Automatic Rule Identification for Agent-Based Crowd Models Through Gene Expression Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7764

@InProceedings{Zhong:2014:AAMAS,

• author = "Jinghui Zhong and Linbo Luo and Wentong Cai and Michael Lees",
• title = "Automatic Rule Identification for Agent-Based Crowd Models Through Gene Expression Programming",
• booktitle = "13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)",
• metis_id = "402420",
• year = "2014",
• editor = "Alessio Lomuscio and Paul Scerri and Ana Bazzan and Michael Huhns",
• pages = "1125)",
• address = "Paris",
• month = "5-9 " # may,
• publisher = "ACM",
• keywords = "genetic algorithms, genetic programming, gene expression programming, agent-based modelling, crowd simulation, decision rules, evolutionary algorithm",
• isbn13 = "978-1-4503-2738-1",
• URL = "http://aamas2014.lip6.fr/proceedings/aamas/p1125.pdf",
• size = "8 pages",
• abstract = "Agent-based modelling of human crowds has now become an important and active research field, with a wide range of applications such as military training, evacuation analysis and digital game. One of the significant and challenging tasks in agent-based crowd modelling is the design of decision rules for agents, so as to reproduce desired emergent phenomena behaviours. The common approach in agent-based crowd modelling is to design decision rules empirically based on model developer's experiences and domain specific knowledge. In this paper, an evolutionary framework is proposed to automatically extract decision rules for agent-based crowd models, so as to reproduce an objective crowd behaviour. To automate the rule extraction process, the problem of finding optimal decision rules from objective crowd behaviours is formulated as a symbolic regression problem. An evolutionary framework based on gene expression programming is developed to solve the problem. The proposed algorithm is tested using crowd evacuation simulations in three scenarios with differing complexity. Our results demonstrate the feasibility of the approach and shows that our algorithm is able to find decision rules for agents, which in turn can generate the prescribed macro-scale dynamics.",
• notes = "info@ifaamas.org http://aamas2014.lip6.fr/ http://aamas2014.lip6.fr/tools/pdf/AAMAS2014_booklet.pdf",

}

Genetic Programming entries for Jinghui Zhong Linbo Luo Wentong Cai Michael Lees

Citations