A new memory model for humanoid robots - introduction of associative memory using chaotic neural network
- Resource Type
- Conference
- Authors
- Itoh, K.; Miwa, H.; Nukariya, Y.; Takanobu, H.; Takanishi, A.
- Source
- RO-MAN 2004. 13th IEEE International Workshop on Robot and Human Interactive Communication (IEEE Catalog No.04TH8759) Robot and human interactive communication Robot and Human Interactive Communication, 2004. ROMAN 2004. 13th IEEE International Workshop on. :125-130 2004
- Subject
- Robotics and Control Systems
Computing and Processing
Signal Processing and Analysis
Humanoid robots
Associative memory
Chaos
Neural networks
Chaotic communication
Oscillators
Humans
Cognitive science
Bifurcation
Neurons
- Language
We have been developing emotion expression humanoid robots in order to develop new mechanisms and functions for a humanoid robot that has the ability to communicate naturally with a human by expressing human-like emotions. In 2003, we introduced the "need model" to the robot mental model so that a robot could generate and express actively its behavior based on its mental state. We implemented the mental model with need in the emotion expression humanoid robot WE-4R (Waseda eye no.4 refined). We also studied the dynamics of a simple harmonic oscillator driven by the chaotic force. The bifurcation parameter of chaotic force is modulated by the position of the harmonic oscillator. We have been studying a system of many harmonic oscillators (neurons) interacting via a chaotic force by using these ideas since 2002. We propose a memory model using a chaotic neural network for human friendly communication. We implemented this model in emotional expression humanoid robot WE-4R.