Towards Adaptive Discrete Event Control Based on PRD, PSS and Automatic Planner

Abstract

Industry 4.0 technologies integrate devices and data, bring exibility, eciency and decision making, derived from decentralization. In a post pandemic society it is mandatory to reduce human presence in production and distribution of goods. This work implements some of Industry 4.0 characteristics by combining manufacturing elements such as Cyber Physical System (CPS) with passive entities that directly aect decisions in the same automatic planning domain. The proposal is illustrated by emulating a Block World problem, where it will be used a set of blocks with Radio Frequency Identication (RFID) each one containing its self goals, represented by predicates, an approach called PRD (Predicate inside RFID Database). A robot can identify objects by helding a RFID reader integrated with a Physical State Space (PSS). Since the robot controller has a local view of the process it is unable to compute the plan for the whole system by itself, so the planning process must be a Cloud service. Local planning must also be taken into consideration, solving any network issues. Thus, a generic solution has to be adapted to t physical execution and domain constraints. Such solution detects changes in the physical environment and redo its plan, generating an adaptive discrete event controller.