Please tell us about yourself
Ramakrishnan Narayanan, a graduate student in industrial engineering at University of Illinois, Urbana Champaign, has spent the majority of his time at ISE working on a project that hopes to create a connected infrastructure between autonomous cars and their surroundings.
Together with Professor Richard Sowers, Professor Daniel Work, the department of Mathematics, and the Illinois Geometry Lab, the research group has created an image recognition algorithm that can identify objects surrounding a car.
They recorded a video through an on-board camera on a car and collected information using the car’s built-in computer.
Later, they processed the video through the image recognition algorithm, which identified the objects seen in the video: people, other cars, buildings, traffic lights, and more.
Their goal is to develop a product that can do this in real time.
Doing this would turn any car into a semi-autonomous vehicle.
What is your research interest?
My work on autonomous vehicle technology featured on the University of Illinois website:
My work is a method to focus on the current mobility revolution. With the need for more intelligent data gathering, there is also a growing need for using existing technology and infrastructure to achieve this goal, without incorporating expensive, complicated systems. Though not the primary aim of this project, the autonomous vehicle could very well be the biggest beneficiary of this technology. I believe this can help in their development of autonomous vehicles and getting our cities ready for a driverless future. We are giving way to shared mobility, combined with regular mass transit and pedestrian-aware street infrastructure. There is a large “networked mobility system” that has a potential to be tapped. Autonomous cars then, will be here soon, to add to the mix.
How did you end up in such an offbeat, unconventional and cool career?
Coming into this project, Narayanan says he had little experience in this area of research, but his interest in autonomous cars has allowed him to become proficient.
I’ve always loved cars. I used to watch them on the street to identify the models when I was a child. I studied mechanical engineering as an undergraduate at Ramaiah Institute of Technology.
Before we get to the technical stuff, I need to know: What’s your next car going to be?
What does the new research entail?
We have recorded a video through an on-board camera on a car and collected information using the car’s built-in computer. After processing the video through the image recognition software, it identified the objects in the video: people, other cars, buildings, traffic lights and other data sources.
What’s your ultimate goal?
He hopes he can apply what he’s learned to a career in the industry.
“I want to be able to use machine learning and big data to build models that give you bigger, better insights into making decisions,” he says. “It’s only limited by what you can think of. Machine learning is essentially a way of teaching a machine how to recognize something, and that recognition need not stop at images or something specific. It can be used in so many different applications, and I see myself working on something like that in the future.”
How does that work?
Many cars already have built-in sensors and information retrieval systems. They let the manufacturers collect data on the speed and direction of travel. Some insurance companies install devices on cars to track the driver’s behavior to the cost of the driver’s insurance. Some large cities conduct a pedestrian count that influences the time on pedestrian crossing lights. Our system could allow those cities to do that in real time.
So what is the time frame?
It would probably take about 30 to 50 years for most cars to become autonomous. We’ll have a gap where some of the cars are autonomous and a few are not. We need cars to talk to each other. We also want cars to talk to the traffic lights, to pedestrian crossings and use other data for analysis of real-time traffic, measurement of pedestrian density and other data sources.
How does your work benefit the industry?
The algorithm can identify surrounding objects such as vehicles, buildings and people.
There are also several potential spinoff applications. For example, Narayanan says they are working on getting the algorithm to recognize bicyclists who are wearing helmets, or to recognize specific cars as they go through intersections.
“It’s all about having this entire infrastructure and your traffic talking to each other, giving each other information in real time about what the situation is,” he says.
The system could also provide insight on human behavior. Currently, many insurance companies install devices on cars to track the driver’s behavior — how fast you’re going, how hard you brake — and determine the cost of the driver’s insurance.
“This can be version two of that,” Narayanan says. “You need more in-depth information on when these things happen. Then you can tell if someone’s an overly cautious driver and is at a greater risk.”
There is still much to be explored with autonomous vehicles, and Narayanan says this specific project is an advancement into the unknown.
“This is something new that, in my knowledge, has not been done a lot before,” he says. “There really hasn’t been research on using data, not just from your cameras but from other sensors within the car, and combining that to build a bigger picture.”
However, as this research continues, he says it will become more difficult to expand the abilities of their image recognition algorithms.
Currently, the algorithms are able to identify objects after being trained with a data set of stock images.
If you want the algorithm to identify a person, you give the algorithm images of different people until it learns what a face looks like.
“That’s easy to do in the current state, but what’s difficult to do is make it identify specific things,” Narayanan says. “That’s where I think we’ll have the greatest challenge.”
What other projects come from this research?
We are working on getting the algorithm to recognize bicyclists who are wearing helmets, or to recognize specific cars as they go through intersections.