师资力量

Faculty

头像

李光亮

职称: 副教授 学院: 电子工程学院 电子邮箱: guangliangli@ouc.edu.cn 办公室: 西海岸电子信息楼A313
  • 基本信息
  • 项目
  • 获奖
  • 论文
  • 课程
  • 教材或专著
  • 专利
  • Research Fields
  • Achievement
  • Social Appointments
  • Teaching Experience
  • Honor Title
  • Additional Information
  • 基本信息
    姓名: 李光亮 出生年月: 1986-08-10 最高学位:博士 入职海大时间: 2016
    主要研究方向:强化学习,机器人学习与自主控制,人机混合增强智能 专业技术职务:副教授 导师类别:博士生导师
    年均课时数: 是否第一学科:是
    国内外重要学术组织任职:自动化学会混合增强智能专委会委员,AAMAS、ICRA等顶尖学术会议分会主席、程序委员会委员
    获得人才称号名称及获得年份:
    其他情况简介: 李光亮,副教授,博士生导师,本科与硕士毕业于山东大学,2016年博士毕业于荷兰阿姆斯特丹大学(导师 Shimon Whiteson, 英国牛津大学教授),2014-2015年在代尔夫特理工大学、2015-2016年在Honda Research Institute Japan交流访问。主要从事人工智能与机器人领域研究,在深度强化学习、人机交互、机器人学习与自主控制等方面取得了多项具有影响力的创新性成果,成功应用于社交机器人与海洋机器人,并在日本本田与中国电科形成示范性应用。在人工智能与机器人领域权威学术期刊Nature Machine Intelligence、IEEE RA-L、IEEE汇刊、Ocean Engineering以及学术会议ICRA、IROS、AAMAS等发表论文60余篇,相关成果得到中美等国院士、ACM/IEEE/AAAS/AAAI Fellow、《Science Robotics》等知名学者团队和期刊的正面引用,取得广泛的国内外影响力。2018年荣获国际学术会议Nanjing City Prize(最佳技术论文奖)与全球知名服务机器人公司颁发的UBTech Prize。申请国家发明专利10项,授权国际发明专利1项。主持国家自然科学基金、国际合作项目、中央军委科技委项目等十余项。在ICML、ICRA、IEEE Humanoids等权威会议组织专题研讨会与竞赛,担任AAMAS、ICRA等顶尖学术会议分会主席、程序委员会委员,IEEE Transactions on Robotics及IEEE Transactions on Neural Network and Learning Systems等IEEE汇刊、Autonomous Robots、ICRA、IROS、AAMAS、NeurIPS 等期刊和会议审稿人,并与日本本田、MIT 、帝国理工学院等机构研究人员成立社交智能机器人联盟(Socially Intelligent Robotics Consortium)。李光亮现为IEEE、自动化学会、CAAI、CCF会员。欢迎感兴趣、有意愿加入课题组攻读博士与硕士学位的学生电联。课题组主页:https://www.guangliangli.net
    2017/01-2017/02,Honda Research Institute Japan,访问学者;2015/10-2016/04,Honda Research Institute Japan,研究实习;2014/10-2015/05,荷兰代尔夫特理工大学,访问学者。
  • 项目
    • 1. 国家自然科学基金委员会 青年基金 2019.01.01 ~ 2021.12.31 主持
    • 2. 中央军委科技委 “国家重点研发计划战略高技术重点专项” 2018.10 ~ 2020.06 主持
    • 3. Honda Research Institute Japan 国际合作研究项目 2017.01 ~ 2025.03 主持
    • 4. 山东省自然科学基金 青年基金 2018.03 ~ 2020.12 主持
    • 5. 中国博士后科学基金 面上项目 2017.07 ~ 2019.07 主持
    • 6. 中央高校基本科研业务费 青年教师专项基金 2016.10 ~ 2018.12 主持
    • 7. 青岛市科技局 青岛市博士后应用研究项目 2017.10 ~ 2019.03 主持
  • 获奖
    • 1. 2018 Nanjing City Prize (最佳技术论文奖) 1
    • 2. 2018 UBTech Prize 1
  • 论文
    • 1. Imitation learning from imperfect demonstrations for AUV path tracking and obstacle avoidance Ocean Engineering 2024.02 SCI 通讯作者
    • 2. Transferring Meta-Policy from Simulation to Reality via Progressive Neural Network IEEE Robotics and Automation Letters 2024.02 SCI 通讯作者
    • 3. Assisting Group Discussions Using Desktop Robot Haru International Conference on Robotics and Automation (ICRA) 2024.05 EI 通讯作者
    • 4. Shaping Social Robot to Play Games with Human Demonstrations and Evaluative Feedback International Conference on Robotics and Automation (ICRA) 2024.05 EI 通讯作者
    • 5. Emotional Understanding for Social Robot Haru via Human-Centered Reinforcement Learning The 15th International Conference on Social Robotics 2023.10 EI 通讯作者
    • 6. Model-based Adversarial Imitation Learning from Demonstrations and Human Reward IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023.06 EI 通讯作者
    • 7. Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model 2023 IEEE International Conference on Robotics and Automation (ICRA) 2023.05 EI 通讯作者
    • 8. GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback 2023 IEEE International Conference on Robotics and Automation (ICRA) 2023.05 EI 通讯作者
    • 9. Where to Look during Conversation: Autonomous Attentive Behavior Learning for Social Robot via Deep Reinforcement Learning The 2023 International Conference on Robotics and Automation (ICRA) Workshop: Balanced Cyberphysical Society 2023.05 通讯作者
    • 10. Emotional Understanding for Social Robot Haru via Human-Centered Reinforcement Learning The 2023 International Conference on Robotics and Automation (ICRA) Workshop: Balanced Cyberphysical Society 2023.05 通讯作者
    • 11. Transferring policy of deep reinforcement learning from simulation to reality for robotics Nature Machine Intelligence 2022.12 SCI 通讯作者
    • 12. Imitating Human Strategy for Social Robot in Real-Time Two-Player Games International Conference on Social Robotics 2022.12 通讯作者
    • 13. Personalized Storytelling with Social Robot Haru International Conference on Social Robotics 2022.12 通讯作者
    • 14. Action Guidance-Based Deep Interactive Reinforcement Learning for AUV Path Planning 2022 International Conference on Machine Learning, Control, and Robotics 2022.10 EI 通讯作者
    • 15. Continuous Control for Autonomous Underwater Vehicle Path Following Using Deep Interactive Reinforcement Learning 2022 International Conference on Machine Learning, Control, and Robotics 2022.10 EI 通讯作者
    • 16. Autonomous Underwater Vehicle Formation Control and Obstacle Avoidance Using Multi-Agent Generative Adversarial Imitation Learning Ocean Engineering 2022.08 SCI 通讯作者
    • 17. Generative Adversarial Interactive Imitation Learning for Path Following of Autonomous Underwater Vehicle Ocean Engineering 2022.07 SCI 通讯作者
    • 18. Affective Behavior Learning for Social Robot Haru with Implicit Evaluative Feedback 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022.06 EI 通讯作者
    • 19. Shaping Haru's Affective Behavior with Valence and Arousal Based Implicit Facial Feedback 2022 31st IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2022.05 EI 通讯作者
    • 20. Shaping Progressive Net of Reinforcement Learning for Policy Transfer with Human Evaluative Feedback 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021) 2021.09 EI 通讯作者
    • 21. Path planning and obstacle avoidance for AUV: A review Ocean Engineering 2021.09 SCI 通讯作者
    • 22. Shaping Affective Robot Haru’s Reactive Response 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2021.06 EI 通讯作者
    • 23. Automating Behavior Selection for Affective Telepresence Robot 2021 International Conference on Robotics and Automation (ICRA 2021) 2021.05 EI 通讯作者
    • 24. Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework The 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2021.05 EI 第一作者,通讯作者
    • 25. A Review on Interactive Reinforcement Learning from Human Social Feedback IEEE Access 2020 SCI 通讯作者
    • 26. Deep Interactive Reinforcement Learning for Path Tracking of Autonomous Underwater Robots IEEE Access 2020 SCI 通讯作者
    • 27. Facial feedback for reinforcement learning: a case study and offline analysis using the TAMER framework Autonomous Agents and Multi-Agent Systems 2020.02 SCI 第一作者,通讯作者
    • 28. NavNet: AUV Navigation through Deep Sequential Learning IEEE Access 2020 SCI 共同通讯
    • 29. Human Social Feedback for Efficient Interactive Reinforcement Agent Learning 29th IEEE RO-MAN 2020 EI 通讯作者
    • 30. Human-Centered Reinforcement Learning: A Survey IEEE Transactions on Human-Machine Systems 2019.08 SCI 第一作者,通讯作者
    • 31. Social Interaction for Effective Agent Learning from Human Reward Autonomous Agents and Multi-Agent Systems 2018 SCI 第一作者,通讯作者
    • 32. Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback 27th IEEE RO-MAN (Nanjing City Prize and UBTech Prize) 2018 EI 第一作者,通讯作者
    • 33. Using Informative Behavior to Increase Engagement While Learning from Human Reward Autonomous Agents and Multi-Agent Systems 2016 SCI 第一作者,通讯作者
    • 34. Towards Learning from Implicit Human Reward 15th International Conference on Autonomous Agents and Multi-agent Systems 2016 EI 第一作者,通讯作者
    • 35. Reinforcement Learning from Demonstration and Human Reward 15th workshop on Adaptive Learning Agents at AAMAS 2016.05 第一作者,通讯作者
    • 36. A Large-Scale Study of Agents Learning from Human Reward 14th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS) 2015 EI 第一作者,通讯作者
    • 37. Learning from Human Reward Benefits from Socio-competitive Feedback 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2014) 2014 EI 第一作者,通讯作者
    • 38. Leveraging Social Networks to Motivate Humans to Train Agents 13th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS) 2014 EI 第一作者,通讯作者
    • 39. The Reinforcement Learning Competition 2014 AI Magazine (受邀请) 2014 SCI 通讯作者
    • 40. Using Informative Behavior to Increase Engagement in the TAMER Framework 12th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS 2013) 2013 EI 第一作者,通讯作者
  • 课程
    • 1. 信号与系统 本科生专业基础课 3.5 56
    • 2. 电路分析基础 本科生专业基础课 3 48
    • 3. 矩阵分析引论 研究生专业课 3 48
    • 4. 人工智能 选修 1 16
  • 教材或专著
  • 专利
  • 成果转化与社会服务
  • Research Fields
  • Achievement
    • 1. 国家自然科学基金委员会 青年基金 2019.01.01 ~ 2021.12.31 主持
    • 2. 中央军委科技委 “国家重点研发计划战略高技术重点专项” 2018.10 ~ 2020.06 主持
    • 3. Honda Research Institute Japan 国际合作研究项目 2017.01 ~ 2025.03 主持
    • 4. 山东省自然科学基金 青年基金 2018.03 ~ 2020.12 主持
    • 5. 中国博士后科学基金 面上项目 2017.07 ~ 2019.07 主持
    • 6. 中央高校基本科研业务费 青年教师专项基金 2016.10 ~ 2018.12 主持
    • 7. 青岛市科技局 青岛市博士后应用研究项目 2017.10 ~ 2019.03 主持
  • Social Appointments
    • 1. 2018 Nanjing City Prize (最佳技术论文奖) 1
    • 2. 2018 UBTech Prize 1
  • Teaching Experience
    • 1. Imitation learning from imperfect demonstrations for AUV path tracking and obstacle avoidance Ocean Engineering 2024.02 SCI 通讯作者
    • 2. Transferring Meta-Policy from Simulation to Reality via Progressive Neural Network IEEE Robotics and Automation Letters 2024.02 SCI 通讯作者
    • 3. Assisting Group Discussions Using Desktop Robot Haru International Conference on Robotics and Automation (ICRA) 2024.05 EI 通讯作者
    • 4. Shaping Social Robot to Play Games with Human Demonstrations and Evaluative Feedback International Conference on Robotics and Automation (ICRA) 2024.05 EI 通讯作者
    • 5. Emotional Understanding for Social Robot Haru via Human-Centered Reinforcement Learning The 15th International Conference on Social Robotics 2023.10 EI 通讯作者
    • 6. Model-based Adversarial Imitation Learning from Demonstrations and Human Reward IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023.06 EI 通讯作者
    • 7. Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model 2023 IEEE International Conference on Robotics and Automation (ICRA) 2023.05 EI 通讯作者
    • 8. GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback 2023 IEEE International Conference on Robotics and Automation (ICRA) 2023.05 EI 通讯作者
    • 9. Where to Look during Conversation: Autonomous Attentive Behavior Learning for Social Robot via Deep Reinforcement Learning The 2023 International Conference on Robotics and Automation (ICRA) Workshop: Balanced Cyberphysical Society 2023.05 通讯作者
    • 10. Emotional Understanding for Social Robot Haru via Human-Centered Reinforcement Learning The 2023 International Conference on Robotics and Automation (ICRA) Workshop: Balanced Cyberphysical Society 2023.05 通讯作者
    • 11. Transferring policy of deep reinforcement learning from simulation to reality for robotics Nature Machine Intelligence 2022.12 SCI 通讯作者
    • 12. Imitating Human Strategy for Social Robot in Real-Time Two-Player Games International Conference on Social Robotics 2022.12 通讯作者
    • 13. Personalized Storytelling with Social Robot Haru International Conference on Social Robotics 2022.12 通讯作者
    • 14. Action Guidance-Based Deep Interactive Reinforcement Learning for AUV Path Planning 2022 International Conference on Machine Learning, Control, and Robotics 2022.10 EI 通讯作者
    • 15. Continuous Control for Autonomous Underwater Vehicle Path Following Using Deep Interactive Reinforcement Learning 2022 International Conference on Machine Learning, Control, and Robotics 2022.10 EI 通讯作者
    • 16. Autonomous Underwater Vehicle Formation Control and Obstacle Avoidance Using Multi-Agent Generative Adversarial Imitation Learning Ocean Engineering 2022.08 SCI 通讯作者
    • 17. Generative Adversarial Interactive Imitation Learning for Path Following of Autonomous Underwater Vehicle Ocean Engineering 2022.07 SCI 通讯作者
    • 18. Affective Behavior Learning for Social Robot Haru with Implicit Evaluative Feedback 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022.06 EI 通讯作者
    • 19. Shaping Haru's Affective Behavior with Valence and Arousal Based Implicit Facial Feedback 2022 31st IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2022.05 EI 通讯作者
    • 20. Shaping Progressive Net of Reinforcement Learning for Policy Transfer with Human Evaluative Feedback 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021) 2021.09 EI 通讯作者
    • 21. Path planning and obstacle avoidance for AUV: A review Ocean Engineering 2021.09 SCI 通讯作者
    • 22. Shaping Affective Robot Haru’s Reactive Response 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2021.06 EI 通讯作者
    • 23. Automating Behavior Selection for Affective Telepresence Robot 2021 International Conference on Robotics and Automation (ICRA 2021) 2021.05 EI 通讯作者
    • 24. Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework The 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2021.05 EI 第一作者,通讯作者
    • 25. A Review on Interactive Reinforcement Learning from Human Social Feedback IEEE Access 2020 SCI 通讯作者
    • 26. Deep Interactive Reinforcement Learning for Path Tracking of Autonomous Underwater Robots IEEE Access 2020 SCI 通讯作者
    • 27. Facial feedback for reinforcement learning: a case study and offline analysis using the TAMER framework Autonomous Agents and Multi-Agent Systems 2020.02 SCI 第一作者,通讯作者
    • 28. NavNet: AUV Navigation through Deep Sequential Learning IEEE Access 2020 SCI 共同通讯
    • 29. Human Social Feedback for Efficient Interactive Reinforcement Agent Learning 29th IEEE RO-MAN 2020 EI 通讯作者
    • 30. Human-Centered Reinforcement Learning: A Survey IEEE Transactions on Human-Machine Systems 2019.08 SCI 第一作者,通讯作者
    • 31. Social Interaction for Effective Agent Learning from Human Reward Autonomous Agents and Multi-Agent Systems 2018 SCI 第一作者,通讯作者
    • 32. Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback 27th IEEE RO-MAN (Nanjing City Prize and UBTech Prize) 2018 EI 第一作者,通讯作者
    • 33. Using Informative Behavior to Increase Engagement While Learning from Human Reward Autonomous Agents and Multi-Agent Systems 2016 SCI 第一作者,通讯作者
    • 34. Towards Learning from Implicit Human Reward 15th International Conference on Autonomous Agents and Multi-agent Systems 2016 EI 第一作者,通讯作者
    • 35. Reinforcement Learning from Demonstration and Human Reward 15th workshop on Adaptive Learning Agents at AAMAS 2016.05 第一作者,通讯作者
    • 36. A Large-Scale Study of Agents Learning from Human Reward 14th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS) 2015 EI 第一作者,通讯作者
    • 37. Learning from Human Reward Benefits from Socio-competitive Feedback 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2014) 2014 EI 第一作者,通讯作者
    • 38. Leveraging Social Networks to Motivate Humans to Train Agents 13th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS) 2014 EI 第一作者,通讯作者
    • 39. The Reinforcement Learning Competition 2014 AI Magazine (受邀请) 2014 SCI 通讯作者
    • 40. Using Informative Behavior to Increase Engagement in the TAMER Framework 12th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS 2013) 2013 EI 第一作者,通讯作者
  • Honor Title
    • 1. 信号与系统 本科生专业基础课 3.5 56
    • 2. 电路分析基础 本科生专业基础课 3 48
    • 3. 矩阵分析引论 研究生专业课 3 48
    • 4. 人工智能 选修 1 16
  • Additional Information
    欢迎感兴趣、有意愿加入课题组攻读博士与硕士学位的学生电联。个人主页:https://www.guangliangli.net