Making Trains Run on Time (economist.com)
Plamen Angelov of the University of Lancaster, in Britain, has an idea that he hopes will make train delays rarer. From a report: Often, Dr Angelov observes, the problem is not the inefficiency of operators but the behaviour of passengers -- the "platform-train interface", to use railway parlance. When trains arrive, passengers crowd around the doors waiting to board, restricting the flow of those getting off. When they are about to depart, people often hold doors open, delaying that departure. (A recent study by Japan's Railway Bureau found that passengers attempting to board trains after their scheduled departure times accounted for almost 50% of delays.) Passengers also frequently stand too close to the carriages for safety. Waiting for malefactors to move back behind the yellow safety line on a platform might hold a train up for less than a minute. But over the course of a journey those minutes add up. Even a slight delay is compounded if it causes a train to slip out of its running order and be held at a subsequent station, or be required to follow a slower service.
Dr Angelov thinks that applying artificial intelligence to the problem might help. And that is what he and his team are doing. Using images from the cctv cameras already mounted in carriages and on platforms, their system employs algorithms that have been trained to detect objects such as people, luggage, pushchairs and bicycles. It then measures the movements and positions of these objects relative to areas such as the train doors or the yellow safety line and uses this information to predict problems. The cameras in the carriages detect how busy particular doors are getting as passengers leave their seats and gather next to the exits when the train approaches a station. At the same time, the station cameras monitor the numbers waiting for the train to arrive, whereabouts they are standing along the platform, and how encumbered they are. The two sets of data can then be compared, providing warning of likely areas of congestion. This permits passengers -- particularly those on the platform -- to be directed to doors that will be less busy.
Dr Angelov thinks that applying artificial intelligence to the problem might help. And that is what he and his team are doing. Using images from the cctv cameras already mounted in carriages and on platforms, their system employs algorithms that have been trained to detect objects such as people, luggage, pushchairs and bicycles. It then measures the movements and positions of these objects relative to areas such as the train doors or the yellow safety line and uses this information to predict problems. The cameras in the carriages detect how busy particular doors are getting as passengers leave their seats and gather next to the exits when the train approaches a station. At the same time, the station cameras monitor the numbers waiting for the train to arrive, whereabouts they are standing along the platform, and how encumbered they are. The two sets of data can then be compared, providing warning of likely areas of congestion. This permits passengers -- particularly those on the platform -- to be directed to doors that will be less busy.
A researcher *in the UK* is trying to make trains run on time *in Japan*? You just broke my irony-meter.
From what I've seen on the trains in Japan, damn near everyone waits patiently behind the yellow line, in 2 lines per door and the people exiting the train are generally not obstructed at all. Then, the waiting passengers board calmly.
I'm thinking these researchers may have never lived in Japan, or only compared the busiest times when there's hardly standing room on the platforms.
Now perhaps if one door was exit only and one was enter only on each car, it would work, but only if loading/unloading an entire car at a time.
"Freedom in the USA is not the ability to do what you want. It is the ability to stop others from doing what THEY want"
Make the boarding passengers stand behind gates which only open after the arriving passengers have left the train.
so that the internally crowded doors open on the sparsely populated part of the platform. Then you don't have to direct the platform passengers so much.
Better yet, design train stations with "Entrance and Exit Only" platforms/sides and delay the enter door opening until people are moving out the exit door. In one side, out the other.... You end up with larger train stations, but you would decrease exiting and loading times.
People suck, and that's why we can't have nice things.
I remember the doors on the peoplemover at Atlanta Airport in the early 80s. From what I recall, they wouldn't crush you or allow the train to depart unless the doors were completely closed... but they weren't particularly GENTLE about closing, or proactive about re-opening if you DID get caught in them. The synthesized voice would sternly shout, "Stop boarding!" three times and slam the doors shut. If you got caught in them, a flashing light would go off, you'd be loudly scolded by the same robotic voice in front of the entire train (and possibly an employee) while you were still stuck in the door, THEN the doors would momentarily slide open again (leaving you with a bruise to motivate you to move more quickly next time). I'm sure they've toned down the aggressiveness quite a bit since then, but it definitely worked... you could see the literal FEAR in people's eyes if they were anywhere NEAR the doors when the "Stop boarding!" began.
My understanding, from friends that have been to Japan, and watching japanophile shows like Japanology+, was that the trains in Japan were almost disgustingly punctual. Is that not the case?
My friends may have been amazed due to comparison to U.S rail systems.
This is a design problem and the result of inferior design.
The best (and most expensive) way to solve this problem is to design the stations so that passengers enter on one side of the train and leave on the other. This is the way rides are designed at amusement parks to facilitate the movement of crowds.
Barring that, a system which direct passengers to debark at certain doors (such as at the front) and enter at other doors (At the back) will also work. This has been used on buses, where passengers exit at the back and enter at the front (where they pay.)
The use of AI in this case may indeed result in fewer accidents resulting from moving trains hitting passengers in exclusion zones, but it will do nothing for keeping trains on time.