International Journal of Humanoid Robotics

The special issue topics focus on the computational intelligence and its application for robotics. Its areas reach out comprehensive ranges; context-awareness software, omnidirectional walking and fuzzy controller of dynamic walking for humanoid robots, pet robots for treatment of ASD children, fuzzy logic control, enhanced simultaneous localization and mapping, fuzzy line tracking for mobile robots, and so on. Computational intelligence (CI) is a method of performing like humans. Generally computational intelligence means the ability of a computer to learn a specific task from data or experimental results. Meanwhile robotic system has many limits to behave like human beings. The robotic system might be too complex for mathematical reasoning, it might contain some uncertainties during the process, or the process might simply be stochastic in real life. Real-life problems cannot be translated into binary code for computers to process it. Computational intelligence might solve such problems.

As Internet of Things (IoT)-based sensors have emerged recently, new technologies are being developed for users to provide suitable services by recognizing the surrounding situations. In the service robot sector, many researches are being carried out in order to exploit the collected data from IoT-based sensors. In addition, researches on robot middleware using context information are actively performed.

In this paper, we propose a robot SW platform, which provides IoT-based context-aware services. This robot software platform consists of Ontology Agent, Robot Service Execution Engine, and Context Handler. The Ontology Agent is a module that searches information, such as sensor location, value type, etc., of the IoT devices stored in Ontology Repository and provides them to the Context Handler. The Context Handler reads IoT devices’ data and checks whether service transition conditions are met. If the conditions are satisfied, the data is delivered to the Robot Service Execution Engine, which is in charge of executing services. In experiments, we show a procedure executing the context-aware robot services through definition of robot services, a robot service execution engine, and a context handler, etc.

In this paper, we propose an omni-directional walking pattern generator to make a child-sized humanoid robot walk in any direction. The proposed omni-directional walking pattern generator creates walking patterns for which zero moment point (ZMP) is located on the center of the supporting foot. For humanoid robots to adapt to human’s life and perform missions, it should be taller than the minimum height of a child. In this paper, we designed a humanoid robot which is similar to a child who is taller than 1m. We show the humanoid robot’s kinematics, design of a three-dimensional (3D) model, develop mechanisms and the hardware structures with servo-motors and compact-size PC. The developed humanoid robot “CHARLES2” stands for Cognitive Humanoid Autonomous Robot with Learning and Evolutionary System-Two. The inverse kinematics of its legs is described. The principle of the omni-directional walking pattern generator is discussed to create walking motions and overcome the robot’s mechanical deficiencies. We applied the proposed omni-directional walking pattern generator based on ZMP. Through experiments, we analyzed walking patterns according to the creation and changing parameter values. The results of the experiments are presented for the efficacy of our proposed walking engine.

The dynamic walking stability of biped robot is a challenging research topic. In this paper, the fuzzy controller on zero movement point (ZMP) criterion is implemented to maintain the balance of dynamic walking. We designed a force sensitive resistor (FSR) sensor circuits to collect information from the sensors for the ZMP trajectory tracking. The robot walking has an imbalance when the ZMP shows the risk of moving out the footprint. The fuzzy controller is provided to drive the ZMP inside the ZMP reference area, by adjusting a suitable angle for the ankle and hip joint. In order to determine the ZMP reference, we compute the inverse kinematic and Jacobian coordinates from the biped robot model. In this research, we also introduce the biped robot configuration for control dynamic walking. A user interface is designed to conventionally observe the ZMP trajectory generation. The experimental results for stability of dynamic walking are presented to appreciate the proposed method.

This study deals with language therapy and play therapy using a cat robot for children with autistic spectrum disorders (ASDs) and verifies the effects of such therapy. Two versions of cat character robots, so-called Semyung robot (SERO) I and II, are suggested. First, SERO I is applied in the field test, which indicated some effective tendancy of ASD children. The robot design was improved accordingly, and the second field test was performed. Through the two field tests, we verified that this robot can be used effectively in the treatment of ASD children.

The study of individual mobile devices has been widely conducted. In this paper, we propose the design of some fuzzy logic control systems for the control of the Segway-type mobile robot, which is a kind of inverted pendulum system. We first design two conventional fuzzy logic control systems for position and balance control of the Segway-type mobile robot. And then, we design another two fuzzy logic control systems with a single input variable for position and its balance control. We also propose a new defuzzification method called vectored sum scheme. Finally, in order to check the feasibility of the proposed systems we present some simulation examples.

