Boston University engineering student Emily Fitzgerald has developed a robot that can recognize specific objects and steer around obstacles without human guidance. She says the robot is almost self-thinking when it comes to navigating roadblocks.
A camera sends information about what it sees to a laptop sitting atop the robot, and the laptop communicates with a laboratory desktop.
Fitzgerald used a deep neural network to train the robot to recognize objects. "There's an algorithm that will take a ton of pictures of one object and will put it in and compile it all," she says. "Then, we basically assign a number to it."
Fitzgerald says the robot "will come upon an object and it will say, 'Oh, there's an object in front of me, let me think about it.' It will...find a picture that corresponds with the object, pick that number, and then it will be able to use that as a reference, so it can exclaim, 'Oh, it's a ball,' 'It's a cone,' or whatever object I had decided to teach it."
Self-guided, object-spotting robots could potentially be used to explore the landscapes of distant planets.
Fitzgerald's effort to give her bot a brain has inspired her to pursue a career in bioimaging. She expects robotic surgical devices running off neural networks to someday detect objects in human patients.
From BU Today
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA