Automatical Guardrail Design of Subway Stations through Multi-objective Evolutionary Algorithm

In subway stations, elevators are one of the most narrowed areas that slow down the moving of crowds. A large number of passengers gather around the elevator entrances and may cause unexpected accidents such as stampede. An effective way to guide the flow of passengers is to use guardrails. So far, the arrangement of guardrails in most subway stations is still designed manually, which requires rich experience and expert knowledge. In this paper, we propose to use the multi-objective evolutionary algorithm to design the guardrails of the elevator entrance automatically. The transfer time of passengers and the flow rate are optimized concurrently. The proposed algorithm is tested in two scenarios with different complexities. Experimental results show that the proposed algorithm can provide promising guardrail arrangements, and reveal some instructive conclusions for guardrail design in subway stations.

[1]  Wentong Cai,et al.  Self-Learning Gene Expression Programming , 2016, IEEE Transactions on Evolutionary Computation.

[2]  Dirk Helbing,et al.  Dynamics of crowd disasters: an empirical study. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Xi Lin,et al.  A G/G(n)/C/C state-dependent simulation model for metro station corridor width design , 2016 .

[4]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[5]  Masanori Suganuma,et al.  A genetic programming approach to designing convolutional neural network architectures , 2017, GECCO.

[6]  Liya Yao,et al.  A comparative study of funnel shape bottlenecks in subway stations , 2017 .

[7]  Serge P. Hoogendoorn,et al.  Controlled experiments to derive walking behaviour , 2002 .

[8]  Gunnar G. Løvås,et al.  Modeling and Simulation of Pedestrian Traffic Flow , 1994 .

[9]  Dipti Srinivasan,et al.  Empirical Investigations Into the Composite Differential Evolution on CEC 2017 Constrained Optimization Problems , 2018, 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[10]  Jun Liu,et al.  Analysis of subway station capacity with the use of queueing theory , 2014 .

[11]  Dirk Helbing,et al.  Simulating dynamical features of escape panic , 2000, Nature.

[12]  Wei Luo,et al.  Experimental Study for Optimizing Pedestrian Flows at Bottlenecks of Subway Stations , 2018 .

[13]  Dirk Helbing,et al.  How simple rules determine pedestrian behavior and crowd disasters , 2011, Proceedings of the National Academy of Sciences.

[14]  Guisheng Yin,et al.  An Effective Differential Evolution With Binary Strategy for Feature Selection Problem , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[15]  D. Helbing,et al.  Self-Organization Phenomena in Pedestrian Crowds , 1998, cond-mat/9806152.

[16]  Mohcine Chraibi,et al.  Measuring the steady state of pedestrian flow in bottleneck experiments , 2016 .

[17]  Peter Vortisch,et al.  Pedestrian Flow at Bottlenecks - Validation and Calibration of Vissim's Social Force Model of Pedestrian Traffic and its Empirical Foundations , 2008, ArXiv.

[18]  Alex A. Freitas,et al.  Evolutionary Computation , 2002 .

[19]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[20]  Bernhard Steffen,et al.  New Insights into Pedestrian Flow Through Bottlenecks , 2009, Transp. Sci..

[21]  André Pinz Borges,et al.  A Case Study Approach to Automatic Driving Train Using CBR with Differential Evolution , 2018, 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[22]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[23]  Liu Liu,et al.  Combining Building and Behavior Models for Evacuation Planning , 2011, IEEE Computer Graphics and Applications.

[24]  Wei Luo,et al.  A Dynamic Time Warping Algorithm Based Analysis of Pedestrian Shockwaves at Bottleneck , 2018 .

[25]  Nirajan Shiwakoti,et al.  Examining influence of merging architectural features on pedestrian crowd movement , 2015 .

[26]  Ris S. C. Lee,et al.  Exploring Trampling and Crushing in a Crowd , 2005 .

[27]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.