Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Communication Protocols
Discussion of Design Issues
Summary and Directions
References

Software integration architectures for agents

Profile image of Ken HawickKen Hawick

2008

visibility

…

description

14 pages

link

1 file

Abstract

Many modern artificial intelligence (AI) systems, including both real physical robots and animat-based models are structured using intelligent agents. A key challenge for building large and complex AI systems is to manage the agent interactions in an appropriate architecture that supports complexity in a scalable and hierarchical manner. In this article we review various agent architectures for both physical and simulated robot systems, and show how appropriate agent communications protocols can be developed to support artificially intelligent systems based on communities of interacting agents. As well as reviewing some of the architectures and supporting software tools and technologies, we present our own ideas for a software architecture for managing intelligent agents. We emphasise the importance of being able to incrementally augment the set of agents as new ideas are developed. We describe how key activities such as agent navigation in physical and simulated spaces; agent communication; world state management and sensory integration all need to be managed in an appropriate framework to support individual agents that will take responsibility for tasks and goals.

Related papers

A multi-agent environment in robotics
carlos ramos

Robotica, 1991

SUMMARY The use of Multi-Agent Systems as a Distributed AI paradigm for Robotics is the principal aim of our present work. In this paper we consider the needed concepts and a suitable architecture for a set of Agents in order to make it possible for them to cooperate in solving non-trivial tasks.

View PDFchevron_right
An Approach for Multi-Robot System Based on Agent Layered Architecture
Dhouha ben noureddine

2016

Many agent-based architectures have been developed to facilitate the improvement of multi-robot systems which are able of performing robust cooperative work. This paper presents a layered architecture to simulate a robot-like agent. Different layers are defined for the software architecture with focusing on openness, flexibility, robustness and optimization properties. The proposed architecture aims to provide a well-structured and managed system for task execution, behaviour and decision-making of multi-robot system (MRS). Based on these ideas, we present a three-tiered agent architecture to harness many aspects of intelligence. Agents continuously observe the environment, in the reactive layer and act accordingly. The sequencing layer provides the means for planning, and task execution. We propose a fuzzy membership function, in the deliberate layer, to choose the appropriate plan during action selection using the satisfaction degree. This method is undertaken to illustrate, evalu...

View PDFchevron_right
Agent-based distributed architecture for mobile robot control
Juan-Luis Posadas-Yagüe

Engineering Applications of Artificial Intelligence, 2008

Mobile robots are physical agents that move and interact continuously while embedded in a dynamic environment. Communications can be one of the most difficult parts of building robot architecture because of the increasing complexity of sensor and actuator hardware, and the interaction between intelligent features and real-time constraints. Currently, hybrid architectures offer the most widespread solutions for controlling intelligent mobile robots. This paper deals with the communications framework necessary to design and implement these architectures. The main goal of this work 1 is to design a modular and portable architecture that allows the development of robot control systems. A multi-level and distributed architecture based on the reactive/deliberative paradigm is presented. Its main components are mobile software agents that interact through a distributed blackboard communications framework. These agents can be run on onboard processors, as well as on fixed workstations depending on their real-time restrictions. The presented control architecture has been tested in a real mobile robot and results demonstrate the effectiveness of distributing software agents to guarantee hard real-time execution.

View PDFchevron_right
Robots in a distributed agent system
Adam Cheyer

1998

We describe how we manage cognitive information within our mobile robotics activities. Our approach can be divided into three parts: the local level through Saphira (the navigation system), the global state through OAA TM (the Open Agent Architecture), and the representation and human-user interaction through multimodal interfaces.

View PDFchevron_right
Applying the ARTIS Agent Architecture to Mobile Robot Control
Vicent Botti

2000

The agent/multi-agent system paradigm is an important field of Arti-ficial Intelligence. The use of this paradigm in real-world problems is one of the main lines of interest in this area. To do this, it is necessary to make use of agent/multi-agent architectures and artefacts. This paper describes an architec-ture for real-time agents, an artefact (InSiDE) for the specification of agent-based systems and the application of this architecture for the control of an autonomous mobile robot.

