Communications of the ACM
Watch an Autonomous Fencing Drone Dodge Sword Attacks
Stanford University researcher Ross Allen specializes in training robots to dodge obstacles at high speeds.
Credit: Ross Allen
Stanford University researcher Ross Allen specializes in training robots to dodge obstacles at high speeds.
He notes much of his research is focused on quadcopters because they are one of the most adaptable, dynamic, and controllable platforms to develop collision-avoidance technology. "[Quadcopter drones] are a great research platform in that they're complex enough that they add all these challenges that researchers like to see," Allen says.
His research is applicable to all robotic systems, but especially those that are fast-moving, or have behaviors they have to obey, such as cars. Allen demonstrates the new technology by swatting at it with a dueling sword.
The autonomous dodging software, called real-time kinodynamic motion planning, can help vehicles or equipment navigate from point to point on a plotted course, while responding to obstacles as they appear. The software enables a delivery drone or self-driving car to swerve and avoid an obstacle and then automatically re-plot its course to find its way back on track.
The software also could help autonomous boats, heavy robotic cranes, or spaceships react to small variables during complicated procedures, according to Allen.
From Inverse
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found