Figure 2 - uploaded by Evren Daglarli
Content may be subject to copyright.
![1 : Diploid chromosomal genetic string [24]](profile/Evren-Daglarli/publication/318542601/figure/fig1/AS:518462305783808@1500622454668/Diploid-chromosomal-genetic-string-24.png)
Source publication
![Figure 2.1 : Diploid chromosomal genetic string [24]](profile/Evren-Daglarli/publication/318542601/figure/fig1/AS:518462305783808@1500622454668/Diploid-chromosomal-genetic-string-24_Q320.jpg)
![Figure 2.3 : Self-Organizing Map Neural Network [32]](profile/Evren-Daglarli/publication/318542601/figure/fig3/AS:518462306033665@1500622454809/Self-Organizing-Map-Neural-Network-32_Q320.jpg)
In this study, the new approaches to the robotics subject, according to emotion and
cognitive based robot control approach, behavior generation and self-learning
paradigms are investigated for the real-time applications of multi-goal mobile robot
tasks, Artificial Emotion and Cognitive Mechanism Based Robot Control Architecture
is built up for a fo...
Citations
... Humanoid robots used in social areas need some human like extraordinary cognitive skills such as reasoning, decision making, problem solving. In order to realize them, these embodied skills should organize very complex behaviour patterns rather than performing more deterministic or repetitive tasks [5]. It is a quite challenging issue that high level cognitive skills including imitation of emotional responses, attention modulation, learning plasticity, modelling of environmental awareness (e.g. ...
... Up to now, there are several instances, which can count as significant qualification. Chronologically, they can be investigated by dividing into several sub-generations which include biologically inspired cognitive architectures, behaviour based and artificial emotion driven AI frameworks [5]. As a reverse engineering perspective of AI, the state of the Richter et al. [8] proposed an autonomous neural dynamics framework in 2014. ...
... To achieve better social interaction between human and robot, neurocognitive models, which are capable of continuously learning present adaptive solutions for developmental and social robotics can be employed. In daily life, as a personal assistant related to educational and rehabilitation purposes, humanoid robots with embodied cognitive skills can be used to support individuals struggling to interact with their social environment [1,5]. In order to realize them, the humanoid robot should have a human like perception system which requires spatio-temporal cognitive perception skills to interpret human's behavioural activity and establish joint attention with human in a shared workspace. ...
In this study, a novel cognitive architecture is proposed to realize computational model of limbic system and cognitive perceptual system inspired by human brain activity, which improves the interaction between human and robot, based on joint attention during the experiments. Using human-robot interaction (HRI), this brain-inspired framework can become a suitable solution for problems related to establishing and maintaining the joint attention.
After the presentation of the problem, literature survey, statement of hypotheses and research questions in chapter 1, some background material about the methods used throughout the thesis is described in chapter 2. Some candidate methods including spiking neural networks, neural mass and dynamic neural fields are investigated. The neural mass model deals with dynamics of neuron population. Population dynamics reflects responses as mean firing rates of population including spiking neurons. The dynamic neural field deals with field dynamics. In field dynamics, the neural activity behaves like wave packets which travel along the neural field. Computational mechanisms are mainly placed on bio-physical plausible neural structures with different dynamics. Also, different learning and adaptation algorithms are applied to the regions of computational models in the background of proposed cognitive perception system.
In chapter 3, the computational framework realizes perceptual cognition skills via thalamus and sensory cortices with multi-modal stimuli so that it provides to help achieving of recognition and modelling perceptual attention tasks for a humanoid robot which can easily communicate with its environment. In chapter 4, computational models of the proposed limbic system including the amygdala, hippocampus, and basal ganglia modules realize some cognitive processes such as emotional responses, episodic memory formation, and selection of appropriate behavioural responses, respectively. Using this system in the humanoid robot, success rates and response times of preschool children are evaluated so that attention deficiencies of them can be diagnosed and improved during the proposed interaction gameplay.
Experimental evaluation and verification tests have been performed to observe and control the physical and cognitive processes of the robot in a developed software framework embodied humanoid robot platform. Several interaction scenarios are implemented to monitor and evaluate the performance of computational model in the system architecture. Finally, results of the methodology used in this study are comprehensively compared with the different models for discussion of relative superiority with respect to each other. According to the findings, the proposed computational brain inspired cognitive architecture is effective in the successful establishment of the joint attention task between the humanoid robot and the human.
... The other coordination level units such as priority filter and instinctual module reconfigure behavioral parameters and different behaviors are derived as endless from available behaviors of the instinctual module [7]. Priorities of the behavioral actions are determined by the priority filter module in the coordination level. ...
... Observation part of the state-space HMM define emotional expressions and their transitions. The predicted behavior states in the coordination level are applied into this procedure [7]. Then below equation compute and obtain emotional expression corresponding to related behavioral state: ...
