While on sab­bat­ical, Javed Aslam, a pro­fessor in the Col­lege of Com­puter and Infor­ma­tion Sci­ence, is col­lab­o­rating with MIT researchers on a project in Sin­ga­pore, studying traffic flows through data from taxi cabs to reveal con­ges­tion pat­terns and deter­mine how to make city dri­ving a less painful experience.

Tell us about the project, and where you come in.
The Future Urban Mobility project is part of a larger Singapore-​​MIT Alliance for Research and Tech­nology enter­prise. Sin­ga­pore wants to figure out how best to get people from place to place. They want to develop, in and beyond Sin­ga­pore, new models for the plan­ning, design and oper­a­tion of future urban trans­porta­tion sys­tems, including public and pri­vate trans­port, land use, envi­ron­mental impacts, urban plan­ning, and transport-​​related policy issues.
I signed on as a senior research asso­ciate. My wife, Daniela Rus, an MIT pro­fessor in the Depart­ment of Elec­trical Engi­neering and Com­puter Sci­ence, signed on as the first prin­cipal inves­ti­gator in-​​residence. Our goal was to kick-​​start all of the research activ­i­ties for the project, in col­lab­o­ra­tion with stu­dents, post-​​docs, researchers, and fac­ulty in Singapore.

Why study Singapore’s traffic as opposed to any other big city?
Sin­ga­pore has a tremen­dous amount of data avail­able with which to study traffic. For example, as part of our study, the taxi com­pany Com­fort Delgro pro­vided us with data for August 2010. The data included roughly 16,000 taxis log­ging their iden­ti­fi­ca­tion num­bers, GPS loca­tions, speeds, status, and date and time­stamps every 30 sec­onds. In essence, I have a roving net­work of 16,000 taxis, and I know exactly how fast they’re going at any point in time all day for a month, in roughly one-​​minute inter­vals. These 16,000 taxis effec­tively com­prise an enor­mous roving “sensor net­work” with which to study traffic, con­ges­tion, mobility pat­terns and so on. We are in the process of obtaining sim­ilar data from the local bus system, as well as static traffic sensor data from over 1,000 road inter­sec­tions in Singapore.

Based on your expe­ri­ence studying traffic pat­terns and con­ges­tion in Sin­ga­pore, what advice can you give city dri­vers on how best to reach their des­ti­na­tions on time?
One seem­ingly coun­ter­in­tu­itive piece of advice is that the fastest route isn’t always the best. While most route plan­ning tools will sug­gest the fastest route based on his­tor­ical data or expected travel time, if you have a hard dead­line to meet, it may well pay to take a some­what longer route that is more con­sis­tent, in that it is less likely to be unusu­ally delayed. Such routes may actu­ally increase your prob­a­bility of reaching your des­ti­na­tion on time.