Deliberative/Reactive Architecture of a Multirobot Patrol System Based on Supervisory Control Theory

Lima, Carolina Rutili de; Khan, Said Ghani; Shah, Syed Humayoon; Lu, Cheng-Kai

doi:10.1109/jsen.2022.3170238

Cited by 3 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discrete event systems (DESs) [1], [2] encompass a wide variety of human-made systems, including power systems [3], unmanned aerial vehicle systems [4], healthcare service systems [5], traffic systems [6], communication protocols [7], [8], digital systems [9] and robotic systems [10], [11]. A DES typically uses deterministic finite automata (DFA) to describe a plant system and its control specification.…”

Section: Introductionmentioning

confidence: 99%

Reducing the Learning Time of Reinforcement Learning for the Supervisory Control of Discrete Event Systems

et al. 2023

View full text Add to dashboard Cite

Reinforcement learning (RL) can obtain the supervisory controller for discrete-event systems modeled by finite automata and temporal logic. The published methods often have two limitations. First, a large number of training data are required to learn the RL controller. Second, the RL algorithms do not consider uncontrollable events, which are essential for supervisory control theory (SCT). To address the limitations, we first apply SCT to find the supervisors for the specifications modeled by automata. These supervisors remove illegal training data violating these specifications and hence reduce the exploration space of the RL algorithm. For the remaining specifications modeled by temporal logic, the RL algorithm is applied to search for the optimal control decision within the confined exploration space. Uncontrollable events are considered by the RL algorithm as uncertainties in the plant model. The proposed method can obtain a nonblocking supervisor for all specifications with less learning time than the published methods.

show abstract