Researchers at the Georgia Institute of Technology (Georgia Tech) have developed an ultra-low power hybrid chip inspired by the human brain that could help small robots collaborate and learn from their experiences.
The new application-specific integrated circuit (ASIC) conserves power using a hybrid digital-analog time-domain processor in which the pulse-width of signals encodes the information.
The neural network IC accommodates both model-based programming and collaborative reinforcement learning, which could provide small robots greater capabilities for reconnaissance, search-and-rescue, and other missions.
The researchers demonstrated the new technology using robotic cars driven by the ASICs. The cars navigated through an arena floored by rubber pads and surrounded by cardboard block walls. As the robots searched for a target, they avoided traffic cones and each other, learning from the environment as the trial took place.
From Georgia Tech News Center
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA