The way that humans walk. That’s amazing. In a crowded space, the amount of data generated in every single walking decision is scientifically just as non-trivial as data about the next word in a spoken sentence. In both cases predictions can be made, the general intent may be algorithmically inferred, and in both cases humans tend to sneak up behind the algorithm and surprise it with seeming randomness.
(Picture: computer-generated Random Walk)
This project’s goal is to study the science of getting lost in a city setting. When is someone ‘lost’ on the street? How does a lost person look when plotted on the map? Is there more than one kind of ‘lost’ behavior on a map - and if so, is it different between - say, lost alzheimer’s patients, lost children and lost tourists? I suppose there is, and I suppose that it can be found.
Human dynamics in cities are radically different than movement in an open terrain. The line of sight is trim and constantly changing, new dangers are popping up by the second, and the perception of space is severely contaminated by sound and smell interference.
The plan: By mapping volunteer’s movements in the city with a tracking application (for example, OpenPaths.cc), this project will try to help find a recurring pattern that may indicate confusion or distress. Currently, volunteers could either just input their data (done automatically) or review it later, marking where they got lost for long periods of time. By knowing exactly when and where a person is, we will be able to visualize the trails, apply machine learning and divide the notion of being “lost” into finer-grained categories.
Using the data (and ultimately, the knowledge) acquired in this set of experiments, we will be able to help many different groups: Children/elderly people (and their families), city planners who want to know what parts of town don’t work, Psychologists, Computer Scientists, and people who are asymptotically stuck on the street, wondering what to have for dinner.