选择语言
< 返回主菜单
lucewu2_fuben.jpg

卢策吾

上海期智研究院PI(2020年7月-2023年6月)
上海交通大学教授

个人简介

上海交通大学计算机科学与工程系特别研究员,曾任上海期智研究院PI。

入选2016年度海外高层次青年引进人才,2018年被《麻省理工科技评论》评选为中国35位35岁以下科技精英(MIT TR35),荣获2019年度“求是杰出青年学者奖”, 2020年获上海市科技进步特等奖(排名第三),以通讯或第一作者在《Nature》,《Nature Machine Intelligence》,TPAMI,CVPR等高水平期刊和会议发表(含接收)论文100多篇,担任《Science》,《Nature Machine Intelligence》审稿人,曾担任CVM 2018程序主席,CVPR 2020,ICCV 2021,IROS 2021领域主席。主要从事计算机视觉与机器人研究,已取得多项突破性研究成果,开源了如人体姿态估计系统Alphapose(GitHub Star 5000+),HAKE(人体行为引擎),GraspNet(高性能机器人抓取系统)等拥有国际先进水平的开源人工智能框架和数据集。


个人荣誉

2018年《麻省理工科技评论》中国35位35岁以下科技精英(MIT TR35)

2019年度“求是杰出青年学者奖”

研究方向

计算机视觉

机器人

亮点成果

成果:机器人模型学习新基准评测平台RoboTube(已开源)

       卢策吾团队建立了一个全新的机器人模仿学习基准平台RoboTube,用于从人类视频中模仿学习行为决策并迁移到真是机器人。该问题大规模评测一直是空白,为了实现这一目标,需要专门为机器人设计多样化、高质量的人类视频数据集。 为了评估其学习表现,团队建立了数字孪生仿真环境帮助机器人和人工智能研究人员在对真实机器人进行测试之前快速且有效地验证其算法。RoboTube 视频数据集包含 5000 个用多视角 RGB-D 相机录制的视频演示,这些视频演示了人类执行的日常家务任务,包括操纵刚性物体、铰接物体、可变形物体和双手操纵。 数字孪生仿真环境,由 3D 扫描的真实物体组成,最大限度地减少了物理世界和模拟环境之间的域差距。 作为本领域最新的基准平台RoboTube 大大降低该领域研究者成本,有力推进了机器人模仿学习社区的可复现研究。

卢策吾2022.png

图. RoboTube基准评测平台,包含50个常用家用应用场景,5000个视频

论文发表

1.  Xinyu Xu,Yonglu Li,Cewu Lu,Learn to Anticipate Future with Dynamic Context Removal,2022 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022


2.  Xinpeng Liu, Yong-Lu Li, Xiaoqian Wu, Yu-Wing Tai, Cewu Lu, Chi-Keung Tang,Interactiveness Field of Human-Object Interactions, 2022 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022


3.  Lixin Yang, Kailin Li, Xinyu Zhan; Fei Wu ; Anran Xu; Liu Liu; Cewu Lu,OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction,2022 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022


4.  Lixin Yang, Kailin Li, Xinyu Zhan, Jun Lv, Wenqiang Xu, Jiefeng Li, Cewu Lu,ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis, 2022 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022


5.  haoyu Xiong, Haoyuan Fu, Jieyi Zhang, Qiang Zhang, Chen Bao, Yongxi Huang, Wenqiang Xu, Animesh Garg, Huazhe Xu, Cewu Lu, RoboTube: Learning Household Manipulation from Human Videos with Simulated Twin Environments, 6th Annual Conference on Robot Learning, 2022


6.  Ruoxi Shi, Zhengrong Xue, Yang You, Cewu Lu, Skeleton Merger: an Unsupervised Aligned Keypoint Detector,2021 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2021


7.  Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu, HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation, 2021 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2021


8.  Minghao Gou, Hao-Shu Fang, Zhanda Zhu, Sheng Xu, Chenxi Wang and Cewu Lu, RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images,2021 International Conference on Robotics and Automation (ICRA), 2021


