• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.360-365
• /
• 2013

The paper introduces dynamic generation technique of foot trajectories using CPG(Central Pattern Generator). In this approach, the generated foot trajectories can be changeable according to variable outputs of CPG in various environments, because they are given as mapping functions of the output signals of the CPG oscillators. It enables to provide an adaptable foot trajectory for environmental change. To demonstrate the effectiveness of the proposed approach, experiments on humanoid robot Nao is executed in the Webot simulation. The performance and motion features of CPG based approach is analyzed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.5
• /
• pp.683-689
• /
• 2014

The paper introduces dynamic generation technique of foot trajectories for humanoid robots using CPG(Central Pattern Generator) and proposes adaptive walking method for slope terrains combining a feedback network. The proposed CPG based technique generates the trajectory of foot in the Cartesian coordinates system and it can change the step length adaptively according to the feedback information. To cope with variable slope terrains, the sensory feedback network in the CPG are designed using the geometry relationship between foot position and body center position such that humanoid robot can maintain its stability. To demonstrate the effectiveness of the proposed approach, the experiments on humanoid robot Nao are executed in the Webot simulation. The performance and motion features of the CPG based approach are compared and analyzed focusing on the adaptability in slope terrains.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1040-1046
• /
• 2015

This paper introduces GP(Genetic Programming) based color detection model for an object detection of humanoid robot vision. Existing color detection methods have used linear/nonlinear transformation of RGB color-model. However, most of cases have difficulties to classify colors satisfactory because of interference of among color channels and susceptibility for illumination variation. Especially, they are outstanding in degraded images from robot vision. To solve these problems, we propose illumination robust and non-parametric multi-colors detection model using evolution of GP. The proposed method is compared to the existing color-models for various environments in robot vision for real humanoid Nao.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.264-272
• /
• 2022

Human-robot cooperative tasks are increasingly required in our daily life with the development of robotics and artificial intelligence technology. Interactive reinforcement learning strategies suggest that robots learn task by receiving feedback from an experienced human trainer during a training process. However, most of the previous studies on Interactive reinforcement learning have required an extra feedback input device such as a mouse or keyboard in addition to robot itself, and the scenario where a robot can interactively learn a task with human have been also limited to virtual environment. To solve these limitations, this paper studies training strategies of robot that learn table balancing tasks interactively using deep reinforcement learning with human's facial expression feedback. In the proposed system, the robot learns a cooperative table balancing task using Deep Q-Network (DQN), which is a deep reinforcement learning technique, with human facial emotion expression feedback. As a result of the experiment, the proposed system achieved a high optimal policy convergence rate of up to 83.3% in training and successful assumption rate of up to 91.6% in testing, showing improved performance compared to the model without human facial expression feedback.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.404-412
• /
• 2020

Typically everyday human life tasks involve at least two people moving objects such as tables and beds, and the balancing of such object changes based on one person's action. However, many studies in previous work performed their tasks solely on robots without factoring human cooperation. Therefore, in this paper, we propose cooperative robot for table balancing using Q-learning that enables cooperative work between human and robot. The human's action is recognized in order to balance the table by the proposed robot whose camera takes the image of the table's state, and it performs the table-balancing action according to the recognized human action without high performance equipment. The classification of human action uses a deep learning technology, specifically AlexNet, and has an accuracy of 96.9% over 10-fold cross-validation. The experiment of Q-learning was carried out over 2,000 episodes with 200 trials. The overall results of the proposed Q-learning show that the Q function stably converged at this number of episodes. This stable convergence determined Q-learning policies for the robot actions. Video of the robotic cooperation with human over the table balancing task using the proposed Q-Learning can be found at http://ibot.knu.ac.kr/videocooperation.html.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.511-521
• /
• 2018

The ability to realize human-motion imitation using robots is closely related to developments in the field of artificial intelligence. However, it is not easy to imitate human motions entirely owing to the physical differences between the human body and robots. In this paper, we propose a work chain-based inverse kinematics to enable a robot to imitate the human motion of upper limbs in real time. Two work chains are built on each arm to ensure that there is motion similarity, such as the end effector trajectory and the joint-angle configuration. In addition, a two-phase filter is used to remove the interference and noise, together with a self-collision avoidance scheme to maintain the stability of the robot during the imitation. Experimental results verify the effectiveness of our solution on the humanoid robot Nao-H25 in terms of accuracy and real-time performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.5
• /
• pp.663-668
• /
• 2018

A combined CPG (Central Pattern Generator) based foot trajectory and GA (Genetic Algorithm) based joint compensation method is presented for adaptive humanoid walking. In order to increase an adaptability of humanoid walking for rough terrains, the experiment for rolling terrains are introduced. The CPG based foot trajectory method has been successfully applied to basic slops and variable slops, but has a limitation for the rolling terrains. The experiments are conducted in an ODE based Webots simulation environment using humanoid robot Nao to verify a stability of walking for various rolling terrains. The proposed method is compared to the previous CPG foot trajectory technique and shows better performance especially for the cascade rolling terrains.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1551-1556
• /
• 2016

A combined CPG (Central Pattern Generator) based foot trajectory and GP (Genetic Programming) based joint compensation method is presented for the adaptive humanoid walking. The CPG based foot trajectory methods have been successfully applied to basic slops and variable slops with slow rates, but have a limitation for the steep slop terrains. In order to increase an adaptability of humanoid walking for the rough terrains, a GP based joint compensation method is proposed and combined to the CPG (Central Pattern Generator) based foot trajectory method. The experiments using humanoid robot Nao are conducted in an ODE based Webots simulation environmemt to verify a stability of walking for the various aslope terrains. The proposed method is compared to the previous CPG foot trajectory technique and shows better performances especially for the steep varied slopes.

• Korean Journal of Cognitive Science
• /
• v.33 no.4
• /
• pp.205-228
• /
• 2022

This study aimed to confirm the effect of social and relational behavior types of robots on human cognition in human-robot interaction. In the experiment, the participants evaluated trust in robots by watching a video on the robot Nao interacting with a human, in which the robot made an error and then made an effort to restore trust. The trust recovery behavior was set as three conditions: an internal attribution in which the robot acknowledges and apologizes for an error, a condition in which the robot apologizes for an error but attributes it externally, and a non-action condition in which the robot denies the error itself and does not take any action for the error. As the result, in all three cases, the error was perceived as less serious when the robot apologized than when it did not, and the ability of the robot was also highly evaluated. These results provide evidence that human attitudes towards robots can respond sensitively depending on the robot's behavior and how they overcome errors, suggesting that human perception towards robots can change. In particular, the fact that robots are more trustworthy when they acknowledge and apologize for their own errors shows that robots can promote positive human-robot interactions through human-like social and polite behavior.

• The Journal of Korea Robotics Society
• /
• v.10 no.2
• /
• pp.90-95
• /
• 2015

The main goal of e-learning systems is just-in-time knowledge acquisition. Rule-based e-learning systems, however, suffer from the mesa effect and the cold start problem, which both result in low user acceptance. E-learning systems suffer a further drawback in rendering the implementation of a natural interface in humanoids difficult. To address these concerns, even exceptional questions of the learner must be answerable. This paper aims to propose a method that can understand the learner's verbal cues and then intelligently explore additional domains of knowledge based on crowd data sources such as Wikipedia and social media, ultimately allowing for better answers in real-time. A prototype system was implemented using the NAO platform.