Search

Abstract Coordination is an important requirement for most Multiagent Systems. A setplay is a particular instance of a coordinated plan for multi-robot systems in collective sports. Setplays are usually designed by robotics specialists using some existing tools, like the SPlanner, or by hand-coding. This work presents recent improvements to the Strategy Planner (SPlanner) and its corresponding FCPortugal Setplays Framework (FSF) to provide sophisticated setplays. This toolkit is useful to design strategic plans for robotic soccer teams as a particular case of Multi-Agent Systems (MASs). The new enhancements enable more realistic setplays, including, but not limited to, the definition of better pass strategies and defensive setplays. The enhanced tool is used to populate a dataset with demonstrations made by soccer experts and used in a Learning from Demonstration (LfD) approach to allow robotic soccer teams to learn new setplays. A new demonstration mode in the RoboCup Soccer Simulation 3D (SSIM3D) viewer RoboViz was also introduced to integrate this tool with SPlanner. Domain experts can use this set of tools to capture a specific scene in a game in RoboViz and use it as an initial step for a new setplay recommendation in SPlanner. The resulting dataset is organized into fuzzy clusters to be used in a reinforcement learning strategy. This paper describes the whole process. Article Highlights This paper’s main contribution is generating a dataset of setplays to support learning from demonstration in robotic soccer. A set of new features were added to the Strategic Planner(SPlanner) to enable the design of more realistic setplays. The official RoboCup viewer (Roboviz) was integrated with SPlanner using a new demonstration mode.

With the advent of the global and digital world, the number of geographically dispersed firms throughout the world has increased and the problem of Supply Chain (SC) disruption appeared as a main c...

Sustainability management at the production control can make business feasible and profitable, ensuring the safety of the employees, communities and consumers, in addition to the efficient use of resources/raw materials. However, industrial standards do not describe how to deal with sustainability at Productive Systems (PSs) design and their control. Therefore, this paper proposes a framework based on extensions of the ANSI/ISA95 standard for assessment of PSs performance considering sustainability indicators. The framework also considers information processing, storage and access remote for each system component through cyber-physical system and cloud computing technologies. Furthermore, a systematic approach based on Petri Nets (PNs) techniques ensures a formalism to verify and validate the behavior of the Sustainable Productive Systems (SuPSs). Application cases demonstrate and indicate the advantages of the proposed framework to the feasibility, profitability, safety and efficiency of SuPSs.

Multi-Agent Systems (MASs) have been used to solve complex problems that demand intelligent agents working together to reach the desired goals. These Agents should effectively synchronize their individual behaviors so that they can act as a team in a coordinated manner to achieve the common goal of the whole system. One of the main issues in MASs is the agents' coordination, being common domain experts observing MASs execution disapprove agents' decisions. Even if the MAS was designed using the best methods and tools for agents' coordination, this difference of decisions between experts and MAS is confirmed. Therefore, this paper proposes a new dataset schema to support learning the coordinated behavior in MASs from demonstration. The results of the proposed solution are validated in a Multi-Robot System (MRS) organizing a collection of new cooperative plans recommendations from the demonstration by domain experts., Comment: This is a pre-print of an article published in the Journal of Intelligent & Robotic Systems. The final authenticated version will be available online at: https://doi. org/10.1007/s10846-019-01123-w

This paper presents a framework based on Petri Net (PN) and Multi Agent System (MAS) techniques for modeling autonomous multi-robots systems, which require high interaction among the robots (in some cases with humans), synchronization of movements, implementation of cooperation strategies, and a strong notion of the physical environment. The framework considers all phases of the developing process, starting with the abstraction phase and going up to the implementation of the model, to ensure an efficient and flexible approach for specifying the proposed control system architecture. An application example details this solution, in which multi-robots systems can perform tasks and collaborative behaviors considering the cited requirements.

This paper proposes a control architecture for reconfigurable manufacturing systems and its design method based on Petri nets (Input Output Place Transition and Production Flow Schema), Service-Oriented Architecture and Holonic and Multi-Agent System techniques, among other good practices. The control architecture integrates value-added activities, information and resources. The method considers the exchange of knowledge among heterogeneous business workflow of manufacturing subsystems in different geographical locations, and allows modeling process, product, machine and device control. An example demonstrates advantages of the resulting control system.

There is a kind of movement for people to consider sustainability in all their daily activities, not only in the acquisition of goods and services but including the care for health. This induces the emergence of a new business model. Any type of production system (PS) should thus consider sustainability in all its activities and a relationship, which includes not only customers but suppliers, and partners involved from conception, design, manufacturing and provide even service after the use and the disposal of the products. Therefore, an evaluation procedure for PS is proposed to monitor four aspects of sustainability, namely: environmental, social, economical and technological. A framework is considered to deal with the concepts of sustainability and to evaluate performance in industrial PSs considering the indicators to qualify and to quantify their sustainability. It adopts the Petri net technique and extensions of the ANSI/ISA95; Cyber Physical System (CPS) and Smart Grid resources are also considered to treat information processing, storage and access flows by each system component and a Cloud Computing System to connect dispersed PSs. In addition, an evaluation process is systematized to support sustainable PSs by the rational use of production resources and the environment, to guarantee the safety of employees and to maintain the economic profitability of the company, thus, making production processes more efficient.

