Proposed Smartphone App to Find Parking Spaces

Drivers may one day be able to find a parking space on their smartphones instead of on the street if a new system envisioned by University of Michigan researchers becomes reality. It would use radar sensors that are already built into many vehicles to create a crowd-sourced, real-time map of parking availability. The map could be linked to a smartphone app, enabling drivers to find street parking more easily or even reserve a spot in a lot or structure before they hit the road. The system could also enable autonomous vehicles to find parking on their own. The researchers recently conducted a preliminary test of the concept on U-M's North Campus, circling a parking lot in a radar sensor-equipped test vehicle to capture data. They'll then compare the radar sensor data with video footage of the test to determine just how well the car can spot empty parking spaces. If the research goes as planned, the team hopes to have a smartphone app ready for use within four to five years. "Up to 30 percent of traffic volume in cities is due to drivers who are circling for a parking space," Saigal said. "A system like this could help reduce congestion, reduce the environmental impact of driving and make urban life less stressful."

Transcript

00:00:00 I think this will change the way we park. What we learn it will be useful to society. The goal of the project is to determine empty parking spots along the highway or in a parking structure, to provide information to the individuals looking for parking spots so they can drive directly to the spot rather than having to search for one. We want to solve this problem using the technology in the market - not something like twenty years or thirty years in the future. So the system is based on using intelligent vehicles that can sense the environment. At this point in time the auto manufacturers are putting the sensors on the high end cars. There are sensors that detect whether you are going to get too close to a car next to you so they beep and let you know that

00:00:50 you...you should be aware and use that to see if we can find empty spots. While we are driving the six radars are scanning the environment, and we try to drive at five miles per hour because this will give us a very constant reading from the radars. All this information is being sent to a computer which is in the back seat of the car, behind the back seat of the car, the information in the car is processed very quickly. As soon as a car passes an empty parking spot it detects it, immediately sends it through wireless communication to the local infrastructure and from there within a couple of seconds having passed the parking spot the users will have the information. I've always been interested in reducing pollution. It will reduce the traffic in the sense

00:01:41 that people would go directly to the spot that they have identified and if that is full they would look in the app and find the next nearest one. Anything you do to reduce travel time is a plus. Of course, the challenging part is like some time there are more than one reflection from one car. The environment has lots of noise: that pedestrian, like trees like the curb. All will have signal to create noise in the background. So how can you distinguish the car and the environments is another challenging problem we have. What we are looking for is a very highly accurate methodology that'll pick out... make very few errors in selecting the empty spots. Our hope is that within the next year and a half we will have a pilot program running within Ann Arbor. We are not producing

00:02:31 devices, we are not designing cars. We are taking information and then processing it and then passing it on. That is what industrial engineers do best. ...And then flew to Dallas and the pilot got off and a new pilot got on. And she flew the plane to Detroit all these pieces are interconnecting: if it's icy in Atlanta and that plane doesn't make it to Dallas...