基本信息
连文昭 男 中国科学院自动化研究所
电子邮件： wenzhao.lian@ia.ac.cn
2011年本科毕业于上海交通大学电子系，2015年获得美国杜克大学(Duke University)电子与计算机工程博士学位和统计学硕士学位。毕业后先后就职于Vicarious AI，Google X，和Figure AI。2023年5月入职中国科学院自动化研究所，任研究员。研发了工业机器人领域基于云边协同和人工智能的机器人操作系统平台；实现了通过单一样本示教习得可泛化的复杂操作技能，操作精度达到亚毫米级；落地了多种形态的工业级产品。在人工智能和机器人领域的国际学术会议与期刊(ICRA/RSS/IROS/ICML/Neurips等)发表学术论文数十篇，申请国际专利十余项。见https://lianwenzhao.github.io/。
研究领域
• 研究机器学习理论与方法，包括模仿学习、仿真学习、机器人视觉、多模态感知以及通用大模型；
• 为自主智能体开发基于人工智能的操作系统和基础架构；
• 上述理论和方法在机器人灵巧操作、复合机器人和智能制造等领域的应用。
招生信息
招生专业
081104-模式识别与智能系统081203-计算机应用技术081002-信号与信息处理
招生方向
机器人学习，模仿学习，仿真学习，机器人视觉，多模态感知机器人软硬件一体化系统机器人灵巧手操作，复合机器人应用
教育背景
2011-08--2015-12 杜克大学 博士2007-09--2011-07 上海交通大学 本科
工作经历
工作简历
2023-05~现在, 中国科学院自动化研究所, 研究员2023-01~2023-05,Figure AI, 技术总监2019-08~2023-01,Google X, 资深研究科学家2016-01~2019-08,Vicarious AI, 高级研究员
出版信息
发表论文
[1] Zheng Wu, Wenzhao Lian, Changhao Wang, Mengxi Li, Stefan Schaal, Masayoshi Tomizuka. Prim-LAfD: A Framework to Learn and Adapt Primitive-Based Skills from Demonstrations for Insertion Tasks. IFAC World Congressnull. 2023, [2] Achu Wilson, Wenzhao Lian, Helen Jiang, Wenzhen Yuan. Cable Routing and Assembly using Tactile-driven Motion Primitives. International Conference on Robotics and Automationnull. 2023, [3] Xinghao Zhu, Wenzhao Lian, Bodi Yuan, Daniel Freeman, Masayoshi Tomizuka. Allowing Safe Contact in Robotic Goal-Reaching: Planning and Tracking in Operational and Null Spaces. International Conference on Robotics and Automationnull. 2023, [4] Wen, Bowen, Lian, Wenzhao, Bekris, Kostas, Schaal, Stefan. CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation. 2022, [5] Jin, Shiyu, Lian, Wenzhao, Wang, Changhao, Tomizuka, Masayoshi, Schaal, Stefan. Robotic Cable Routing with Spatial Representation. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2022, 7(2): 5687-5694, http://dx.doi.org/10.1109/LRA.2022.3158377.[6] Wu, Zheng, Xie, Yichen, Lian, Wenzhao, Wang, Changhao, Guo, Yanjiang, Chen, Jianyu, Schaal, Stefan, Tomizuka, Masayoshi. Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning. 2022, http://arxiv.org/abs/2210.00350.[7] Migimatsu, Toki, Lian, Wenzhao, Bohg, Jeannette, Schaal, Stefan. Symbolic State Estimation with Predicates for Contact-Rich Manipulation Tasks. 2022, [8] Wen, Bowen, Lian, Wenzhao, Bekris, Kostas, Schaal, Stefan. You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration. 2022, http://arxiv.org/abs/2201.12716.[9] Luo, Jianlan, Sushkov, Oleg, Pevceviciute, Rugile, Lian, Wenzhao, Su, Chang, Vecerik, Mel, Ye, Ning, Schaal, Stefan, Scholz, Jon. Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study. 2021, http://arxiv.org/abs/2103.11512.[10] Zachares, Peter A, Lee, Michelle A, Lian, Wenzhao, Bohg, Jeannette. Interpreting Contact Interactions to Overcome Failure in Robot Assembly Tasks. 2021, http://arxiv.org/abs/2101.02725.[11] Lian, Wenzhao, Kelch, Tim, Holz, Dirk, Norton, Adam, Schaal, Stefan. Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks. 2021, http://arxiv.org/abs/2103.05140.[12] Wu, Zheng, Lian, Wenzhao, Unhelkar, Vaibhav, Tomizuka, Masayoshi, Schaal, Stefan. Learning Dense Rewards for Contact-Rich Manipulation Tasks. 2020, http://arxiv.org/abs/2011.08458.[13] Yamada, Makoto, Lian, Wenzhao, Goyal, Amit, Chen, Jianhui, Wimalawarne, Kishan, Khan, Suleiman A, Kaski, Samuel, Mamitsuka, Hiroshi, Chang, Yi, ACM. Convex Factorization Machine for Toxicogenomics Prediction. KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MININGnull. 2017, 1215-1224, http://dx.doi.org/10.1145/3097983.3098103.[14] Evan X. Chen, Wenzhao Lian, Lawrence Carin, Brady David Jones. Task-driven Adaptive Sensing on Quadrupole Mass Filter Systems for Classification. Computational Optical Sensing and Imagingnull. 2015, [15] Lian, Wenzhao, Talmon, Ronen, Zaveri, Hitten, Carin, Lawrence, Coifman, Ronald. Multivariate time-series analysis and diffusion maps. SIGNAL PROCESSING[J]. 2015, 116: 13-28, http://dx.doi.org/10.1016/j.sigpro.2015.04.003.[16] Wenzhao Lian, Ricardo Henao, Rao, Vinayak, Joseph Locus, Lawrence Carin. A Multitask Point Process Predictive Model. International Conference on Machine Learningnull. 2015, [17] Lian Wenzhao, Rai Piyush, Salazar Esther, Carin Lawrence, AAAI. Integrating Features and Similarities: Flexible Models for Heterogeneous Multiview Data. PROCEEDINGSOFTHETWENTYNINTHAAAICONFERENCEONARTIFICIALINTELLIGENCEnull. 2015, 2757-2763, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485625502112.[18] Wenzhao Lian, Rao, Vinayak, Brian Eriksson, Lawrence Carin. Modeling Correlated Arrival Events with Latent Semi-Markov Processes. International Conference on Machine Learningnull. 2014, [19] Carlson, David E, Vogelstein, Joshua T, Wu, Qisong, Lian, Wenzhao, Zhou, Mingyuan, Stoetzner, Colin R, Kipke, Daryl, Weber, Douglas, Dunson, David B, Carin, Lawrence. Multichannel Electrophysiological Spike Sorting via Joint Dictionary Learning and Mixture Modeling. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING[J]. 2014, 61(1): 41-54, https://www.webofscience.com/wos/woscc/full-record/WOS:000333263300006.[20] Kyle Ulrich, David Carlson, Wenzhao Lian, Jana Borg, Kafui Dzirasa, Lawrence Carin. Analysis of Brain States from Multi-Region LFP Time-Series. Advances in Neural Information Processing Systemsnull. 2014,