scholarly journals Cognitive map plasticity and imitation strategies to improve individual and social behaviors of autonomous agents

2010 ◽  
Vol 1 (1) ◽  
Author(s):  
Philippe Laroque ◽  
Nathalie Gaussier ◽  
Nicolas Cuperlier ◽  
Mathias Quoy ◽  
Philippe Gaussier
Keyword(s):  
Autonomous Agents ◽  
Hebbian Learning ◽  
Social Behaviors ◽  
Place Cells ◽  
Cognitive Map ◽  
Multi Agent System ◽  
Learning Mechanism ◽  
Global Performance ◽  
Multi Agent ◽  
The Brain

AbstractStarting from neurobiological hypotheses on the existence of place cells (PC) in the brain, the aim of this article is to show how little assumptions at both individual and social levels can lead to the emergence of non-trivial global behaviors in a multi-agent system (MAS). In particular, we show that adding a simple, hebbian learning mechanism on a cognitive map allows autonomous, situated agents to adapt themselves in a dynamically changing environment, and that even using simple agent-following strategies (driven either by similarities in the agent movement, or by individual marks - “signatures” - in agents) can dramatically improve the global performance of the MAS, in terms of survival rate of the agents. Moreover, we show that analogies can be made between such a MAS and the emergence of certain social behaviors.

A Control Methodology for Autonomous Multi-Agent System in Collective and Uniform Distribution and Reorientation

2013 ◽  
Vol 392 ◽  
pp. 366-373
Author(s):  
Tao Yang ◽  
Yong Jun Jia ◽  
Li Bo Yang
Keyword(s):  
Uniform Distribution ◽  
Decentralized Control ◽  
Autonomous Agents ◽  
Asymptotical Stability ◽  
Control Law ◽  
Multi Agent System ◽  
Agent System ◽  
Contribution Analysis ◽  
Multi Agent ◽  
Control Methodology

This paper proposes a decentralized control law of NlCyP&BG for a team of autonomous agents, which aims at achieving collective and uniform distribution around an appointed destination. A technique by virtual of coordinate constraints is described for eigenvalues derivation and contribution analysis, so that conditions for local asymptotical stability of n-agent system is deduced. Simulation work on a two-agent case and an extended four-agent case are displayed to prove the validity of stability conclusion, and at the same time the effectiveness of control law in accomplishing expected distribution and reorientation is verified exactly.

Measuring complacency in humans interacting with autonomous agents in a multi-agent system

2020 ◽  
Author(s):  
Sebastian S. Rodriguez ◽  
Jacqueline Chen ◽  
Harsh Deep ◽  
Jaewook Lee ◽  
Derrik E. Asher ◽  
...  
Keyword(s):  
Autonomous Agents ◽  
Multi Agent System ◽  
Agent System ◽  
Multi Agent

From libraries to wayfinding, waylosing, and symbolism

2021 ◽  
pp. 359-420
Author(s):  
Michael A. Arbib
Keyword(s):  
Public Library ◽  
Graph Model ◽  
Brain Regions ◽  
Place Cells ◽  
Cognitive Map ◽  
Symbolic Form ◽  
Symbolic Forms ◽  
Cell Recording ◽  
Getting Lost ◽  
The Brain

After demonstrating that a building is a system of systems, we examine the symbolism of certain libraries. A cognitive account of wayfinding uses the Seattle Public Library to analyze getting lost in buildings—which we contrast with waylosing as in exploration. Cognitive maps in the brain represent places and the means to find one’s way between them. Different “worlds” each have their own, modeled as a world graph (WG) with distinctive places represented by nodes, and paths represented by edges. Complementing this, a locometric map represents locomotor effort in getting from one place to another. Single-cell recording from rat hippocampus reveals place cells whose activity correlates with the place in which the animal finds itself. However, “place” here corresponds to location on a locometric map, rather than distinctive places of WG nodes. The taxon affordance model (TAM), models how one navigates without a cognitive map. Several brain regions are involved, but not hippocampus. The world graph model (WGM) makes essential use of the hippocampus in coordination with brain regions processing the relevant WG. Finally, we contrast symbolic form in buildings with the use of explicit signage. Oscar Niemeyer’s Brasilia Cathedral exemplifies how architects may achieve novel symbolic forms.

scholarly journals A Social Multi-Agent Cooperation System Based on Planning and Distributed Task Allocation

Information ◽  
2020 ◽  
Vol 11 (5) ◽  
pp. 271
Author(s):  
Atef Gharbi
Keyword(s):  
Task Allocation ◽  
Autonomous Agents ◽  
Computational Time ◽  
Multi Agent System ◽  
Model Checker ◽  
Computation Tree ◽  
Message Exchange ◽  
Multi Agent ◽  
Distributed Task Allocation ◽  
Cooperation System

Planning and distributed task allocation are considered challenging problems. To address them, autonomous agents called planning agents situated in a multi-agent system should cooperate to achieve planning and complete distributed tasks. We propose a solution for distributed task allocation where agents dynamically allocate the tasks while they are building the plans. We model and verify some properties using computation tree logic (CTL) with the model checker its-ctl. Lastly, simulations are performed to verify the effectiveness of our proposed solution. The result proves that it is very efficient as it requires little message exchange and computational time. A benchmark production system is used as a running example to explain our contribution.

EFFICIENCY ANALYSIS OF THE TIME-SHUFFLING METHOD FOR THE EVOLUTION OF AGENT BEHAVIOR

2012 ◽  
Vol 23 (02) ◽  
pp. 523-542
Author(s):  
PATRICK EDIGER ◽  
ROLF HOFFMANN
Keyword(s):  
Autonomous Agents ◽  
State Machine ◽  
State Machines ◽  
Multi Agent System ◽  
Agent System ◽  
Agent Behavior ◽  
Local View ◽  
Finite State ◽  
Multi Agent ◽  
Algorithm Scheme

We have analyzed the effectiveness and the efficiency of a time-shuffling method applied to an evolutionary algorithm scheme in order to optimize the behavior of autonomous agents in a multi-agent system. The multi-agent system is modeled as cellular automata (CA) because of the inherent parallelism of the model, which suits well the requirements of a system of autonomous moving agents with a local view. The task of the agents is the all-to-all communication, i.e., all agents shall communicate their initially mutually exclusive information to all other agents. The agents' uniform behavior is defined by a finite-state machine, which is evolved by a genetic algorithm (GA). 20 different initial two-dimensional environments were defined as a training set, 10 of them with border, 10 with cyclic wrap-around. The state machine was evolved (1) directly by a GA for all 20 environments, and (2) indirectly by two separate GAs for the 10 environments with border and the 10 environments with wrap-around, with a subsequent time-shuffling technique in order to integrate the good abilities from both of the separately evolved state machines. The time-shuffling technique alternates two state machines periodically. The results show that time-shuffling two separately evolved state machines is effective and much more efficient than the direct application of the GA.

AN AGENT DECISION SUPPORT MODULE BASED ON GRANULAR ROUGH MODEL

2012 ◽  
Vol 11 (04) ◽  
pp. 793-820 ◽  
Author(s):  
SALLY M. EL-GHAMRAWY ◽  
ALI I. ELDESOUKY
Keyword(s):  
Decision Support ◽  
Decision Maker ◽  
Autonomous Agents ◽  
Coordination Mechanism ◽  
Distributed Artificial Intelligence ◽  
Multi Agent System ◽  
Rough Model ◽  
Selection Decision ◽  
Multi Agent ◽  
Specific Agent

A multi-agent system (MAS) is a branch of distributed artificial intelligence, composed of a number of distributed and autonomous agents. In a MAS, effective coordination is essential for autonomous agents to achieve their goals. Any decision based on a foundation of knowledge and reasoning can lead agents into successful cooperation; to achieve the necessary degree of flexibility in coordination, an agent must decide when to coordinate and which coordination mechanism to use. The performance of any MAS depends directly on the decisions made by the agents. The agents must therefore be able to make correct decisions. This paper proposes a decision support module in a distributed MAS that is concerned with two main decisions: the decision needed to allocate a task to specific agent/s and the decision needed to select the appropriate coordination mechanism when agents must coordinate with other agent/s to accomplish a specific task. An algorithm for the task allocation decision maker (TADM) and the coordination mechanism selection decision maker (CMSDM) algorithm are proposed that are based on the granular rough model (GRM). Furthermore, a number of experiments were performed to validate the effectiveness of the proposed algorithms; the efficiency of the proposed algorithms is compared with recent works. The preliminary results demonstrate the efficiency of our algorithms.

Application of a System-Wide Trust Strategy when Supervising Multiple Autonomous Agents

2016 ◽  
Vol 60 (1) ◽  
pp. 133-137 ◽  
Author(s):  
James C. Walliser ◽  
Ewart J. de Visser ◽  
Tyler H. Shaw
Keyword(s):  
Supervisory Control ◽  
System Performance ◽  
Autonomous Agents ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Performance Information ◽  
Agent Systems ◽  
Multi Agent ◽  
And Performance ◽  
And Training

When interacting with complex systems, the manner in which an operator trusts automation influences system performance. Recent studies have demonstrated that people tend to apply trust broadly rather than exhibiting specific trust in each component of the system in a calibrated manner (e.g. Keller & Rice, 2010). While this System–Wide Trust effect has been established for basic situations such as judging gauges, it has not been studied in realistic settings such as collaboration with autonomous agents in a multi-agent system. This study utilized a multiple UAV control simulation, to explore how people apply trust in multi autonomous agents in a supervisory control setting. Participants interacted with four UAVs that utilized automated target recognition (ATR) systems to identify targets as enemy or friendly. When one of the autonomous agents was inaccurate and performance information was provided, participants were 1) less accurate, 2) more likely to verify the ATR’s determination, 3) spent more time verifying images, and 4) rated the other systems as less trustworthy even though they were 100% correct. These findings support previous work that demonstrated the prevalence of system-wide trust and expand the conditions in which system-wide trust strategies are applied. This work suggests that multi-agent systems should provide carefully designed cues and training to mitigate the system-wide trust effect.

Sign in / Sign up

Export Citation Format

Share Document