李潇

副教授

所在系所:机器人研究所

电子邮件:sjtu_lixiao@sjtu.edu.cn

通讯地址:上海交大350vip8888新葡的京集团

个人主页: /teacher_directory1/lixiao.html

个人简介
科研工作

教育背景

2015年9月-2019年12月 美国波士顿大学机械工程, 博士
2012年9月-2014年5月: 美国约翰霍普金斯大学, 硕士
2009年9月-2012年5月: 加拿大英属哥伦比亚大学, 学士

工作经历

2022.12-至今:350vip8888新葡的京集团,副教授
2020年3月-2022年11月: 美国麻省理工学院计算机科学与人工智能实验室 博士后
2014年5月-2015年8月: 美国约翰霍普金斯大学计算感知和机器人实验室 研究员

研究方向

研究方向:实验室旨在结合数据驱动(机器学习,神经网络等)和模型驱动(最优控制,规划等)的方法开发具有环境感知,理解,持续学习和安全执行能力的机器人系统。

研究课题:
* 增强学习 (reinforcement learning)
* 模仿学习 (imitation learning)
* 深度感知规划模型的压缩 (deep sensing-planning model compression)
* 环境感知和理解 (sensing and scene understanding)
* 知识表征和生成 (knowledge representation and generation)
* 轨迹预测和规划 (trajectory prediction and planning)

应用方向:
* 机器人的移动操作(mobile manipulation)
* 人机控制和交互模型的集成 (interactive and planning module integration)
* 自动导航(autonomous navigation)
* 机器人云和边缘计算(cloud and edge computing for robots)












代表性论文专著

【2023】
* S. Jiwani, X.Li, S.Karaman, D.Rus, Risk-Aware Neural Navigation From BEC Input for Interactive Driving, IEEE International Conference on Robots and Automation (ICRA), (2023) [pdf]

【2022】
* X.Li, G.Rosman, C.Vasile, I.Gilitschenski, S.Karaman, D.Rus, Learning An Explainable Trajectory Generator Using The Automaton Generative Network (AGN), IEEE Robotics and Automation Letters (RA-L)/ICRA, (2022) [pdf]
* Y.Ban, X.Li, G.Rosman, I.Gilitschenski, S.Karaman, D.Rus, Learning Semantic-Aware Trajectory Predictor Using Knowledge Graph Network, IEEE International Conference on Robots and Automation (ICRA), (2022) [pdf]
* B. Araki, J. Choi, L. Chin, K. Vodrahalli, X. Li, D. Rus, Learning Policies by Learning Rules, IEEE Robotics and Automation Letters (RA-L)/ICRA, (2022) [pdf]
* X. Li, J. Decastro, C. Vasile, S. Karaman, D. Rus, Learning a Risk-Aware Trajectory Planner From Demonstrations Using Logic Monitor, Conference on Robot Learning (CoRL) (2022) [pdf]

【2021】
* X.Li, G.Rosman, I.Gilitschenski, C.Vasile, J.A.DeCastro, S.karaman, D.Rus, Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features, IEEE Robotics and Automation Letters (RA-L) 6 (2021):3459-3466. [pdf]
* B. Araki, X. Li, K. Vodrahalli, J. DeCastro, M.J.Fry, D. Rus, The Logical Options Framework, International Conference on Machine Learning (ICML) (2021) [pdf]

【2020】
* C.I.Vasile, X.Li and C.Belta, Reactive Sampling-Based Path Planning with Temporal Logic Specifications, International Journal of Robotics Research (IJRR) 39 (2020): 1002-1028 [pdf]
* C.Sun, X.Li and C.Belta, Automata Guided Semi-Decentralized Multi-Agent Reinforcement Learning, American Control Conference (ACC) (2020): 3900-3905. [pdf]
* X.Li, G.Rosman, I.Gilitschenski, C.Vasile, J.A.DeCastro, S.Karaman, D.Rus, Differentiable Logic Layer for Rule Guided Trajectory Prediction, Conference on Robot Learning (CoRL), (2020) [pdf]

【2019】
* X.Li, Z.Serlin, Y.Guang and C.Belta, A Formal Methods Approach to Interpretable Reinforcement Learning for Robotic Planning, Science Robotics 4 (2019). [pdf]
* X.Li, C.Belta, Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions [pdf]

【2018】
* X.Li, Y.Ma and C.Belta, A Policy Search Method for Temporal Logic Specified Reinforcement Learning Task, American Control Conference (ACC), (2018): 240-245. [pdf]
* X.Li, C.Belta, Automata Guided Skill Composition, [pdf]

【2017】
* X.Li, C.I.Vasile and C.Belta, Reinforcement Learning With Temporal Logic Rewards, IEEE International Conference on Intelligent Robotics And Systems (IROS), (2017): 3834-3839. [pdf]
* X.Li, C.Belta, A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks, [pdf]

【2016】
* X.Li and P.Kazanzides, Task Frame Estimation During Model-Based Teleoperation for Satellite Servicing, IEEE International Conference on Robots and Automation (ICRA), (2016):2834-2839 [pdf]

【2015】
* X.Li and P.Kazanzides, Parameter Estimation And Anomaly Detection While Cutting Insulation During Telerobotic Satellite Servicing, IEEE International Conference on Intelligent Robots And Systems (IROS), (2015):4562-4567 [pdf]