Results 1 - 10
of
37
Emergent Control and Planning in an Autonomous Vehicle
, 1993
"... We use a connectionist network trained with reinforcement to control both an autonomous robot vehicle and a simulated robot. We show that given appropriate sensory data and architectural structure, a network can learn to control the robot for a simple navigation problem. We then investigate a more c ..."
Abstract
-
Cited by 36 (7 self)
- Add to MetaCart
We use a connectionist network trained with reinforcement to control both an autonomous robot vehicle and a simulated robot. We show that given appropriate sensory data and architectural structure, a network can learn to control the robot for a simple navigation problem. We then investigate a more
Adapting Control Strategies for Situated Autonomous Agents
- In Proceedings of the Florida Artificial Intelligence Research Symposium
, 1995
"... This paper studies how to balance evolutionary design and human expertise in order to best design situated autonomous agents which can learn specific tasks. A genetic algorithm designs control circuits to learn simple behaviors, and given control strategies for simple behaviors, the genetic algorith ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
This paper studies how to balance evolutionary design and human expertise in order to best design situated autonomous agents which can learn specific tasks. A genetic algorithm designs control circuits to learn simple behaviors, and given control strategies for simple behaviors, the genetic
RedAgent-2003: An autonomous, market-based supply-chain management agent
"... The Supply Chain Management track of the international Trading Agents Competition (TAC SCM) was introduced in 2003 as a test-bed for researchers interested in building autonomous agents that act in dynamic supply chains. TAC SCM provides a challenging scenario for existing AI decisionmaking algorith ..."
Abstract
- Add to MetaCart
algorithms, due to the high dimensionality and the non-determinism of the environment, as well as the combinatorial nature of the problem. In this paper we present RedAgent, the winner of the first TAC SCM competition. RedAgent is based on a multi-agent design, in which many simple, heuristic agents manage
Behavior Emergence in Autonomous Robot Control by Means of Feedforward and Recurrent Neural Networks
"... Abstract—We study the emergence of intelligent behavior within a simple intelligent agent. Cognitive agent functions are realized by mechanisms based on neural networks and evolutionary algorithms. The evolutionary algorithm is responsible for the adaptation of a neural network parameters based on t ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Abstract—We study the emergence of intelligent behavior within a simple intelligent agent. Cognitive agent functions are realized by mechanisms based on neural networks and evolutionary algorithms. The evolutionary algorithm is responsible for the adaptation of a neural network parameters based
A Multiple-Team Organization for Decentralized Guidance and Control of Formation Flying Spacecraft
- AIAA Intelligent Systems Conference
, 2004
"... In recent years, formation flying has become an enabling technology for several mission concepts at both NASA and the Department of Defense. In most cases, a multiple-satellite approach is required in order to accomplish the large-scale geometries imposed by the sensing objectives. In general, the p ..."
Abstract
-
Cited by 7 (3 self)
- Add to MetaCart
is likely to be unreasonable unless the onboard software is sufficiently autonomous, robust, and reconfigurable. This paper presents the prototype of a system that addresses these objectives – a decentralized guidance and control system that is distributed across spacecraft using a multipleteam framework
W-learning: A simple RL-based Society of Mind
, 1995
"... W-learning is a self-organising action-selection scheme for systems with multiple parallel goals, such as autonomous mobile robots. It uses ideas drawn from the subsumption architecture for mobile robots (Brooks), implementing them with the Q-learning algorithm from reinforcement learning (Watki ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
W-learning is a self-organising action-selection scheme for systems with multiple parallel goals, such as autonomous mobile robots. It uses ideas drawn from the subsumption architecture for mobile robots (Brooks), implementing them with the Q-learning algorithm from reinforcement learning
Multi-Agent Plan Repair With DTPs
"... A planning problem can be transformed into a (temporal) constraint satisfaction problem called a Disjunctive Temporal Problem (DTP). Many planning problems have a distributed nature: multiple parties are involved in the construction of a global plan. We discuss a multi-agent architecture where each ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
agent acts as a DTP constraint solver responsible for the consistency of his own problem partition. Though there are efficient algorithms for the Distributed Constraint Satisfaction Problem (DCSP), they can not be directly applied to a DTP. This is because multiple agents have to reach consensus over
Programmable architectures that are complex and self-organized: from morphogenesis to engineering
- in 11th Int‟l Conf. Simulat. Synth. Living Syst.(ALIFE XI
, 2008
"... Outside biological and social systems, natural pattern formation is essentially “simple ” and random, whereas complicated struc-tures are the product of human design. So far, the only self-organized (undesigned) and complex morphologies that we know are biological organisms and some agent societies. ..."
Abstract
-
Cited by 15 (5 self)
- Add to MetaCart
Outside biological and social systems, natural pattern formation is essentially “simple ” and random, whereas complicated struc-tures are the product of human design. So far, the only self-organized (undesigned) and complex morphologies that we know are biological organisms and some agent societies
Supporting Social Networks with Agent-Based Services
"... ABSTRACT Current approaches to build social networking systems are based on a centralized architecture because it allows a simple browser-based user experience and makes easier and more efficient to implement many algorithms used in a social networking site (e.g., friend suggestion), However this k ..."
Abstract
- Add to MetaCart
ABSTRACT Current approaches to build social networking systems are based on a centralized architecture because it allows a simple browser-based user experience and makes easier and more efficient to implement many algorithms used in a social networking site (e.g., friend suggestion), However
(No) More design patterns for multi-agent systems
"... A multi-agent systems (MAS) can be used to solve several problems that permeate current complex software systems design, specially distributed systems. The MAS research community has extensively studied protocols, algorithms, methodologies, and architectures to create autonomous, adaptable, robust, ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
A multi-agent systems (MAS) can be used to solve several problems that permeate current complex software systems design, specially distributed systems. The MAS research community has extensively studied protocols, algorithms, methodologies, and architectures to create autonomous, adaptable, robust
Results 1 - 10
of
37