基本信息
蔡莹皓  女  硕导  中国科学院自动化研究所
电子邮件: yinghao.cai@ia.ac.cn
通信地址: 北京海淀区中关村东路95号
邮政编码:

研究领域

机器人操作技能的视觉特征学习、机器人感知-决策联合学习

招生信息

   
招生专业
081101-控制理论与控制工程
招生方向
机器人视觉抓取,机器人模仿学习,自主学习

教育背景

2003-09--2009-06   中国科学院自动化研究所   模式识别与智能系统,博士学位
1999-09--2003-06   中南大学   计算机科学与技术,学士

工作经历

2015-11~至今,中科院自动化所,副研究员

2014-11~2015-11,中科院自动化所,助理研究员

2011-06~2014-10,美国南加州大学, Postdoctoral Fellow

2009-06~2011-06,芬兰奥卢大学, Senior Research Scientist


专利与奖励

   
奖励信息
(1) CVPR2019视觉定位竞赛第三名, , 其他, 2019
(2) Mobile Multimedia Computing研讨会最佳论文奖, 其他, 2015
(3) ECCV多摄像机目标跟踪竞赛第一名, , 其他, 2014
专利成果
[1] 刘巍, 温大勇, 鲁涛, 蔡莹皓, 杨彩云, 葛悦光, 李朋, 常文凯, 王硕. 用于连接ROS的通讯系统. CN: CN110955536A, 2020-04-03.

[2] 葛悦光, 温大勇, 蔡莹皓, 鲁涛, 刘巍, 李朋, 常文凯, 王硕. 消防机器人和基于云平台架构的消防机器人系统. CN: CN110888442A, 2020-03-17.

[3] 王硕, 刘乃军, 鲁涛, 蔡莹皓, 席宝. 基于虚拟现实的机器人远程示教系统. CN: CN107263449B, 2020-01-10.

[4] 王硕, 席宝, 鲁涛, 蔡莹皓, 刘乃军. 基于视觉的遥操作机器人控制系统及方法. CN: CN107363831B, 2020-01-10.

[5] 王硕, 李朋, 杨彩云, 鲁涛, 温大勇, 蔡莹皓, 常文凯, 王睿, 刘巍, 葛悦光. 一种具备在线地图构建和导航功能的自主消防机器人系统. CN: CN110201340A, 2019-09-06.

[6] 谭铁牛, 黄凯奇, 蔡莹皓. 基于多摄像机的目标连续跟踪方法. 中国: CN101751677A, 2010-06-23.

[7] 谭铁牛, 黄凯奇, 蔡莹皓. 基于信息融合的夜间视觉监控方法. 中国: CN101409825, 2009.04.15.

