TOKYO -- Fujitsu Laboratories Ltd. has said that it has developed a learning system for humanoid robots that uses a dynamically reconfigurable neural network to enable the efficient learning of movement and motor coordination.
The company said the neural network approach makes the teaching of motion to a humanoid robot simpler and faster. Traditional approaches have required large amounts of software to be written to connect and control a robot's complex sensors and actuators.
Neural networks have so far proven to be very slow in learning movements, requiring days or even months, and they have been unable to generate a wide variety of motions, according to Fujitsu.
Fujitsu Lab's technology is based on an architecture of Central Pattern Generator (CPG) networks, mimicking a function found in earthworms and lampreys, which mathematically simulates a neural oscillator, which mimics a function found in vertebrates providing a neurological 'pulse'.
This advanced neural network features have been combined with a numerical perturbation (NP) method that quantifies the configuration and connection-weight status of the network.
This combination, known as CPG/NP learning, has been optimized and applied to motion learning in the new technology. In addition, Fujitsu simultaneously developed a software program, known as the Humanoid Movement-Generation System, which enables humanoid robots to learn a wide range of movements.
The central pattern generators generate motions in the robot using self-induced oscillations. These are evaluated using a pre-set evaluation function that determines whether the movement is correct or incorrect.
A big advantage is that the approach greatly minimizes the amount of software code involved in motion control, cutting it to less than one-tenth that used in conventional systems, Fujitsu said. For a robot with 20 moveable joints the learning time is reduced by 10 to the -30th power of the time previously required, Fujistus said. This enables the robot to learn to adapt and react instantly as it moves.
As part of the robot-motivated development work Fujitsu has also developed a programming language for coding neural networks. Later this year the software system will be included in the HOAP Series of humanoid robots that are already being marketed by Fujitsu Automation Limited
Fujitsu said more details of the system would be made public at Robodex 2003, which scheduled to take place at Pacifico, Yokohama, Japan from April 3 to 6.
RSS
Digital
10 emerging technologies to watch:
EE Times has compiled a list of emerging technologies that we think will be worth watching out for in 2010. Biofeedback or thought-control of electronics are among the contenders.
10 CEOs out in 2009:
It's been a tough year for the global electronics industry and CEOs. We survey the dismissal of 10 industry CEOs during the first three quarters of 2009 and what's ahead for the rest of the year.
Executive pay:
The economy stinks. Rank-and-file engineers are feeling the pain. What about technology CEOs? We crunched the numbers buried in corporate financial statements to find out. Here's what we found.
10 companies in trouble (revisited):
What follows is an updated version of 10 companies in trouble. Some companies have been removed since the last version, others remain. Still others have been added to the mix.
Early predictions for 2010:
The electronics industry is recovering, but there is still some uncertainty in the market. Some see a boom year in 2010. Some see a double dip. So what's in store for the rest of this year and 2010?
Top 10 IC vendors with cash:
The world's biggest IC companies by revenue rank not only among the best in their respective industry segments but are also more likely to have huge piles of cash that can be used to fund acquisitions, R&D and product development.
Notable women in microelectronics:
There is no better time than a global economic recession to examine the keys to successful corporate governance. So, EE Times has compiled an international list that celebrates women who are business and technology leaders in semis.
EE Times updates Silicon 60:
Seventeen companies have been added to the lastest version of our Silicon 60 list of emerging startups. Forty-three companies survived as emerging companies that are still worth watching.
RSS| 
Digital| 
Mobile
