Filters








257,224 Hits in 6.3 sec

Control States and Complete Agent Architectures

Darryl N. Davis
2001 Computational intelligence  
A developing agent architecture, that can support motivation and other control states associated with mind, is presented.  ...  The contention is that a highly interconnected four-layer architecture is required for a complete (cognitive) agent, making use of reflexive, reactive, deliberative and reflective behaviors.  ...  What makes a complete agent? What kinds of motivation and related processing structures need a complete agent have? What are the appropriate architectures and control issues for such an agent?  ... 
doi:10.1111/0824-7935.00167 fatcat:5tgob2m5pzbd3bocq7iqtsl5ou

Multiagent Systems for 3D Reconstruction Applications [chapter]

Metehan Aydın, Erkan Bostancı, Mehmet Serdar Güzel, Nadia Kanwal
2020 Multi Agent Systems - Strategies and Applications  
One of the well-known and well-used techniques is image-based reconstruction. An imagebased reconstruction starts with data acquisition step and ends with 3D model of the scene.  ...  The explanation is provided by literature reviews and a study whose purpose is reconstructing an area in 3D using a multiagent UAV system.  ...  There are four types of mission completed message in the system, these are error, state, success and not completed messages.  ... 
doi:10.5772/intechopen.88460 fatcat:dyrvxe2ekva4fkccvb4sgsvy6q

A multi-agent architecture for control of AGV systems

Pooya Farahvash, Thomas O. Boucher
2004 Robotics and Computer-Integrated Manufacturing  
The architecture includes functions at the manufacturing cell level, materials handling and transport level, and factory scheduling level.  ...  In this paper a set of agents (a multi-agent system) is introduced to control an automated manufacturing environment.  ...  In addition to agents for planning and control, recovery agents are designed to diagnose error states and provide recovery plans.  ... 
doi:10.1016/j.rcim.2004.07.005 fatcat:tw5vg2klojfethf7vq4kqpewbe

The Exception Handling Pattern in the Architectural Layers Using Aspect-Oriented Programming [chapter]

Lei Zhang, Lianbo Ma, Weixing Su
2012 Advances in Intelligent and Soft Computing  
Compared with the previous work, the system proposed in this paper, is based on the application service agents, using the complex logic controlling method in RFID acquisition system and the acquisition  ...  The implementation mechanism of the application agent structure is presented as well as the complex logic controlling method. The progress analysis model is also given.  ...  The state of controlling process is divided into the system configuration state and the task processing state.  ... 
doi:10.1007/978-3-642-27866-2_66 fatcat:exfrfrn7zrgzho7jcvjgwppwiu

Reactive and motivational agents: Towards a collective minder [chapter]

Darryl N. Davis
1997 Lecture Notes in Computer Science  
of motivational and other control states.  ...  Introduction This paper reports on the Architectures for Intelligent Agents project within which computational complete agent architectures are being investigated (using a two dimensional simulated world  ...  Members of the Cognition and Affect group, in particular Aaron Sloman and Ian Wright, for discussions related to this work.  ... 
doi:10.1007/bfb0013594 fatcat:rltxncjrsjg3lg4txwzgmf2t6e

Hierarchical and State-based Architectures for Robot Behavior Planning and Control [article]

Philipp Allgeuer, Sven Behnke
2018 arXiv   pre-print
In this paper, two behavior control architectures for autonomous agents in the form of cross-platform C++ frameworks are presented, the State Controller Library and the Behavior Control Framework.  ...  While the former is state-based and generalizes the notion of states and finite state machines to allow for multi-action planning, the latter is behavior-based and exploits a hierarchical structure and  ...  Every robotic agent requires some form of architecture for behavior control in order to complete the tasks that it is given.  ... 
arXiv:1809.11067v1 fatcat:nktgdhcyrjgpxisznb6gx5vpam

Peer-to-Peer Control of Microgrids [article]

Hamada Almasalma, Jonas Engels, Geert Deconinck
2017 arXiv   pre-print
As many different control methods for microgrids can be found in literature, this paper proposes a classification from highly centralized to distributed peer-to-peer control architectures.  ...  Different control algorithms suited for the proposed peer-to-peer control strategy are discussed.  ...  This type of architecture, inspired by P2P computer networking [18] , is characterized by the complete absence of a central controller.  ... 
arXiv:1711.04070v1 fatcat:at2hmboj7vf45dstyev2m2j4qm

Architectural Roles of Affect and How to Evaluate Them in Artificial Agents

Matthias Scheutz
2011 International Journal of Synthetic Emotions  
It provides functional and architectural characterizations for simple and complex affective states, discusses possible interactions between affective and nonaffective processes, and proposes an experimental  ...  Keywords: utility of affect, affective agent architectures, evaluation of affective agents, virtual and robotic agents, functional roles of affect  ...  Acknowledgments The author would like to thank Paul Schermerhorn for helpful suggestions to improve the narrative and Aaron Sloman for his influential work on architecture-based affect concepts.  ... 
doi:10.4018/jse.2011070103 fatcat:q3qagtyaxrbpligewlcmdujvie

Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban [article]

Peter Karkus, Mehdi Mirza, Arthur Guez, Andrew Jaegle, Timothy Lillicrap, Lars Buesing, Nicolas Heess, Theophane Weber
2020 arXiv   pre-print
We find that our modular RL approach dramatically outperforms the state-of-the-art monolithic RL agent on Mujoban.  ...  Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control.  ...  We collect data for training by executing the planner, controller and control-completion modules, and using true abstract states as labels.  ... 
arXiv:2010.01298v1 fatcat:fn27yde4avdvla7jgo5bylnmzy

Cognitive Architectures for Affect and Motivation

Darryl N. Davis
2010 Cognitive Computation  
By what means can a general architecture know when it has adapted to a specific task, a particular environment or a specific state of a previously known environment?  ...  Rather we should look to foundational requirements for intelligent systems, and ask do we require emotions in machines or an alternative equivalent, for example affect, of use in control and self-regulation  ...  This requirement for affective states in complete cognitive theories and architectures was highlighted in earlier prominent research [6] [7] .  ... 
doi:10.1007/s12559-010-9053-4 fatcat:piglkiodenb3zdvhfgysc3ifky

An Architectural Strategy for Self-Adapting Systems

Danny Weyns, Tom Holvoet
2007 International Workshop on Software Engineering for Adaptive and Self-Managing Systems (SEAMS '07)  
The self-adapting properties of the approach are based on the agents' abilities to adapt their behavior to dynamic and changing circumstances.  ...  The architectural strategy for self-adapting systems structures the software into a number of interacting autonomous entities (agents) that are situated in an environment.  ...  Agent is an autonomous problem solving entity in the system. An agent encapsulates its state and controls its behavior.  ... 
doi:10.1109/seams.2007.3 dblp:conf/icse/WeynsH07 fatcat:mokxuz44mbdltpcmfoqe7fmare

All-to-All Communication with CA Agents by Active Coloring and Acknowledging [chapter]

Patrick Ediger, Rolf Hoffmann
2010 Lecture Notes in Computer Science  
hidden control states?  An agent, modeled within the CA paradigm Applications with CA Agents  ...  pro-active change-oriented and self-initiated behavior; acts on its own initiative, not only reacting, using a plan; some state changes independent of neighborh.?  ...  is copied to FREE cell ACRI 2010, Sept. 21-24, Ascoli Piceno | Computer Architecture Group, Dept. of Computer Science | 20 MoveControlState ColorControlState from front cell control state  ... 
doi:10.1007/978-3-642-15979-4_3 fatcat:ewq5ef76erhvhf6j7zds3hfmha

From Actor Event-Loop to Agent Control-Loop

Alessandro Ricci
2014 Proceedings of the 4th International Workshop on Programming based on Actors Agents & Decentralized Control - AGERE! '14  
Event-loops and control-loops are the main control architectures adopted respectively in actors and in agents.  ...  These architectures have a strong impact on the principles and discipline that can be adopted to design and program actors and agents.  ...  Introduction The event-loop and the control-loop are two main control architectures adopted in literature to define the runtime behaviour of actors and agents.  ... 
doi:10.1145/2687357.2687361 dblp:conf/agere/Ricci14 fatcat:ublh4wqj3vbwrlukhbkjvxwql4

NetworkAI: An Intelligent Network Architecture for Self-Learning Control Strategies in Software Defined Networks

Haipeng Yao, Tianle Mai, Xiaobin Xu, Peiying Zhang, Maozhen Li, Yunjie Liu
2018 IEEE Internet of Things Journal  
To address this issue, this paper presents NetworkAI, an intelligent architecture for self-learning control strategies in SDN networks.  ...  NetworkAI employs deep reinforcement learning and incorporates network monitoring technologies such as the in-band network telemetry to dynamically generate control policies and produces a near optimal  ...  Network State Upload In the SDN network architecture, the controller can send an action decision to the underlying network with an aim to acquire a complete network control.  ... 
doi:10.1109/jiot.2018.2859480 fatcat:r2deqvl6rjdple5ck7gdweluve

Agent oriented system approach for workflow automation

Atsushi Inamoto
1999 International Journal of Production Economics  
Furthermore, a system architecture to materialize this system concept is designed, and a network infrastructure and software architecture for its implementation are proposed. 1999 Elsevier Science B.V.  ...  In order to elaborate on this new system concept, the agent-oriented system approach is adopted for greater sophistication with respect to mobility, autonomy and serviceability, and intelligence.  ...  , e-form agents have autonomy and can control and manage workflow by moving freely from one role to another based on their own decision.  ... 
doi:10.1016/s0925-5273(98)00159-5 fatcat:jmmg3iheevdm5fecc6fkyrps6q
« Previous Showing results 1 — 15 out of 257,224 results