9.  Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Xijie Huang, Liang Xu, Cewu Lu,Transferable Interactiveness Knowledge for Human-Object Interaction Detection, 2021 IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2021


10.  Bo Pang, Gao Peng, Yizhuo Li, Cewu Lu,PGT: A Progressive Method for Training Models on Long Videos,2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2021


11.  Hao-Shu Fang, Yichen Xie, Dian Shao, Cewu Lu,DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection,2021 35th AAAI Conference on Artificial Intelligence(AAAI),2021


12.  Hao-Shu Fang, Yichen Xie, Dian Shao, Yong-Lu Li, Cewu Lu,DecAug: Augmenting HOI Detection via Decomposition, 2021 35th AAAI Conference on Artificial Intelligence(AAAI),2021


13. Bo Pang , Yizhuo Li, Jiefeng Li, Muchen Li, Hanwen Cao, Cewu Lu, TDAF: Top-Down Attention Framework for Vision Tasks, 2021 35th AAAI Conference on Artificial Intelligence(AAAI),2021


14.  Gao Peng, Bo Pang, Cewu Lu, Efficient 3D Video Engine Using Frame Redundancy,  2021 IEEE Winter Conference on Applications of Computer Vision(WACV), 2021


15.  Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li,  Cewu Lu,HOI Analysis: Integrating and Decomposing Human-Object Interaction,2020 34th Conference on Neural Information Processing Systems (NeurIPS),2020


16.  Jiajun Tang, Jin Xia, Xinzhi Mu, Bo Pang, and Cewu Lu,Asynchronous Interaction Aggregation for Action Detection,2020 European Conference on Computer Vision(ECCV), 2020


17.  Can Wang, Jiefeng Li, Wentao Liu, Chen Qian, and Cewu Lu, HMOR: Hierarchical Multi-person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation,2020 European Conference on Computer Vision(ECCV), 2020


18. Yujing Lou, Yang You, Chengkun Li, Zhoujun Cheng, Liangwei Li,Lizhuang Ma, Weiming Wang, and Cewu Lu,Human Correspondence Consensus for 3D Object Semantic Understanding,2020 European Conference on Computer Vision(ECCV), 2020


19. Xiangyu Chen, Zelin Ye, Jiankai Sun, Yuda Fan, Fang Hu, Chenxi Wang, Cewu Lu,Transferable Active Grasping and Real Embodied Dataset,2020 International Conference on Robotics and Automation (ICRA), 2020


20.  Bo Pang, Kaiwen Zha, Hanwen Cao, Jiajun Tang, Minghui Yu & Cewu Lu, Complex sequential understanding through the awareness of spatial and temporal concepts, Nature Machine Intelligence,2020


21.  Hao-Shu Fang, Chenxi Wang, Minghao Gou,Cewu Lu,GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


22.  Bo Pang, Yizhuo Li, Yifan Zhang, Muchen Li, Cewu Lu, TubeTK: Adopting Tubes to Track Multi-Object in a Unified One-Step Model, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


23.  Jianhua Sun, Qinhong Jiang, Cewu Lu, Recursive Social Behavior Graph for Trajectory Prediction, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


24.  Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu,Shiyi Wang, Hao-Shu Fang, Ze Ma, Mingyang Chen, Cewu Lu,PaStaNet: Toward Human Activity Knowledge Engine, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


25.  Yong-Lu Li, Xinpeng Liu, Han Lu, Shiyi Wang, Junqi Liu, Jiefeng Li, Cewu Lu,Detailed 2D-3D Joint Representation for Human-Object Interaction, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


26.  Yong-Lu Li, Yue Xu, Xiaohan Mao, Cewu Lu,Symmetry and Group in Attribute-Object Compositions, 2020 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2020


27.  Zhengtian Xu, Shu Liu, Jianping Shi, Cewu Lu,Outdoor RGBD Instance Segmentation with Residual Regretting Learning,2020 IEEE Transactions on Image Processing(TIP), 2020