出版信息

   
发表论文
[1] 邢晓霞, 蔡莹皓, 鲁涛, 杨一平, 温大勇. Joint Self-Supervised Monocular Depth Estimation and SLAM. International Conference on Pattern Recognitionnull. 2022, [2] 李佳怡, 鲁涛, 曹笑歌, 蔡莹皓, 王硕. Meta-Imitation Learning by Watching Video Demonstrations. International Conference on Learning Representationsnull. 2022, [3] Hao, Peng, Lu, Tao, Cui, Shaowei, Wei, Junhang, Cai, Yinghao, Wang, Shuo. Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2022, 7(2): 3656-3663, [4] Liu, Naijun, 鲁涛, 蔡莹皓, 王睿, 王硕. Manipulation skill learning on multi-step complex task based on explicit and implicit curriculum learning. SCIENCE CHINA-INFORMATION SCIENCES[J]. 2022, 65(1): http://dx.doi.org/10.1007/s11432-019-2648-7.
[5] Lu, Ning, Cai, Yinghao, Lu, Tao, Cao, Xiaoge, Guo, Weiyan, Wang, Shuo. Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter. ROBOTICA. 2022, [6] 李博遥, 李佳怡, 鲁涛, 蔡莹皓, 王硕. Hierarchical Learning from Demonstrations for Long-Horizon Tasks. International conference on robotics & automation (ICRA)null. 2021, [7] 邢晓霞, 蔡莹皓, 鲁涛, 杨一平, 温大勇. 3DTDesc: learning local features using 2D and 3D cues. MACHINE VISION AND APPLICATIONS[J]. 2021, 32(3): http://dx.doi.org/10.1007/s00138-021-01176-8.
[8] Xi, Bao, Wang, Rui, Cai, YingHao, Lu, Tao, Wang, Shuo. A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory. INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING[J]. 2021, 18(4): 619-631, http://dx.doi.org/10.1007/s11633-021-1296-x.
[9] 郝鹏, 鲁涛, 崔少伟, 魏俊杭, 蔡莹皓, 王硕. SOZIL: Self-Optimal Zero-shot Imitation Learning. Ieee transactions on cognitive and developmental systems[J]. 2021, [10] 李佳怡, 李博遥, 鲁涛, 卢宁, 蔡莹皓, 王硕. DIMSAN: Fast Exploration with the Synergy between Density-based Intrinsic Motivation and Self-adaptive Action Noise. IEEE International Conference on Robotics and Automation, ICRA 2021null. 2021, [11] Li, Boyao, Lu, Tao, Li, Jiayi, Lu, Ning, Cai, Yinghao, Wang, Shuo, IEEE. ACDER: Augmented Curiosity-Driven Experience Replay. 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)[J]. 2020, 4218-4224, [12] Liu, Naijun, Cai, Yinghao, Lu, Tao, Wang, Rui, Wang, Shuo. Real-Sim-Real Transfer for Real-World Robot Control Policy Learning with Deep Reinforcement Learning. APPLIED SCIENCES-BASEL[J]. 2020, 10(5): https://www.webofscience.com/wos/woscc/full-record/WOS:000525298100003.
[13] Naijun Liu, 蔡莹皓, Tao Lu, Rui Wang, Shuo Wang. Real–Sim–Real Transfer for Real-World Robot Control Policy Learning with Deep Reinforcement Learning. Applied Sciences[J]. 2020, 10(5): https://doaj.org/article/999c6c3f45c441c88e3cd95711828acb.
[14] xing xiaoxia, cai yinghao, Lu, Tao, yang yiping, 温大勇. Dynamic Guided Network for Monocular Depth Estimation. International Conference on Pattern Recognition[J]. 2020, [15] Xin, Zhe, Cai, Yinghao, Lu, Tao, Xing, Xiaoxia, Cai, Shaojun, Zhang, Jixiang, Yang, Yiping, Wang, Yanqing. Localizing Discriminative Visual Landmarks for Place Recognition. 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)[J]. 2019, 5979-5985, [16] Chang, Wenkai, Li, Peng, Yang, Caiyun, Lu, Tao, Cai, Yinghao, Wang, Shuo, IEEE. Self-modeling Tracking Control of Crawler Fire Fighting Robot Based on Causal Network. 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)null. 2019, 3911-3917, [17] li xiaocan, 蔡莹皓, 鲁涛, Wang, Shuo. Learning Category-level Implicit 3D Rotation Representations for 6D Pose Estimation from RGB Images. IEEE International Conference on Robotics and Biomimetics (ROBIO)[J]. 2019, [18] 鲁涛. Programming by Visual Demonstration for Pick-and-Place Tasks using Robot Skills. IEEE International Conference on Robotics and Biomimetics (ROBIO). 2019, [19] 刘乃军, 鲁涛, 蔡莹皓, 王硕. 机器人操作技能学习方法综述. 自动化学报[J]. 2019, 458-470, http://lib.cqvip.com/Qikan/Article/Detail?id=77798479504849574851484850.
[20] 于灏, 杜华军, 蔡莹皓, 鲁涛, 王睿, 王硕. 基于改进SIFT-ICP算法的物体点云建模方法. 高技术通讯. 2019, 29(8): 750-757, http://lib.cqvip.com/Qikan/Article/Detail?id=7002773468.
