Publications

Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo (2024). Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning. arXiv preprint.
Cite
Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo (2024). Simplex-enabled Safe Continual Learning Machine. arXiv preprint arXiv:2409.05898.
Cite
Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo (2024). Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings. The Twelfth International Conference on Learning Representations (ICLR).
Cite URL
Mirco Theile, Hongpeng Cao, Marco Caccamo, Alberto L Sangiovanni-Vincentelli (2024). Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning. 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Cite
Bingzhuo Zhong, Hongpeng Cao, Majid Zamani, Marco Caccamo (2023). Towards safe ai: Sandboxing dnns-based controllers in stochastic games. Proceedings of the AAAI Conference on Artificial Intelligence.
Cite
Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo (2023). Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees. 2023 62nd IEEE Conference on Decision and Control (CDC).
Cite
Junjie Ming, Daniel Bargmann, Hongpeng Cao, Marco Caccamo (2023). Flexible Gear Assembly with Visual Servoing and Force Feedback. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Cite
Hongpeng Cao, Lukas Dirnberger, Daniele Bernardini, Cristina Piazza, Marco Caccamo (2023). 6IMPOSE: Bridging the reality gap in 6D pose estimation for robotic grasping. Frontiers in Robotics and AI.
Cite
Hongpeng Cao, Mirco Theile, Federico G Wyrwal, Marco Caccamo (2022). Cloud-edge training architecture for sim-to-real deep reinforcement learning. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Cite
Bingzhuo Zhong, Abolfazl Lavaei, Hongpeng Cao, Majid Zamani, Marco Caccamo (2021). Safe-visor architecture for sandboxing (AI-based) unverified controllers in stochastic cyber--physical systems. Nonlinear Analysis: Hybrid Systems.
Cite