Generation Networking主席（Chair），中国科协第400期青年科学家论坛回顾暨“弘扬科学家精神”报告会执行主席等。

科研方向

物联网大数据处理技术

代表性学术成果

代表性CCF-A类论文：

[JSAC]. C. H. Liu*, Z. Chen, J. Tang, J. Xu, C. Piao, "Energy-Efficient UAV Control for Effective and Fair Communication Coverage: A Deep Reinforcement Learning Approach," IEEE Journal of Selected Areas in Communications, Volume:3, Issue:9, Page(s): 2059-2070, 2018. 高被引论文

[JSAC]. C. H. Liu*, Z. Chen, Y. Zhan, "Energy-Efficient Distributed Mobile Crowd Sensing: A Deep Learning Approach," IEEE Journal of Selected Areas in Communications, Volume: 37, Issue: 6, Page(s): 1262 – 1276, June 2019.

[TKDE]. C. H. Liu*, J. Xu, J. Tang and J. Crowcroft, "Social-aware Sequential Modeling of User Interests: A Deep Learning Approach," IEEE Transactions on Knowledge and Data Engineering, Volume: 31, Issue: 11, Page(s): 2200 – 2212, Nov. 1 2019.

[TKDE]. C. H. Liu*, Y. Wang, C. Piao, Z. Dai, Y. Yuan, G. Wang, D. Wu, "Time-Aware Location Prediction by Convolutional Area-of-Interest Modeling and Memory-Augmented Attentive LSTM," IEEE Transactions on Knowledge and Data Engineering, DOI: 10.1109/TKDE.2020.3005735, June 2020.

[TMC]. C. H. Liu, X. Ma, X. Gao and J. Tang*, "Distributed Energy-Efficient Multi-UAV Navigation for Long-Term Communication Coverage by Deep Reinforcement Learning," IEEE Transactions on Mobile Computing, Volume: 19, Issue:6, Page(s): 1274-1285, JUNE 2020

[TMC]. C. H. Liu*, Z. Dai, Y. Zhao, J. Crowcroft, D. Wu and K. K. Leung, "Distributed and Energy-Efficient Mobile Crowdsensing with Charging Stations by Deep Reinforcement Learning," IEEE Transactions on Mobile Computing, Volume: 20, Issue: 1, Page(s): 130-146, January 2021.

[TPAMI]. S. Li, C. H. Liu*, Q. Lin, Q. Wen, L. Su, G. Huang, Z. Ding, "Deep Residual Correction Network for Partial Domain Adaptation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume:43, Issue: 7, Page(s): 2329-2344, July 2021.  高被引论文

[TPAMI]. S. Li, B. Xie, Q. Lin, C. H. Liu, G. Huang, and G. Wang,“Generalized Domain Conditioned Adaptation Network,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2021.3062644, 01 March 2021.

[TPAMI]. B. Xie, S. Li*, M. Li, C. H. Liu, G. Huang, and G. Wang,“SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Jan. 2023.

[TVCG]. G. Li, R. Li, Z. Wang, C. H. Liu*, M. Lu, and G. Wang,“HiTailor: Interactive Transformation and Visualization for Hierarchical Tabular Data,”IEEE Transactions on Visualization and Computer Graphics, Volume: 29, Issue: 1, Page(s): 139-148, Jan. 2023.

[TC]. R. Han, C. H. Liu*, S. Li, S. Wen, and X. Liu,“Accelerating Deep Learning Systems via Critical Set Identification and Model Compression,” IEEE Transactions on Computers, Volume: 69, Issue: 7, Page(s): 1059-1070, 1 July 2020.

[KDD]. H. Wang, C. H. Liu*, Z. Dai, J. Tang, G. Wang,“Energy-Efficient 3D Vehicular Crowdsourcing for Disaster Response by Distributed Deep Reinforcement Learning,”in  ACM SIGKDD 2021 , virtual, August 2021, Page(s): 3679–3687 (Best Paper Award - Runner Up).

[MOBICOM]. R. Han, Q. Zhang, C. H. Liu*, G. Wang, J. Tang, L. Y. Chen,“LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision,”in  ACM MOBICOM 2021 , virtual, October 2021, Page(s): 406–419. (Best Community Paper Award - Runner Up).

[NeurIPS]. F. Lv, J. Liang, K. Gong, S. Li*, C. H. Liu, H. Li, D. Liu, G. Wang,“Pareto Domain Adaptation,” in  NeurIPS 2021 , virtual, Dec. 6-14, 2021.