[21] Xi, Bao, Wang, Shuo, Ye, Xuemei, Cai, Yinghao, Lu, Tao, Wang, Rui. A robotic shared control teleoperation method based on learning from demonstrations. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS[J]. 2019, 16(4): 1-13, https://doaj.org/article/76ecf0f0692a4145b1b873fac451d531.
[22] Xin, Zhe, Cai, Yinghao, Cai, Shaojun, Zhang, Jixiang, Yang, Yiping, Wang, Yanqing, IEEE. Visual Localization in Changing Environments using Place Recognition Techniques. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)null. 2018, 1785-1790, [23] Xin Zhe, Cai Yinghao, Zhang Jixiang, Yang Yiping, Wang Yanqing, IEEE. Probabilistic Voting for Sequence Based Visual Place Recognition. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)null. 2018, 1791-1796, [24] Xing, Xiaoxia, Cai, Yinghao, Lu, Tao, Cai, Shaojun, Yang, Yiping, Wen, Dayong, IEEE. 3DTNet: Learning Local Features using 2D and 3D Cues. 2018 INTERNATIONAL CONFERENCE ON 3D VISION (3DV)null. 2018, 435-443, [25] 曹淼, 杜学丹, 王硕, 鲁涛, 蔡莹皓, 闫哲. 基于深度学习的机器人抓取位置检测方法. 高技术通讯. 2018, 28(1): 58-66, http://lib.cqvip.com/Qikan/Article/Detail?id=675012122.
[26] Cai, Yinghao, Lu, Ying, Kim, Seon Ho, Nocera, Luciano, Shahabi, Cyrus. Querying geo-tagged videos for vision applications using spatial metadata. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING[J]. 2017, 2017(1): http://dx.doi.org/10.1186/s13640-017-0165-6.
[27] Du Xuedan, Cai Yinghao, Zhang Leijie, Wang Shuo. Overview of Deep Learning. 2017, http://ir.ia.ac.cn/handle/173211/20870.
[28] 杜学丹, 蔡莹皓, 王硕, 闫哲, 鲁涛. 一种基于深度学习的机械臂抓取方法. 机器人[J]. 2017, 39(6): 820-828,837, [29] Li, Yonglu, Cai, Yinghao, Wen, Dayong, Yang, Yiping, IEEE. Optimization of Radial Distortion Self-Calibration for Structure from Motion from Uncalibrated UAV Images. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)null. 2016, 3721-3726, [30] Chen Xinze, Chen Guangliang, Cai Yinghao, Wen Dayong, Li Heping. Semantic Segmentation with Modified Deep Residual Networks. Proceedings of Chinese Conference on Pattern Recognitionnull. 2016, http://ir.ia.ac.cn/handle/173211/14458.
[31] Cai, Yinghao, Medioni, Gerard. Persistent people tracking and face capture using a PTZ camera. MACHINE VISION AND APPLICATIONS[J]. 2016, 27(3): 397-413, http://ir.ia.ac.cn/handle/173211/10991.
[32] Du Xuedan, Cai Yinghao, Wang Shuo, Zhang Leijie, IEEE. Overview of Deep Learning. 2016 31ST YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC)[J]. 2016, 159-164, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000392695100027.
[33] Shachaf Melman, Yael Moses, Gerard Medioni, Yinghao Cai. The multi-strand graph for a PTZ tracker. IEEE International Conference on Advanced Video and Signal Based Surveillancenull. 2015, http://ir.ia.ac.cn/handle/173211/10978.
[34] Yinghao Cai, Ying Lu, SeonHo Kim, Luciano Nocera, Cyrus Shahabi. Gift: A geospatial image and video filtering tool for computer vision applications with geo-tagged mobile videos. IEEE International Conference on Multimedia and Exponull. 2015, http://ir.ia.ac.cn/handle/173211/10977.
[35] He, Ran, Cai, Yinghao, Tan, Tieniu, Davis, Larry. Learning predictable binary codes for face indexing. PATTERN RECOGNITION[J]. 2015, 48(10): 3160-3168, http://dx.doi.org/10.1016/j.patcog.2015.03.016.
[36] Yinghao Cai, Gerard Medioni. Exploring Context Information for Inter-Camera Multiple Target Tracking. IEEE Winter Conference on Applications of Computer Visionnull. 2014, http://ir.ia.ac.cn/handle/173211/10979.
[37] Gerard Medioni, Yinghao Cai. Persistent People Tracking and Face Capture Over a Wide Area. IEEE Conference on Computer Vision and Pattern Recognition Workshopnull. 2014, http://ir.ia.ac.cn/handle/173211/10980.
[38] Cyrus Shahabi, Seon Ho Kim, Luciano Nocera, Giorgos Constantinou, Ying Lu, Yinghao Cai, Gerard Medioni, Ramakant Nevatia, Farnoush BanaeiKashani. Janus - Multi Source Event Detection and Collection System for Effective Surveillance of Criminal Activity. Journal of Information Processing Systems[J]. 2014, 1-22, http://ir.ia.ac.cn/handle/173211/10976.
