- Goal Agent (GA)

194 The Future of Humanoid Robots – Research and Applications

The knowledge learned from the demonstrations is stored in the Long Term Memory (LTM). When given a new task in a new situation, ISAC retrieves the knowledge from the LTM and generates a new behavior according to the sensed task information in the STM and

The PA obtains the sensory information from environment. Normally, encoders on the joints of the robot, cameras on the head of the robot, and the force feedback sensor on the wrist of

**Executive Control Agent Perception-Action** 

Attention Network

Procedural Memory

the salience of each percept, and facilitates perceptual binding.

Sensory Ego Sphere

**Short Term Sensory Memory**

> **Working Memory System**

**Filtering & Focusing Agent**

> Episodic Memory

The obtained information is sent to and stored in the STM. The Sensory Ego Sphere (SES) is implemented in the STM, which performs spatio-termporal coincidence detection, mediates

The WMS stores the task-related information in chunks. This component is especially

The CEA provides central processing, decision making, and control policy generating for different task goals which is stored in the Goals Agent (GA). In hierarchy architecture, this

component accesses all of the sensed information and makes decision for tasks.

Declarative / Semantic Memory

**Internal Rehearsal System**

**Relational Mapping System Affordance Relations**

Central Executive Agent

Cognitive Control & Decision Making System

*DELIBERATION & COMMITTMENT*

**Long Term Memory**

Goals & Motivation System Goals Agent

**Affect Agent**

WMS[Kawamura et al., 2008]. - Perceptual Agents (PA)

the robot are implemented in this agent.

**Agent**

Perceptual Agents

Arm Agent Head Agent Hand Agent

Activator Agents


*REACTION*

Fig. 3. ISAC cognitive architecture. - Short Term Memory (STM)


important in the generation stage. - Central Executive Agent (CEA)

Environment Environment

Correspondingly, the GA stores the motivations or goals of tasks in situations.


The LTM stores the memory especially the knowledge for long term use. Procedural, semantic, and episodic knowledge are stored in this component. In imitation learning, the learned skill or knowledge is stored as procedural and episodic knowledge using a mathematical model.


The IRS evaluates the results of the decisions made from the CEA through internal rehearsal.

The activity of ISAC can be divided into two stages: Learning from Demonstration, Generation by Imitating. Figure 2 displays the control loop for the first stage: Learning from Demonstration.

Fig. 4. Control loop of the learning from demonstration.
