Hierarchical Behavior Model for Multi-Agent System with Evasion Capabilities and Dynamic Memory

A Enis Çetin ,Erhan Bülbül

doi:10.3390/ijgi9040279

Abstract

The behavior of an agent may be simple or complex depending on its role. Behavioral simulation using agents can have multiple approaches that have different advantages and disadvantages. By combining different behaviors in a hierarchical model, situational inefficiencies can be compensated. This paper proposes a behavioral hierarchy model that combines different mechanisms in behavior plans. The study simulates the social behavior in an office environment during an emergency using collision avoidance, negotiation, conflict solution, and path-planning mechanisms in the same multi-agent model to find their effects and the efficiency of the combinational setups. Independent agents were designed to have memory expansion, pathfinding, and searching capabilities, and the ability to exchange information among themselves and perform evasive actions to find a way out of congestion and conflict. The designed model allows us to modify the behavioral hierarchy and action order of agents during evacuation scenarios. Moreover, each agent behavior can be enabled or disabled separately. The effects of these capabilities on escape performance were measured in terms of time required for evacuation and evacuation ratio. Test results prove that all mechanisms in the proposed model have characteristics that fit each other well in situations where different hierarchies are needed. Dynamic memory management (DMM), together with a hierarchical behavior plan, achieved a performance improvement of 23.14% in escape time without providing agents with any initial environmental information.

Highlights

Most multi-agent applications and studies aim to replicate specific human behaviors such as herding [1], negotiation [2], and cooperation [3]
The simulation can be considered to have a non-deterministic structure and this may have a slight effect on model performance
A hierarchical behavior model for a multi-agent system with evasion capabilities and dynamic memory simulating the social behavior in an office environment during an emergency was presented

Summary

Introduction

Most multi-agent applications and studies aim to replicate specific human behaviors such as herding [1], negotiation [2], and cooperation [3]. The emergency evacuation problem has a complex nature in a crowded environment, due to the behavior of people under stress. This situation may become even more complicated depending on the physical structure of the environment. The estimated routes of some agents may intersect with others and create bottlenecks, collisions, and conflicts depending on the crowd Different mechanisms [34] for maintaining personal space have been simulated using multi-agent models. Studies on emergency egress mostly focus on physical environmental conditions, with an assumption that either agents have prior information about the environment or information is provided to them during evacuation. NNooddeess ooff ggaatteess aanndd wweeiigghhttss ooffeeddggeess:: ((aa)) nnooddeess ooff aa ggaattee ((rreeddcciirrcclleess))aannddeennttrraanncceeeeddggee ((ddaasshheeddlilninee));;((bb))wweeigighhtstsooffeeddggeess

Agent Model

Evasion Mechanisms

Behavioral Hierarchy Plan

Calibration of Reconsideration Mechanism

Test Results

Conclusions