Tech
How a Robot Makes Up Its Mind: New Visualization System for Navigation
Catherine Griffin
First Posted: Oct 29, 2014 12:31 PM EDT
How does a robot make a decision? It's all based on its programming, but understanding what goes into this decision-making process is important for future system designs. That's why scientists created a new visualization system that shows what a robot is thinking as it tries to make up its "mind."
"Normally, a robot may make some decision, but you can't quite tell what's going on in its mind-why it's choosing a particular path," said Ali-akbar Agha-mohammadi, one of the researchers, in a news release. "But if you can see the robot's plan projected on the ground, you can connect what it perceives with what it does to make sense of its actions."
In order to test the system, the researchers had a Roomba-like robot decide where to travel in order to avoid a human pedestrian walking back and forth while getting to the other side of a room. While the robot considered its options, a large pink dot appeared to follow the pedestrian. Lines, each representing a possible route for the robot to take, were radiated across the room in meandering patterns and colors. The green line signified the optimal route. As the pedestrian and robot moved, these lines changed.
"As designers, when we can compare the robot's perceptions with how it acts, we can find bugs in our code must faster," said Agha-mohammadi. "For example, if we fly a quadrotor, and see something go wrong in its mind, we can terminate the code before it hits the wall, or breaks."
In fact, the new system may help speed up the development of systems, such as self-driving cars, package-delivering drones, and other robots that need to plan routes in the moment.
"There are a lot of problems that pop up because of uncertainty in the real world, or hardware issues, and that's where our system can significantly reduce the amount of effort spent by researchers to pinpoint the causes," said Shayegan Omidshafiei, one of the researchers.
The findings could be huge in terms of robot development in the future. By using this system, scientists can quickly test programming to see if it works or if it needs finer tuning.
See Now:
NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone
TagsRobot ©2024 ScienceWorldReport.com All rights reserved. Do not reproduce without permission. The window to the world of science news.
More on SCIENCEwr
First Posted: Oct 29, 2014 12:31 PM EDT
How does a robot make a decision? It's all based on its programming, but understanding what goes into this decision-making process is important for future system designs. That's why scientists created a new visualization system that shows what a robot is thinking as it tries to make up its "mind."
"Normally, a robot may make some decision, but you can't quite tell what's going on in its mind-why it's choosing a particular path," said Ali-akbar Agha-mohammadi, one of the researchers, in a news release. "But if you can see the robot's plan projected on the ground, you can connect what it perceives with what it does to make sense of its actions."
In order to test the system, the researchers had a Roomba-like robot decide where to travel in order to avoid a human pedestrian walking back and forth while getting to the other side of a room. While the robot considered its options, a large pink dot appeared to follow the pedestrian. Lines, each representing a possible route for the robot to take, were radiated across the room in meandering patterns and colors. The green line signified the optimal route. As the pedestrian and robot moved, these lines changed.
"As designers, when we can compare the robot's perceptions with how it acts, we can find bugs in our code must faster," said Agha-mohammadi. "For example, if we fly a quadrotor, and see something go wrong in its mind, we can terminate the code before it hits the wall, or breaks."
In fact, the new system may help speed up the development of systems, such as self-driving cars, package-delivering drones, and other robots that need to plan routes in the moment.
"There are a lot of problems that pop up because of uncertainty in the real world, or hardware issues, and that's where our system can significantly reduce the amount of effort spent by researchers to pinpoint the causes," said Shayegan Omidshafiei, one of the researchers.
The findings could be huge in terms of robot development in the future. By using this system, scientists can quickly test programming to see if it works or if it needs finer tuning.
See Now: NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone