Mingyu Cai

Mingyu Cai

Assistant Professor, Department of Mechanical Engineering, University of California Riverside

Journal Papers

  1. Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications.
    Mingyu Cai, Erfan Aasi, Calin Belta, Cristian-Ioan Vasile. IEEE Robotics and Automation Letters (RA-L), 2023. [Video] [Bibtex] [PDF]

  2. Safety-Critical Modular Deep Reinforcement Learning with Temporal Logic through Gaussian Processes and Control Barrier Functions.
    Mingyu Cai, Cristian-Ioan Vasile. Under Review, 2022. [Video] [PDF]

  3. Optimal Probabilistic Motion Planning with Potential Infeasible LTL Constraints.
    Mingyu Cai, Shaoping Xiao, Zhijun Li, Zhen Kan. IEEE Transactions on Automatic Control (TAC), 2022. [Bibtex] [PDF]

  4. Intelligent Traffic Light via Policy-based Deep Reinforcement Learning.
    Yue Zhu, Mingyu Cai, Chris W. Schwarz, Junchao Li, Shaoping Xiao. International Journal of Intelligent Transportation Systems Research 2022. [Bibtex] [PDF]

  5. Online Motion Planning with Soft Metric Interval Temporal Logic in Unknown Dynamic Environment.
    Zhiliang Li, Mingyu Cai*, Shaoping Xiao, Zhen Kan. IEEE Control Systems Letters (L-CSS), 2022. [Bibtex] [PDF] [Video]

  6. Probabilistic Coordination of Heterogeneous Teams From Capability Temporal Logic Specifications.
    Mingyu Cai, Kevin Leahy, Zachary Serlin, Cristian-Ioan Vasile. IEEE Robotics and Automation Letters (RA-L), 2022. [Bibtex] [PDF]

  7. Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic.
    Mingyu Cai, Mohammadhosein Hasanbeig, Shaoping Xiao, Alessandro Abate, Zhen Kan. IEEE Robotics and Automation Letters (RA-L), 2021. [Bibtex] [PDF] [Demo] [Code]

  8. Receding Horizon Control-Based Motion Planning With Partially Infeasible LTL Specifications.
    Mingyu Cai, Hao Peng, Zhijun Li, Hongbo Gao, Zhen Kan. IEEE Control Systems Letters (L-CSS), 2020. [Bibtex] [PDF] [Video] [Code]

  9. Learning-based probabilistic LTL motion planning with environment and motion uncertainties.
    Mingyu Cai, Hao Peng, Zhijun Li, Zhen Kan. IEEE Transactions on Automatic Control (TAC), 2020. [Bibtex] [PDF]

Conference Papers

  1. Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications.
    Mingyu Cai, Makai Mann, Zachary Serlin, Kevin Leahy, Cristian-Ioan Vasile. IEEE American Control Conference (ACC), San Diego, USA, May, 2023. [Video] [Bibtex] [PDF]

  2. Learning Signal Temporal Logic through Neural Network for Interpretable Classification.
    Danyang Li, Mingyu Cai, Cristian-Ioan Vasile, Roberto Tron. IEEE American Control Conference (ACC), San Diego, USA, May, 2023. [Bibtex] [PDF]

  3. Probabilistic Coordination of Heterogeneous Teams From Capability Temporal Logic Specifications.
    Mingyu Cai, Kevin Leahy, Zachary Serlin, Cristian-Ioan Vasile. IEEE International Conference on Robotics and Automation (ICRA). Philadelphia, USA, May, 2022. [Bibtex] [PDF]

  4. Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic.
    Mingyu Cai, Mohammadhosein Hasanbeig, Shaoping Xiao, Alessandro Abate, Zhen Kan. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021. [Bibtex] [PDF] [Demo] [Code]

  5. Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction.
    Mingyu Cai, Shaoping Xiao, Baoluo Li, Zhiliang Li, Zhen Kan. IEEE International Conference on Robotics and Automation (ICRA). Xian, China, May 2021. [Bibtex] [PDF] [Code]

  6. Receding Horizon Control-Based Motion Planning With Partially Infeasible LTL Specifications.
    Mingyu Cai, Hao Peng, Zhijun Li, Hongbo Gao, Zhen Kan. American Control Conference (ACC) , New Orleans, Louisiana, USA, June 2021. [Bibtex] [PDF] [Demo] [Video] [Code]

  7. Characterizing herdability of signed networks via graph walks.
    Baike She,Mingyu Cai, Zhen Kan. IEEE Conference on Decision and Control Conference (CDC), Orlando, FL, USA, December 2019. [Bibtex] [PDF]