Using GIS and genetic algorithm in highway alignment optimization

• Published in: Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems Vol. 2; pp. 1563 - 1567 vol.2
• Main Authors: Chan Weng Tat, Fan Tao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2003
• Subjects: Computational Intelligence Society; Constraint optimization; Cost function; Genetic algorithms; Geographic Information Systems; Joining processes; Road accidents; Road transportation; Road vehicles; Vehicle driving
• ISBN: 9780780381254; 0780381254
• DOI: 10.1109/ITSC.2003.1252747

Optimizing highway alignments is a difficult combinatorial problem from highway engineering. The problem is to find an alignment connecting two given end points such that the alignment incurs minimal total costs. From past experience, it has been found that the two critical success factors in the optimizing of highway alignments are a good search algorithm, and an efficient and accurate way to calculate the total costs of the highway. The genetic algorithm (GA) is a good choice as a search algorithm as its stochastic nature and global search characteristic enables the GA to find high quality solutions even for complex problems. The solution for an accurate cost model may lie with the use of the geographic information system (GIS). GIS can spatially represent both the physical, natural and socio-economic features of the region of the alignment. Furthermore, the spatial analytical capabilities of the GIS provide valuable inputs to the highway alignment optimization. This paper describes an integrated model that combines the capabilities of the GA and the GIS to optimize the highway alignments.