View PDFchevron_right
An architecture for rational agents interacting with complex environments
Carlos Iván Chesñevar

2003

View PDFchevron_right
The autonomous agent architecture
Marcello Balduccini

In this paper we give a summary of the Autonomous Agent Architecture (AAA architecture for short) for intelligent agents. The AAA architecture is the result of several years of research on the design and implementation of intelligent agents that reason about, and act in, changing environments. In the AAA architecture, the knowledge about the domain where the agent is situated is encoded in Answer Set Prolog and is shared by all of the reasoning components. The agent's reasoning components are also formalized in Answer Set Prolog. Typical AAA agents are capable of observing the environment, interpreting the observations, recovering from unexpected observations, and planning to achieve their goals.

View PDFchevron_right
The Distributed Control Framework: A software infrastructure for agent-based distributed control and robotics
Vikram Manikonda

2008 American Control Conference, 2008

We address the shortage of available software frameworks for distributed control systems/robotics and describe a novel agent-based software architecture simplifying the development, testing, and deployment of distributed controllers. Our Distributed Control Framework (DCF) provides extensive support for robot team coordination and management, a pluggable architecture for sensing and estimation, robust simulation capabilities with support for hardware in the loop, and a highlevel platform-independent programming language for hybrid control called MDLe (Motion Description Language Extended). We highlight two experiments that showcase the DCF and MDLe using real robots, and we conclude the paper with the derivation and discussion of an indoor robot navigation system used in our experiments. The navigation system combines robot odometry and range measurements from a network of Cricket sensors using an extended Kalman filter.

View PDFchevron_right
Agent-based Application Framework for Multiple Mobile Robots Cooperation
Enric Cervera

Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005

We present an agent-based framework for the development of distributed applications for a team of heterogenous mobile robots. The main goal is to ease the development of cooperative tasks among teams of robots. The proposed architecture must have not only the capacity to allow the team of robots to accomplish such tasks, but also it must have tools and features that allow programmers to develop complex applications in a reasonable time. Agent-based development platforms are used for this purpose, integrating the necessary capabilities for developing distributed applications, and managing the communications among all the components.

View PDFchevron_right
Multi-Agent Distributed Architecture For Mobile Robotics
Massimo Cossentino

2001

An approach to the design of multi-agent architectures for mobile robotics is presented, that is based on the Unified Modeling Language. The main goal of the work is to provide a framework to perform a rigorous agent-based design process for cognitive architectures both in the case of a single robot, and in a multi-robot scenario. Details of the methodology, system implementation using FIPA-OS environment, along with real and simulated experiments are reported. <<communicate>> Strategies Producer VocalSensMsgResponse Waiting Handling incoming communication Planning Handling outcoming communication message arrived new data available strategy established message sent no new message message not processed strategy not completed message not sent

View PDFchevron_right

References (31)

