Technology
New learning method balances robot stability and tracking performance
Aerospace engineering researchers at the University of Illinois Urbana-Champaign combined reinforcement learning with control theory to guarantee robot stability while improving tracking performance by up to 15% over existing methods, covering wheeled, flying and six-legged robots.
Published · Updated · Source: Tech Xplore · Robotics · AI translation
IllustrationTech Xplore Robotics reports that a robot must not only learn to complete a task optimally but also do so without going beyond reasonable expectations. Until now, roboticists could have one or the other. Researchers in aerospace engineering at The Grainger College of Engineering, University of Illinois Urbana-Champaign, proposed a new method that combines reinforcement learning with control theory to guarantee robot stability while improving tracking performance.
The report says the method improves tracking performance by up to 15% compared with existing methods, involving wheeled, flying and six-legged robots. The above information comes from the original source and was organized by AI.
Read the original source