The self-driving vehicle, in which the driver will hardly be necessary, promises to revolutionize the concept of mobility. But until that day arrives, other technologies are already making it easier to get around, especially in big cities.
Robots that can regulate traffic, algorithms that detect people in order to avoid accidents or crosswalks that alert smartphone-distracted pedestrians are just three examples of technologies that are already adapted to our movement.
A robot among pedestrians
Both drivers and pedestrians understand the rules perfectly when driving on a road, but what about robots? Engineers at the Massachusetts Institute of Technology (MIT) have designed an autonomous device that is able to keep pace with pedestrian traffic and observe the codes shared by pedestrians.
In a campus building, the robot was able to move around at a human pace (1.2 metres per second) for more than twenty minutes. Equipped with sensors and webcams, the device has algorithms to map the environment and determine its position. To control it, engineers have used the same methods as driverless land vehicles.
Although researchers have not yet tried using it to control traffic, they believe it could serve to regulate the flow of people or cars with some of the tools it is already using —sensors, cameras and algorithms. For example, if a green or red lights were built in, it would be like an advanced traffic light. “We have not yet investigated a traffic control mode, but some of the same principles would apply such as avoiding collisions and the robot balancing its objectives (controlling traffic, or getting to a goal location) with the surrounding peoples’ intents (where they want to go),” explains Michael Everett, one of the engineers who has participated in its design.
The algorithm that detects people
In large cities, pedestrians being stuck by vehicles are commonplace —whether because of a lack of visibility on the part of the driver, because of distraction or due to negligence of the person crossing the street. Accidents of this type could be avoided thanks to a new algorithm devised by engineers at the University of California San Diego (USA).
Compared to current systems, the tool performs the detection in near real time and with greater accuracy. This technology, which incorporates deep learning models (trained with thousands of images), could be used in smart vehicles, robotics, and image and video search systems.
“We just work on the detection itself. It would be up to the car manufacturer to decide what to do with them. They would be computed in a computer inside the car,” explains Nuno Vasconcelos, professor of Electrical Engineering at the university and director of the research.
Crosswalks modified for smartphone zombies
Walking with our eyes glued to our smartphone has its risks, especially if we have to cross a road. In some cities, crosswalks now incorporate traffic lights embedded into the ground at the edges accessed by pedestrians. When the traffic light turns red, the lights on the ground also illuminate, thereby catching the attention of the person who is looking at their smartphone and has not noticed the traffic light. When the traffic light turns green, the ground-level lights also change.
These lights can also be oriented towards the drivers, especially if the crosswalk lacks traffic lights and is not clearly visible. With yellow flashing lights around it, drivers are warned from a distance that they have to slow down. Another option that has been implemented in the Chinese city of Chongqing is to designate exclusive lanes for people who use their smartphones while walking.
The most accessible route
Getting around with a shopping cart, a baby carriage or a wheelchair is often not an easy task. When these people calculate the route to get to a place, the usual navigation applications do not inform them if the sidewalk curbs are navigable or if a street is particularly steep.
The AccessMap tool, designed by researchers at the Taskar Center for Accessible Technology at the University of Washington, USA, addresses all these issues and offers customizable routes to inhabitants of Seattle. First, they have to indicate their preferences, i.e. what degree of slope they can deal with or if they need curb cuts, for example.
“In the usual routing, algorithms penalise for distance because they are looking for the shortest path,” says Anat Caspi, director of the Taskar Centre, in a conversation with OpenMind. In the case of AccessMap, the algorithm does not choose the shortest path, but rather the one that takes into account the user’s preferences.
Tolls with automatic payment
To reduce traffic in congested areas of large cities, some municipalities such as London have implemented an automatic toll system. With cameras and sensors located at strategic points, they photograph the license plates of cars that access a certain area and are automatically charged. In New York City they plan to launch the measure by the end of the year to limit the traffic levels in Manhattan, reports The New York Times.
In countries like Portugal they have designed huge arcs suspended over the toll roads that are equipped with cameras that photograph the license plates.
When accessing the first toll road, the driver only has to inform the system of the credit card on which he wants to be charged. After that there is nothing else to do and the arcs keep track of the routes the driver takes on these toll roads. He does not have to re-register every day, and at the end of the month, or whatever period he has stipulated, he will see the charge in his bank account.