  1. Thanngiah, S.R., Shmygelska, O., Mennell, W.: An agent architecture for vehicle routing prob- lems. In: Proc 2001 ACM Symposium on Ap- plied Computing, Las Vegas, USA (2001) 517- 521 ISBN 1-58113-287-5.
  2. Settembre, G.P., Scerri, P., Farinelli, A., Sycara, K., Nardi, D.: A decentralized approach to coop- erative situation assessment in multi-robot sys- tems. In: Proc. of 7th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2008). Number ISBN:978-0-9817381-0-9, Estoril, Portu- gal (2008) 31-38
  3. Wikipedia: Kevin Warwick. Web Sites: en. wikipedia.org/wiki/Kevin Warwick (2002)
  4. Sellem, P., Amram, E., Luzeaux, D.: Open multi-agent architecture extended to distributed autonomous robotic systems. In: SPIE Aerosense'00, Conference on Unmanned Ground Vehicle Technology II. (2000) Orlando, FL, USA.
  5. Brooks, R.: A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation RA 2 (1986) 14-25
  6. Desouza, G.N., Kak, A.C.: A subsumptive, hi- erarchical, and distributed vision-based architec- ture for smart robotics. IEEE Transactions on Robotics and Automation 34 (2004) 1988-2002
  7. Andre, D., Russell, S.: State abstraction in pro- grammable reinforcement learning. Technical re- port, Univ. California at Berkeley, USA. (2002) UCB/CSD-02-1177.
  8. Levesqu, H., Reiter, R., Lesperance, Y., Lin, F., Scherl, R.: Golog: A logic programming language for dynamic domains. Journal of Logic Program- ming 31 (1997) 59-84
  9. Hawick, K.A., James, H.A., Scogings, C.J.: A virtual prolog approach to implementing beliefs, desires and intentions in animat agents. In Zhang, S., Jarvis, R., eds.: AI 2005: Advances in Artifi- cial Intelligence -Proc 18th Australian Joint Con- ference on Artificial Intelligence. Number LNAI 3809 in CSTN-022, Sydney, Australia, Springer (2005) ISSN 0302-9743, ISBN 3-540-30462-2.
  10. Soler, J., Julian, V., Carrascosa, C., Botti, V.: Applying the ARTIS Agent Architecture to Mo- bile Robot Control. In: Proc. Int Joint Conf 7th Ibero-American Conf on AI:Advances in AI. Volume LNCS 1952. (2000) 359-368 ISBN 3-540- 41276-X.
  11. Firby, R.J.: The rap language manual. Tech- nical report, University of Chicago, Chicago, Il, USA. (1995) Animate Agent Project Working Note AAP-6.
  12. Thrun, S.: A framework for programming em- bedded systems: Initial design and results. Tech- nical Report CMU-CS-98-142, Carnegie Mellon University, Pittsburgh, PA, USA. (1998)
  13. Horswill, I.: Functional programming of behaviour-based systems. Autonomous Robots 9 (2000) 83-93 CSTN-054
  14. Wilson, S.W.: The animat path to AI. In Meyer, J.A., Wilson, S., eds.: From Animals to Ani- mats 1: Proceedings of The First International Conference on Simulation of Adaptive Behavior, Cambridge, MA: The MIT Press/Bradford Books (1991) 15-21
  15. Hawick, K.A., Scogings, C.J., James, H.A.: Defensive spiral emergence in a predator-prey model. Complexity International (2008) 1-10
  16. Scogings, C., Hawick, K.: Altruism amongst spa- tial predator-prey animats. In Bullock, S., Noble, J., Watson, R., Bedau, M., eds.: Proc. 11th Int. Conf. on the Simulation and Synthesis of Living Systems (ALife XI), Winchester, UK, MIT Press (2008) 537-544
  17. Hawick, K., Scogings, C.J.: Resource scarcity effects on spatial species distribution in animat agent models. In Grigoriadis, K., ed.: Proc. IASTED International Conference on Environ- mental Modelling and Simulation, 16-18 Novem- ber, Orlando, USA. Number CSTN-059, Orlando, USA. (2008) 284-289 ISBN 978-0-88986-777-2.
  18. Hawick, K.A., James, H.A., Silis, A.J., Grove, D.A., Kerry, K.E., Mathew, J.A., Coddington, P.D., Patten, C.J., Hercus, J.F., Vaughan, F.A.: DISCWorld: An environment for service-based metacomputing. Future Generation Computing Systems (FGCS) 15 (1999) 623
  19. Mathew, J., James, H., Hawick, K.: Develop- ment Routes for Message Passing Parallelism in Java. In: Proc. of the AM Java Grande 2000 Conference. (2000) 54-61 DHPC-082.
  20. Leist, A., Hawick, K.: Small-world networks, dis- tributed hash tables and the e-resource discovery problem in support of global e-science infrastruc- ture. Technical Report CSTN-069, Massey Uni- versity (2009)
  21. The Bluetooth Special Interest Group: The Blue- tooth Core Specification. www.bluetooth.com (2002)
  22. Hawick, K., James, H.: Personal communications and mobile decision support. Technical report, Adelaide University (2002) DHPC-113.
  23. Dallas Semiconductor Corp.: Introducing Tini (2002)
  24. Packard, H.: iPAQ Handheld Mobile Devices (2008)
  25. Maravillas, E., Reyes, N.H., Dadios, E.P.: Hy- brid fuzzy logic strategy for soccer robot game. Journal of Advanced Computational Intelligence and Intelligent Informatics 8 (2004) 65-71
  26. Gerdelan, A., Iskandar, D., Djohar, A.F., Reyes, N.: Utilising the Hybrid Fuzzy A* Algorithm in a Cooperative Multi-Agent System. In: in Con- ference Program and Abstracts of the 4th Con- ference on Neuro-Computing and Evolving In- telligence (NCEI06) and 6th International Con- ference on Hybrid Intelligent Systems (HIS06). (2006)
  27. Gerdelan, A., Reyes, N.: Synthesizing Adap- tive Navigational Robot Behaviours using a Hy- brid Fuzzy A* Approach. In: Advances in Soft Computing: Computational Intelligence: The- ory and Applications. Springer, (Berlin & Hei- delberg) (2006) pp. 699-710.
  28. Gerdelan, A., Reyes, N.: A Novel Hybrid Fuzzy A* Robot Navigation System for Target Pursuit and Obstacle Avoidance. In: Proceedings of the First Korean-New Zealand Joint Workshop on Advance of Computational Intelligence Methods and Applications. Volume vol.1., Auckland, New Zealand (2006) pp. 75-79
  29. Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall (1995)
  30. NASA: Peer-to-peer human-robot interaction project (2006)
  31. Rana, O.F., Bunford-Jones, D., Hawick, K.A., Walker, D.W., Addis, M., Surridge, M.: Re- source discovery for dynamic clusters in compu- tational grids. In: Proceedings of the 15th Inter- national Parallel & Distributed Processing Sym- posium. (2001) 82