[39] Yinghao Cai, Thang Dinh, Gerard Medioni. Towards a practical PTZ Face Detection and Tracking System. IEEE Workshop on Applications of Computer Visionnull. 2013, http://ir.ia.ac.cn/handle/173211/10981.
[40] Cai Yinghao, Medioni Gerard, Thang Ba Dinh, IEEE. Towards a Practical PTZ Face Detection and Tracking System. 2013 IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION (WACV)null. 2013, 31-38, [41] Yinghao Cai, Gerard Medioni. Demo:Persistent People Tracking and Face Capture using a PTZ Camera. International Conference on Distributed Smart Camerasnull. 2013, http://ir.ia.ac.cn/handle/173211/10982.
[42] Yinghao Cai, Valtteri Takala, Matti Pietikainen. Matching Groups of People by Covariance Descriptor. International Conference on Pattern Recognitionnull. 2010, http://ir.ia.ac.cn/handle/173211/10984.
[43] Yinghao Cai, Matti Pietikainen. Person Re-identification Based on Global Color Context. 10th Asian Conference on Computer Visionnull. 2010, http://ir.ia.ac.cn/handle/173211/10983.
[44] Valtteri Takala, Yinghao Cai, Matti Pietikainen. Boosting Clusters of Samples for Sequence Matching in Camera Networks. International Conference on Pattern Recognitionnull. 2010, http://ir.ia.ac.cn/handle/173211/10985.
[45] Cai Yinghao, Tan Tieniu, Huang Kaiqi. Recovering the topology of multiple cameras by finding continuous paths in a trellis. International Conference on Pattern Recognition (ICPR)null. 2010, 3541-3544, http://ir.ia.ac.cn/handle/173211/5377.
[46] 蔡莹皓. 非重叠多摄像机场景下的目标连续跟踪. 2009, http://www.irgrid.ac.cn/handle/1471x/976825.
[47] Yinghao Cai, Kaiqi Huang, Tieniu Tan. Matching Tracking Sequences Across Widely Separated Cameras. IEEE International Conference on Image Processingnull. 2008, http://ir.ia.ac.cn/handle/173211/10986.
[48] Cai Yinghao, Huang Kaiqi, Tan Tieniu, IEEE. MATCHING TRACKING SEQUENCES ACROSS WIDELY SEPARATED CAMERAS. 2008 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGSnull. 2008, 769-772, [49] Yinghao Cai, Kaiqi Huang, Tieniu Tan. Human Appearance Matching Across Multiple Non-overlapping Cameras. International Conference on Pattern Recognitionnull. 2008, http://ir.ia.ac.cn/handle/173211/10987.
[50] Cai, Yinghao, Huang, Kaiqi, Tan, Tieniu, IEEE. Human Appearance Matching Across Multiple Non-overlapping Cameras. 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6null. 2008, 1994-1997, [51] Zhang Zhaoxiang, Cai Yinghao, Huang Kaiqi, Tan Tieniu, IEEE. Real-time moving object classification with automatic scene division. 2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7null. 2007, 2401-2404, [52] Yinghao Cai, Wei Chen, Kaiqi Huang, Tieniu Tan. Continuously Tracking Objects Across Multiple Widely Separated Cameras. The 8th Asian Conference on Computer Visionnull. 2007, http://ir.ia.ac.cn/handle/173211/10988.
[53] Cai Yinghao, Chen Wei, Huang Kaiqi, Tan Tieniu, Yagi Y, Kang SB, Kweon IS, Zha H. Continuously tracking objects across multiple widely separated cameras. COMPUTER VISION - ACCV 2007, PT I, PROCEEDINGSnull. 2007, 4843: 843-852, [54] Yinghao Cai, Kaiqi Huang, Yunhong Wang, Tieniu Tan. Context Enhancement of Nighttime Surveillance by Image Fusion. International Conference on Pattern Recognitionnull. 2006, http://ir.ia.ac.cn/handle/173211/10990.

科研活动

   
科研项目
( 1 ) 基于多源视频的大范围场景目标跟踪, 负责人, 国家任务, 2016-01--2018-12
( 2 ) 面向空间在轨灵巧操作的机器人模仿学习研究, 负责人, 其他任务, 2019-01--2020-12
( 3 ) 机器人知识和技能获取与增长的人工智能和机器学习理论与方法, 参与, 国家任务, 2018-01--2020-12
( 4 ) 基于多模态传感关联与多层次知识协同的视觉测量理论与方法研究, 参与, 国家任务, 2018-01--2020-12
( 5 ) 水下机器人自主感知、导航与控制, 参与, 国家任务, 2018-01--2020-01
( 6 ) 基于镜像神经机制的操作技能自主学习技术研究, 参与, 地方任务, 2017-01--2018-12
( 7 ) 室外大范围复杂动态场景安保机器人长期导航与场景理解, 负责人, 国家任务, 2020-01--2023-12
( 8 ) 自主无人系统的开放通用高端智能控制器, 负责人, 国家任务, 2022-06--2025-05

指导学生

现指导学生

郑力铭  硕士研究生  085400-电子信息  

马文轩  硕士研究生  081101-控制理论与控制工程