... The basic structure of the emotion core is shown in Fig. 3 [3]. Given a current behavioral state X k and provided with a second independently distributed uniform random number an emotional expression Y k+1 corresponding to a symbolic set; SE ¼ {distress, relief, aggressive, enjoyy} is observable with probability [7]: ...
This paper presents an artificial emotional-cognitive system-based autonomous robot control architecture for a four-wheel driven and four-wheel steered mobile robot. Discrete stochastic state-space mathematical model is considered for behavioral and emotional transition processes of the autonomous mobile robot in the dynamic realistic environment. The term of cognitive mechanism system which is composed from rule base and reinforcement self-learning algorithm explain all of the deliberative events such as learning, reasoning and memory (rule spaces) of the autonomous mobile robot. The artificial cognitive model of autonomous robot control architecture has a dynamic associative memory including behavioral transition rules which are able to be learned for achieving multi-objective robot tasks. Motivation module of architecture has been considered as behavioral gain effect generator for achieving multi-objective robot tasks. According to emotional and behavioral state transition probabilities, artificial emotions determine sequences of behaviors for long-term action planning. Also reinforcement self-learning and reasoning ability of artificial cognitive model and motivational gain effects of proposed architecture can be observed on the executing behavioral sequences during simulation. The posture and speed of the robot and the configurations, speeds and torques of the wheels and all deliberative and cognitive events can be observed from the simulation plant and virtual reality viewer. This study constitutes basis for the multi-goal robot tasks and artificial emotions and cognitive mechanism-based behavior generation experiments on a real mobile robot.
... They have multiple objectives which may conflict with each other. According to the temporary needs and goals of the robot, behaviors are dynamically changed in a realistic environment [2]. ...
... The size of behavioral search space comprises to anticipate all probabilities for these behaviors. There is exact relationship between selection of search space boundaries and input sensor range (perception limit) [2]. Behavior producing module allows establishing interaction of stimulus-response which can be called as relationship between sensor and motor ( Figure 1) [4]. ...
In this study, behavior generation and self-learning paradigms are investigated for the real-time applications of multi-goal mobile robot tasks. The method is capable to generate new behaviors and it combines them in order to achieve multi goal tasks. The proposed method is composed from three layers: Behavior Generating Module, Coordination Level and Emotion -Motivation Level. Last two levels use Hidden Markov models to manage dynamical structure of behaviors. The kinematics and dynamic model of the mobile robot with non-holonomic constraints are considered in the behavior based control architecture. The proposed method is tested on a four-wheel driven and four-wheel steered mobile robot with constraints in simulation environment and results are obtained successfully.
... Behavioral system can be considered as low-level control component of general architecture. This level generates different behaviors as relational fuzzy logic inference process [2]. ...
... The size of behavioral search space comprises to anticipate all probabilities for these behaviors. There is exact relationship between selection of search space boundaries and input sensor range (perception limit) [2]. ...
... Also it can be considered as core of behavior producing process. This section includes inner states which belong to behavior producing module [2]. Behavior producing module allows establishing interaction of stimulus-response which can be called as relationship between sensor and motor ( Figure 1) [4]. ...
In this study, behavioral system based robot control architecture is built up for a four-wheel driven and four-wheel steered mobile robot. Behavioral system is determined as evolutionary neural-fuzzy inference system for behavior generation and self-learning processes in the general robot control architecture. The kinematics and dynamic model of the mobile robot with non-holonomic constraints is used as present structure which is modeled in previous studies. The posture and speed of the robot and the configurations, speeds and torques of the wheels can be observed from the simulation plant and virtual reality viewer. The behaviors are investigated regarding their gains, fuzzy inference structures, real-time applicability and their coordination.
... The other coordination level units such as priority filter and instinctual module reconfigure behavioral parameters and different behaviors are derived as endless from available behaviors of the instinctual module [7]. Priorities of the behavioral actions are determined by the priority filter module in the coordination level. ...
... Observation part of the state-space HMM defines emotional expressions and their transitions. The predicted behavior states in the coordination level are applied into the procedure [7]. Then below equation compute and obtain emotional expression corresponding to related behavioral state. 1 1 . ...
... Given a current behavioral state Xk and provided with a second independently distributed uniform random number an emotional expression 1 + k Y corresponding to a symbolic set; SE = {Distress, Relief, Aggressive, Enjoy. . . . } is observable with probability [7] ) ...
This paper presents artificial emotional system based autonomous robot control architecture. Hidden Markov model developed as mathematical background for stochastic emotional and behavior transitions. Motivation module of architecture considered as behavioral gain effect generator for achieving multi-objective robot tasks. According to emotional and behavioral state transition probabilities, artificial emotions determine sequences of behaviors. Also motivational gain effects of proposed architecture can be observed on the executing behaviors during simulation.