[ICLR]. M. Xie, S. Li*, R. Zhang, C. H. Liu,“Dirichlet-based Uncertainty Calibration for Active Domain Adaptation,” in  ICLR 2023 , virtual, May 1-5, 2023.

[INFOCOM]. C. H. Liu, Z. Dai, H. Yang, J. Tang, “Multi-Task-Oriented Vehicular Crowdsensing: A Deep Learning Approach,”in  IEEE INFOCOM 2020  , virtual, 6-9 July, Page(s): 1123-1132.

[INFOCOM]. C. H. Liu, C. Piao, J. Tang, “Energy-Efficient UAV Crowdsensing with Multiple Charging Stations by Deep Learning,”in  IEEE INFOCOM 2020 , virtual, 6-9 July, Page(s): 199-208.

[INFOCOM]. Z. Dai, H. Wang, C. H. Liu*, R. Han, J. Tang, G. Wang,“Mobile Crowdsensing for Data Freshness: A Deep Reinforcement Learning Approach,”in  IEEE INFOCOM 2021 , virtual, 10-13 May, 2021, Page(s): 1-10.  

[INFOCOM]. Z. Dai, C. H. Liu*, Y. Ye, R. Han, Y. Yuan, G. Wang, J. Tang,“AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning,”in  IEEE INFOCOM 2022 , Virtual, 2-5 May, 2022.

[ICDE]. C. H. Liu, Y. Zhao, Y. Yuan, G. Wang, D. Wu, K. K. Leung,“Curiosity Driven Energy-Efficient Worker Scheduling in Vehicular Crowdsourcing: A Deep Reinforcement Learning Approach,”in  IEEE ICDE 2020 , Dallas, USA, April 2020, Page(s):25-36.

[ICDE]. C. H. Liu, C. Piao, X. Ma, Y. Yuan, J. Tang, G. Wang,“Modeling Citywide Crowd Flows using Attentive Convolutional LSTM,”in  IEEE ICDE 2021 , virtual, April 19-23 2021, Page(s):217-228.

[ICDE]. Y. Wang, C. H. Liu*, C. Piao, Y. Yuan, R. Han, G. Wang,“Human-Drone Collaborative Spatial Crowdsourcing by Memory-Augmented and Multi-Agent Deep Reinforcement Learning,”in  IEEE ICDE 2022 , virtual, May 9-12 2022.

[ICDE]. Y. Ye, C. H. Liu, Z. Dai, J. Zhao*, Y. Yuan, G. Wang, J. Tang,“Exploring both Individuality and Cooperation for Air-Ground Spatial Crowdsourcing by Multi-Agent Deep Reinforcement Learning,” in  IEEE ICDE 2023 , virtual, 2023.

[CVPR]. S. Li, M. Xie, K. Gong, C. H. Liu*, Y. Wang, W. Li, “Transferable Semantic Data Augmentation for Domain Adaptation,” in  IEEE CVPR 2021 , virtual, June 19-25, 2021, Page(s):11516-11525. (oral presentation)

[AAAI]. Y. Zhao, K. Wu, Z. Xu, Z. Che, Q. Lu, J. Tang, C. H. Liu, “A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving,” AAAI 2022 , Virtual, 22 Feb-1 March, 2022. (oral presentation)

代表性论著和教材：

[1] 刘驰（主编）；韩锐、赵健鑫、马建（副主编），《物联网技术概论》第三版，机械工业出版社，2021年11月  北京理工大学“十四五”规划教材、北京理工大学精品教材

[2] 刘驰、王占健、马晓鑫、戴子彭等（编著），《深度强化学习：学术前沿与实践应用》，机械工业出版社，2020年4月

[3] 刘驰（主编）、符积高、徐闻春（编著）,《Spark:原理、机制及应用》，机械工业出版社，2016年3月

承担科研情况

所获奖励

社会兼职

备注

1. 实验室每年约录取博士、硕士，本科保研学生若干，请抓紧发邮件到chiliu@bit.edu.cn联系。

2. 实验室拥有NVIDIA A6000、RTX3090、2080Ti、XP系列显卡80余块，CPU集群一个（15台服务器），GPU服务器6台，边缘计算设备15台，能充分满足人工智能与大数据的科研需求。

3. 实验室常年与华为、字节跳动、美的、旷视、微软、腾讯、阿里及诸多海内外高校保持频繁的学术交流、实习生选派和博士生推荐。

4. 特别欢迎本校保研的同学提前来实验室，一起做高水平论文！

5. Last update October 2022