Tanks are typically used for the storage of oil by the petrochemical industry, and the storage quality is largely determined by the safety of the equipment. Recently, Electromagnetic Acoustic Transducer (EMAT) technology has been the focus of many non-destructive examinations, as EMATs can generate elastic waves without contact, thereby making it easy to carry out the process of detection. The Shear Horizontal (SH)-guided waves that are generated by an EMAT are modeled in a plate made of ferromagnetic material, and this is of particular interest regarding the testing of welded structures. This paper provides an EMAT-sensor design that can be used to find cracks in the welds of a tank whereby the need for people to climb onto the tank is removed; furthermore, regarding cases where the amplitude signal of the SH-wave EMATs is too low, a simulation is used in this paper to propose a method that improves the transduction efficiency.

FastSLAM, such as FastSLAM 1.0 and FastSLAM 2.0, is a popular algorithm to solve the simultaneous localization and mapping (SLAM) problem for mobile robots. In real environments, however, the execution speed by FastSLAM would be too slow to achieve the objective of real-time design with a satisfactory accuracy because of excessive comparisons of the measurement with all the existing landmarks in particles, particularly when the number of landmarks is drastically increased. In this paper, an enhanced SLAM (ESLAM) is proposed, which uses not only odometer information but also sensor measurements to estimate the robot’s pose in the prediction step. Landmark information that has the maximum likelihood is then used to update the robot’s pose before updating the landmarks’ location. Compared to existing FastSLAM algorithms, the proposed ESLAM algorithm has a better performance in terms of computation efficiency as well as localization and mapping accuracy as demonstrated in the illustrated examples.

In this paper, a navigation method using fuzzy line tracking, QR code recognition and path planning algorithm is proposed for the transportation robot. We build a grid map by attaching QR codes on a floor and using lines that are gaps between tiles. The transportation robot is developed with a camera to capture floor images that is used to detect QR code and extract lines’ parameters by applying linear equation and FIR filter. A fuzzy decision-maker is designed to solve the deviation problem occurring during a navigation process between QR codes. The QR code is used to get the current position and recognize the direction to neighbor QR codes. Finally, the D*Lite algorithm is applied to search for an optimal path from the robot position to a goal position on the grid map using QR codes. The proposed method is verified by the navigation experiments of the transportation robot in the real environment. The robot can follow the optimal path obtained from planning algorithm with high stability and accuracy.

As human–robot interaction is widely and increasingly used, automated user verification has become a necessary condition for system access. Signature recognition is one of the representative methods for user verification. In this paper, a novel method using Pseudo-Inked Signature for online signature recognition is proposed. Pseudo-Inked Signature consists of three types of information of pen pressure value, pen tilting angle, and pen theta angle during online signature writing. We propose a fusion method for three different types of information by mimicking the inked effect of real pen writing. Besides a style of penmanship, Pseudo-Inked Signature reflects the characteristics of handwriting behavior. Therefore, it can make different Pseudo-Inked Signature even though the original signature images from different users look very similar to each other. Similarly, it can also make more similar Pseudo-Inked Signatures even though the original signature images from the same user look somewhat different to each other. In addition, since only one gray-scale image is dealt with to represent the signature style of a person by Pseudo-Inked Signature image, it is efficient and very easy to handle. Finally, we tested user verification experiments using $k$-NN classifier. The experimental results show that Pseudo-Inked Signature is good enough for the real application.

A distributed simulation and control method for humanoid robot systems based on the discrete event net models is proposed. Extended Petri nets are adopted as an effective tool to describe, design and control the cooperative behavior of robots. Based on hierarchical net decomposition, conceptual and detailed Petri net models are assigned to the upper level and the lower level controllers, respectively. For the lower level control, individual net models of robots are executed on separate local controllers. The unified net representation for the hierarchical coordination of cooperative execution control by multiple robots is proposed. Overall control software is implemented and executed on a general hierarchical and distributed control architecture corresponding to the hardware structure of robot systems. The upper level system controller and lower level local controllers are concurrently executed, communicating events information (enabled transitions) with each other, so that the cooperative robotic tasks are successfully performed.