Fujitsu Labs applies neural networks to robot learning
March 27, 2003 | Source: Silicon Strategies
Fujitsu Laboratories Ltd. has developed a learning system for humanoid robots that uses a dynamically reconfigurable neural network to enable efficient learning of movement and motor coordination.
The technology is based on Central Pattern Generator (CPG) networks, mimicking a function found in earthworms and lampreys that mathematically simulates a neural oscillator. This is combined with a numerical perturbation (NP) method that quantifies the configuration and connection-weight status of the network.
For a robot with 20 moveable joints, the learning time is reduced by 1030 of the time previously required.