刘华平

2021.03.31 11:36

职称 教授 电话
邮箱 hpliu@tsinghua.edu.cn

undefined

姓名:刘华平

职称:教授

电子邮件:hpliu@tsinghua.edu.cn

教育背景

工学学士 (机械工程), 上海理工大学, 中国, 1997

工学硕士 (电气工程), 同济大学, 中国, 2000

工学博士 (计算机科学与技术), 清华大学, 中国, 2004

学术兼职

Senior Editor, International Journal of Robotics Research(2023-present)

Associate Editor, IEEE Transactions on Cybernetics (2020-2023)

Associate Editor, IEEE Transactions on Automation Science and Engineering (2017-2020)

Area Chair, Robotics Science and Systems (RSS), 2018-2019, 2021-2022

中国人工智能学会理事

中国人工智能学会“认知系统与信息处理专业委员会”副主任

中国自动化学会“智能自动化专业委员会”秘书长

研究领域

智能机器人感知、学习与控制

研究概况

针对灵巧机械手、移动机器人,提出了多模态异构信息融合的结构化稀疏编码方法、交互式主动感知的层次化强化学习方法,以及跨模态持续更新的增量式学习方法,克服现有方法割裂了感知、学习与动作之间联系的缺点,为解决机器人对开放环境的感知,以及对动态任务的适应提供了新的解决途径

研究项目

国家杰出青年科学基金项目:机器人智能感知与学习(62025304):2021-2025

国家自然科学基金国际合作重点项目:机器人具身触觉感知与学习的基础理论与关键技术(62120106005):2022-2026

学术成果

1. Embodied multi-agent task planning from ambiguous instruction, in: Proc. of Robotics: Science and Systems (RSS), 2022

2. Continual learning with recursive gradient optimization, in: Prof. of International Conference on Learning Represenation (ICLR), 2022

3. MQA: Answering the question via robotic manipulation. in: Proc. of Robotics: Science and Systems (RSS), 2021

4. Understanding the Behaviour of Contrastive Loss, in: Proc. of Computer Vision and Pattern Recognition (CVPR), 2021

5. Lifelong visual-tactile cross-modal learning for robotic material perception, IEEE Transactions on Neural Networks and Learning Systems, 2021

6. Toward image-to-tactile cross-modal perception for visually impaired people, IEEE Transactions on Automation Science and Technology, 2021

7. Embodied semantic scene graph generation, Conference on Robot Learning (CoRL), 2021

8. Towards embodied scene description, in: Proc. of Robotics: Science and Systems (RSS), 2020

9. Multi-agent embodied question answering in interactive environments, in: Proc. of European Conference on Computer Vision (ECCV), 2020

10. Unsupervised representation learning by invariance propagation, Advances in Neural Information Processing Systems (NeurIPS), 2020

上一篇:刘洋

下一篇:马少平

关闭