Related papers

An Agent-Based Architecture for a Multi-Robot System
Alaa Khamis

2008

Abstract This paper presents an agent-based architecture for a multi-robot system. The proposed architecture combines the hierarchical and the decentralized approaches in order to increase the robustness of the multi-robot system to component failure and decrease the computation and communication load. Processes are split into two layers: a cognitive layer, where the higher brain functions take place, and an action layer, where the low level functions take place.

View PDFchevron_right
An agent based design process for cognitive architectures in robotics
Roberto Pirrone

2001

Nowadays, robots have to face very complex tasks, often requiring collaboration between several individuals. As a consequence, robotics can be considered one of the most suitable paradigms for agent-based software. In this work, we present an approach to the design of distributed multi-agent architectures for mobile robotics, that is based on the Unified Modeling Language.

View PDFchevron_right
A survey of robotic agent architectures
Bora İ Kumova

2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 2017

Robotic agents consist of various compositions of properties that are found in their mechatronics, behavioural and cognitive architectures. Common properties of each architecture type serve as criteria for assessing the degree of intelligence of most embodied agent models. Although embodied intelligence has long been accepted for robotic agents, the literature is short on combined evaluations that discuss all properties of all architecture types in one framework. Here we provide a review of existing taxonomies for each type of architecture and attempt to combine them all in a single taxonomy for robotic agents.

View PDFchevron_right
Experiences with an architecture for intelligent, reactive agents
David Miller

Journal of Experimental and Theoretical Artificial Intelligence, 1997

This paper describes an implementation of the 3 T robot architecture which has been under development for the last eight y ears. The architecture uses three levels of abstraction and description languages which a r e compatible between levels. The makeup of the architecture helps to coordinate planful activities with real-time behaviors for dealing with dynamic environments. In recent y ears, other architectures have been created with 1 similar attributes but two features distinguish the 3 T a r c hitecture: 1) a variety of useful software tools have been created to help implement this architecture on multiple real robots and 2) this architecture, or parts of it, have been implemented on a variety o f v ery di erent robot systems using di erent processors, operating systems, e ectors and sensor suites.

View PDFchevron_right
A Broker based architecture to control robots in a simulated environment
helder coelho

We present an extension to the Aglets platform in order to support brokering services agencies in a transparent process for the agent designer. This architecture is constructed to provide a set of functionalities, not originally available in the core Aglet environment. These include, white page service, group formation and yellow page support in a distributed and mobile agent environment. The extension was developed in three directions, new environment agents, new agent architectures and an extended agent live cycle model. We also extend the Aglet message model in order to support KQML like directives and speech acts. With these modifications, we encapsulate the Aglets environment in a set of new facilities that provide the designer with a set of higher-level tools to develop his agents. We use this platform to control a team of robots in a simulated environment, providing a complex communication channel to the robots, extending the original features providing a white pages service and a GPS like facility.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved