most citedCloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning

11 citations · 12 across the 2 of their papers we have counts for

collaborators
Showing eess.SYShow all

2 papers · 1 filter

eess.SY2022★ 1 cited

Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture

Bingzhuo Zhong, Hongpeng Cao, Majid Zamani +1

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. AI-based) controlle…

eess.SY2021

Safe-visor Architecture for Sandboxing (AI-based) Unverified Controllers in Stochastic Cyber-Physical Systems

Bingzhuo Zhong, Abolfazl Lavaei, Hongpeng Cao +2

High performance but unverified controllers, e.g., artificial intelligence-based (a.k.a. AI-based) controllers, are widely employed in cyber-physical systems (CPSs) to accomplish c…