no code implementations • 19 Mar 2024 • Mirco Theile, Hongpeng Cao, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli
In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance.
no code implementations • 26 May 2023 • Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo
In this paper, we propose the Phy-DRL: a physics-model-regulated deep reinforcement learning framework for safety-critical autonomous systems.
no code implementations • 29 Mar 2023 • Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo
Deep reinforcement learning (DRL) has achieved tremendous success in many complex decision-making tasks of autonomous systems with high-dimensional state and/or action spaces.
1 code implementation • 30 Aug 2022 • Hongpeng Cao, Lukas Dirnberger, Daniele Bernardini, Cristina Piazza, Marco Caccamo
To overcome this gap, we introduce 6IMPOSE, a novel framework for sim-to-real data generation and 6D pose estimation.
no code implementations • 28 Mar 2022 • Bingzhuo Zhong, Hongpeng Cao, Majid Zamani, Marco Caccamo
In this paper, we propose a construction scheme for a Safe-visor architecture for sandboxing unverified controllers, e. g., artificial intelligence-based (a. k. a.
no code implementations • 4 Mar 2022 • Hongpeng Cao, Mirco Theile, Federico G. Wyrwal, Marco Caccamo
To overcome the reality gap, our architecture exploits sim-to-real transfer strategies to continue the training of simulation-pretrained agents on a physical system.
no code implementations • 10 Feb 2021 • Bingzhuo Zhong, Abolfazl Lavaei, Hongpeng Cao, Majid Zamani, Marco Caccamo
To cope with this difficulty, we propose in this work a Safe-visor architecture for sandboxing unverified controllers in CPSs operating in noisy environments (a. k. a.