In a new industrial business model, all aspects of sustainability, i.e. (i) environmental for reduction of negative impacts of using resources, (ii) economic for viability and profitability of business, (iii) social for assuring the safety of employees, communities and consumers, and (iv) technological for efficient and safe use of production resources, need to be effectively incorporated in the productive activities. On the other hand, existing decision-making structures in industries do not explicitly consider how to deal with sustainability indicators when developing a productive system (PS) and its control system. Therefore, this paper discusses the components of a framework and their interactions to apply new concepts to evaluate performance in industrial PSs considering the indicators to qualify and to quantify their sustainability. The framework adopts the Petri net technique and extensions of the ANSI/ISA 95 standard to systemize the evaluation process. This approach assures a formal way to verify and to validate the system sustainability. Besides, the framework considers information processing, storage and access flows between each system component under Cyber Physical System (CPS) and Cloud Computing concepts.

In general, the performance of productive systems considers the efficient use of technological transformation resources (such as machines and raw materials), information processing, and handling/transportation operations. However, there are no normalized criteria or rules to evaluate the performance of a productive system in the context of sustainability. Thus, this paper introduces an approach to identify and evaluate the performance indicators related to the sustainability of productive systems, specifically for geographically dispersed cases, i.e., dispersed productive system (DPS), in which the processes are in a distributed and dispersive architecture. The proposed approach is based on a framework aimed to measure sustainability key performance indicators (SuKPIs) that evaluate the sustainability of a system. The framework considers the ANSI/ISA-95 standard, and the sustainability assessment methodology considers the balance of sustainability indicators, which depend on economic, environmental, social, and technological aspects. The Petri net and derived techniques are used to model and to verify the main functionalities of the proposed framework, and also to monitor the productive processes of DPS for data acquisition of the SuKPIs. An application example is also presented to show the feasibility and validity of the proposal.

A practical problem in automation systems modeling is the choice between a fully hybrid approach and the fluidization of some parts conserving the general discrete event approach. This paper explores the approach based on specific hybrid parts into a discrete event system using a unified Petri nets environment called GHENeSys (General Hierarchical Enhanced Net System), which follows the ISO/IEC 15909 standard and includes extensions such as hierarchy and time concepts. Then, a design method based on GHENeSys Timed Hybrid Petri Net (GTHPN) technique is proposed to model these hybrid parts. GHENeSys subnets are associated with macro-places and help to control combinatorial explosion and has extended arcs to guarantee the GTHPN applicability to practical cases. All resulting models of the approach proposed could also benefit from an easier conversion to PLC programs in IEC 61131 representation. A case study is presented for producing constructive blocks showing the advantages of the current proposition. Un problema práctico en sistemas automatizados es la selección entre el enfoque totalmente híbrido o la fluidización de algunas partes conservando el enfoque general de eventos discretos. Este articulo trata el enfoque basado en partes hibridas en un modelo discreto usando el ambiente unificado de Redes de Petri llamado GHENeSys (Sistema de Red Extendida Jerárquica General), compatible con la norma ISO/IEC 15909 incluyendo los conceptos de jerarquía y tiempo. Por tanto, se propone un método de diseño y una técnica GTHPN (Redes de Petri Temporizadas Hibridas GHENeSys) para modelar estas partes híbridas. Las subredes en macro-lugares controlan la explosión de estados y controlar transiciones mediante arcos extendidos de GHENeSys garantiza la efectividad de GTHPN para casos prácticos. Además, todo modelo resultante permite una fácil conversión a programas de PLCs en lenguajes IEC61131. Se presenta un caso de estudio para producción de bloques de construcción demostrando estas ventajas mencionadas.

Available industrial standards do not explicitly consider how to treat sustainability indicators in PS design and its control system. Therefore, this paper proposes a framework to systematize the performance evaluation process for industrial PS considering indicators that qualify and quantify its sustainability. The framework adopts Petri net technique and extensions of the standard ANSI/ISA95. Simulation-based analysis, decision making techniques and a PS´s classification based on product green seal are also considered. Furthermore, the framework considers the processing information, storing and accessing each component using a Cyber Physical Technology due to the trend of PSs to be, in fact, a network for companies that are, in general geographically dispersed.

This work presents recent improvements to Strategy Planner (SPlanner) and its corresponding FCPortugal Setplays Framework (FSF) to provide sophisticated setplays. This toolkit is useful to design strategic plans for robotic soccer teams as a particular case of Multi-Agent Systems (MASs). The new enhancements enable more realistic setplays, including, but not limited to, the definition of better passes strategies and defensive setplays. The enhanced tool is used to populate a dataset with demonstrations made by soccer experts and used in a Learning from Demonstration (LfD) approach to allow teams of robotic soccer learning new setplays.