Changmok Oh

Bed-type robotic system for the bedridden

An intelligent bed robot system (IBRS) is proposed to help the elderly and the disabled for their independent life in bed. The IBRS is a special bed equipped with two robot arms and an array of pressure sensors attached onto the mattress. The pressure distribution on the mattress is used to estimate the pose of the patient, and an appropriate assistance is provided by the robot arms

Control of mobile robots using RBF network

This paper deals with handling the unknown factors, such as the external disturbance and the unknown dynamics, for a mobile robot control. We propose a RBF network based controller for compensate for them. The stability of the proposed controller is proven by using Lyapunov function. To show the effectiveness of the proposed controller, several simulation results are presented. Through the simulations, we show that the proposed controller can overcome the modelling uncertainty and the disturbances. Also the proposed RBF controller outperforms the previous works from the viewpoint of computation time, which is a crucial fact for a real-applications.

RFID sensor deployment using differential evolution for indoor mobile robot localization

This paper presents the sensor deployment method to design a RFID sensor network for the mobile robot localization using evolutionary approach. For this purpose, we employ the differential evolution (DE), which is well-known for promising performance. We propose two variation methods, the direct optimization strategy for the maximum usage of initial information intuitively and the full coverage optimization strategy for the dense coverage for the surveillance and the security. In that case, the proper tuning of parameters of DE is essential. We experiment sensor deployment in two maps for providing guidance about parameter tuning. The experimental results show better sensor deployment result according to guided parameter setting. The full coverage optimization strategy also shows proper result using guided parameters from the standard DE case.

Control of a nonholonomic mobile robot using an RBF network

This article deals with handling unknown factors, such as external disturbance and unknown dynamics, for mobile robot control. We propose a radial-basis function (RBF) network-based controller to compensate for these. The stability of the proposed controller is proven using the Lyapunov function. To show the effectiveness of the proposed controller, several simulation results are presented. Through the simulations, we show that the proposed controller can overcome the modelling uncertainty and the disturbances. The proposed RBF controller also outperforms previous work from the viewpoint of computation time, which is a crucial fact for real-time applications.

Development of a future Intelligent Sweet Home for the disabled

This article introduces a new smart house, the Intelligent Sweet Home, developed at the Korea Advanced Institute of Science and Technology (KAIST), Korea, for testing advanced concepts for independent living for elderly and physically handicapped individuals. The work focuses on human-friendly technical solutions for motion/mobility assistance, health monitoring, and advanced human–machine interfaces that provide easy control of both assistive devices and home-installed appliances. The smart house behaves in accordance with the users commands, the users intentions, and the users current health status. Various interfaces based on hand gestures, voice, body movement and posture, and the health monitoring system were studied and tested. This article emphasizes the structure of the system.

Intelligent Bed Robot System: Pose Estimation Using Sensor Distribution Mattress

In this paper, an intelligent bed robot system (IBRS) is proposed, that is a special bed equipped with robot manipulator. To assist a patient using IBRS, pose and motion estimation process is fundamental. It is designed to help the elderly and the disabled for their independent life in bed without other assistants

Integrated path planning for a partially unknown outdoor environment

In this paper, we propose an integrated path planning algorithm that reasons on integration between a local path planners based on sensory information and global path planners based on global prior information in a partially unknown outdoor environment. A local path planner typically generates collision-free paths using laser range sensors, sonar sensors, etc., nearby robots or unmanned ground vehicles. In contrast, a global path planner generates efficient paths based on given cost function using initially given maps. To generate efficient collision-free paths in a partially unknown outdoor environment, we utilize both information properly in RRT as the local path planner and A* as global path planner and separate a role of each planner not to overlap with each other. It is assume that a partially unknown outdoor environment only provides obstacle information nearby a robot or a vehicle within a range of a sensor and prior approximate information about the entire map. The proposed integrated path planner improves overall computational time and cost to obtain one of the complete path from start to goal.

Modified A* algorithm for outdoor environments with risk and velocity map

A* algorithm can generate the optimized unique path if the cost function is well designed based on the given information. Especially for global path planning (GPP), A* is one of best solutions because GPP itself assume that a prior information. In this paper, classic A* algorithm is modified for outdoor military robot with risk and velocity map. For this purpose, we design velocity map using digital elevation map (DEM) and the cost function for considering risk and velocity map.

EEG signal classification based on PCA and NN

Electroencephalogram (EEG) pattern classification plays an important role in the domain of brain computer interface. However, EEG data is a multivariate time series data which contains noise and artifacts. In this paper we present methods contains for EEG pattern classification which jointly employ principal component analysis (PCA) and neural networks (NN). We believe that this hybrid approach offers the better chance for reliable classification of the EEG signal

User pose estimation using sensor distribution bed

In this paper, an intelligent bed robot system (IBRS) is proposed, that is a special bed equipped with robot manipulator. To assist a patient using IBRS, pose and motion estimation process is fundamental. It is designed to help the elderly and the disabled for their independent life in bed without other assistants.