Intelligent Robot Motion using Fuzzy logic-Based CTP and Artificial Neural Networks Mohsen Davoudi and Mehdi Davoudi Department ofElectrical Engineering, Abhar Azad University, Abhar, Iran. Department ofElectrical Engineering, Imam Hossein University. mohsen.davoudiggmail.com, davoodiiggmail.com Abstract (GCL) [1].Fuzzy Logic-Based probability theory has Human has some perception based behavior seen in the fundamental ability to operate on perception-based his body movements. Movements of hands, legs, head, information, which bivalent logic-based probability etc show the inner emotion of the person in specific theory does not posses. Hence, fuzzy logic offers a situations subconsciously. This paper introduces a conceptual structure, which accommodates partiality Generalized Constraint Language (GCL) for humanoid and granularity. We define a standard GCL for robots to categorize data neededfor trajectory tracking humanoid robots to categorize data needed for for each joint of the robot which lead to emotion trajectory tracking for each joint which lead to emotion mimicry. An Artificial Neural Network generates mimicry or intelligent robot motion. velocity and acceleration for each joint of humanoid Uncertainty is an attribute of the input information. using GCL values. A concept that plays a key role in This information, whatever its form is, after Fuzzy emotion mimicry with CTP is GCL. analysis, may be represented as GCL [2]. Fuzzy analyzer gets two types of Linguistic proposition that Keywords: Emotion; fuzzy; GCL; humanoid robot are detected from a sentence: 1) The type of emotion, 2) The intensity of emotion. For example I say "move your hands very angry", 1. INTRODUCTION two words are detected: angry and very. An idea which underlies the approach described in this paper is that an emotion may be viewed as a proposition Humanoid Robots are going to do many tasks like that fuzzy analyzer approximates by means of the humans. But as we know human has some perception intensity and type of emotion. Furthermore, a based behavior. proposition plays the role of a carrier of information. In Humans have capability to perform a wide variety of the next step, an Artificial Neural Network (ANN) physical motions without any measurements and any generates velocity and acceleration for each joint of computations. In performing such movements, humans humanoid using GCL values as inputs. A concept that employ perceptions of time, situation, possibility, inner plays a key role in with CTP is GCL. Because it is an emotions and other attributes of physical and mental interface between two sections of this analyze: a) objects. emotion interpreter (Fuzzy analyzer), b) a data Reflecting the bounded ability of the human brain to generator for physical motion of the humanoid robot. resolve details of motions, perceptions are intrinsically The computational theory of perceptions enhances imprecise. the ability of Al to deal with real-world problems such The computational theory of perceptions (CTP) as robots in which decision relevant information is a contains a special capability to compute and reason mixture of measurements and perceptions. Humanoid with perception-based information. This paper intelligent motion is compromise between perceptions introduces a fuzzy logic-based analyzer that interprets of emotions in common sense and measured data for the linguistic emotions that are common among people trajectory tracking in humanoid's joints. into what is called the Generalized Constraint Language Proc. 5th IEEE Int. Conf. on Cognitive Informatics (ICCI'06) Y.Y. Yao, Z.Z. Shi, Y. Wang, and W. Kinsner (Eds.)69 1-4244-0475-4/06/$20.OO @2006 IEEE69 ieeexplore.ieee.org ﻗﺎﺑﻞ ﺑﺎرﮔﯿﺮى از ﺳﺎﯾﺖ- ﭼﯿﻦIEEE ICCI ﻣﻘﺎﻟﻪ ﻣﻨﺘﺸﺮه در