Taxi Automation Using Real Time Adaptive Scheduling

Abstract

the taxi dispatch problem involves assigning taxis to requester waiting at different locations. A dispatch system currently in use by a major cab service provider divides the city (in which the system operate s) into regional dispatch areas. Each area has fixed assigned adjacent areas hand - coded by human experts. When a local area does not have bare cabs, the system chooses an adjacent area to search. However, such fixed, hand - coded adjacency of areas cannot be a prudent indicator because it does not take into consideration frequent changes in traffic patterns and road structure. This causes dispatch officials to limit the system by manually enforcing movement on taxis. The proposed system dynamically modifies t he adjacency of dispatch areas . The proposed technique will decrease the total waiting time, is less in comparison with the present system and increases taxi utilization in comparison with results of the simulation without self - organization. Interestingly, research work also discovers that human intervention (by either the taxi - dispatch officials or the taxi drivers), to manually overcome the drawbacks of the existing dispatch system can be counterproductive when used with a self - organizing system.