• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.444-451
• /
• 2013

The purpose of this study was to investigate the changes in temporospatial variables in healthy elderly and healthy adults during usual walking, narrow base walking and centerline-guided walking. Twenty healthy elderly and nineteen healthy adults were participated in this study. In each conditions, the subjects were walked on a 6m walkway at comfortable self-selected speeds under three conditions : (1) usual walking, (2) walking within a 50% of the distance between the subject's ASIS (3) walking along a centerline. GAITRite system was used for kinematic analysis to assess the temporospatial variables. There were no significant changes in healthy adults(p>.05), but walking speed, cadence, H-H base support, functional ambulation performance were significantly decreased progressively as pathway narrowed in elderly adults(p<.05). The results show that elderly people had more difficulty with walking on narrow pathway for fear of falling. This study provides data for use in basic research into safe walking and preventing falling for elderly.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.1
• /
• pp.51-56
• /
• 2013

In order to apply a biped robot in real world, the robot requires a robust walking and a function of localization, path planning and navigation. Recently, localization and path planning using RFID of mobile robot has been studying. However, when the biped robot walks, it has unstability and tends to leave the path. In the paper we propose a method of walking stabilization using FSR(Force Sensing Resistor), Gyro and accelerometer for the real biped robot. Also a path tracking algorithm using RFID sensor attached in robot's foot is proposed based on localization of the robot. The proposed algorithm is verified from walking experiments using real biped robot on uneven terrain and path tracking experiments on the RFID environments.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.86-90
• /
• 2007

본 논문에서는 Particle Swarm Optimization(PSO) 기법을 이용한 이족보행로봇의 보행 계획방법을 제안한다. 이족보행로봇의 보행 프리미티브를 기반으로 PSO의 학습 및 군집 특성을 이용하여 장애물이 있는 작업공간에서 보행 계획을 수행하였다. 먼저 PSO의 탐색알고리즘을 사용하여 장애물을 회피하는 실행 가능한 보행 프리미티브들의 순서를 찾아내고 탐색된 순서를 바탕으로 경로 최적화 알고리즘을 수행하는 보행 계획방법을 제안하였다. 제안된 PSO 기반 이족보행로봇의 보행 계획방법은 모의실험을 통하여 발걸음 탐색 시간이 줄고 최적화된 보행 경로를 생성하는 것을 검증하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.89-92
• /
• 2022

본 논문에서는 딥러닝 모델 기반 보행자의 GPS 경로를 예측하는 시스템을 제안한다. 다양한 경로 예측 방식들 중 본 논문은 GPS 데이터 기반 경로 예측 연구이다. 시계열 데이터인 보행자의 GPS 경로를 학습하여 다음 경로를 예측하도록 하는 딥러닝 모델 기반 연구이다. 본 논문에서는 보행자의 GPS 경로를 딥러닝 모델이 학습할 수 있도록 데이터 구성 방식을 제시하였으며, 예측 범위에 큰 제약이 없는 예측 딥러닝 모델을 제안한다. 본 논문의 딥러닝 모델에 적합한 파라메터들을 제시하였으며, 우수한 예측 성능을 보이는 결과를 제시한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.622-628
• /
• 2009

A proper walking pattern is to be assigned for a walk of multi-legged robots. For the purpose of identifying a good walking pattern for multi-legged robots, this paper consider a simple model of quadruped robotic walking and analyze its walking balance based on the centroid of foot polygons formed in every step. A performance index to estimate the walking balance is also proposed. Simulation studies show that the centroid trajectory of foot polygons and the walking balance in a common quadruped walking are different according to the walking pattern employed. Based on the walking balance index and a bio-mimetic aspect, a useful walking pattern for quadruped robots is finally addressed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.3
• /
• pp.67-74
• /
• 2011

In recent years, with increasing utilization of mobile devices such as smartphones, the need for PNS(Pedestrian Navigation Systems) that provide guidance for moving pedestrians is increasing. For the navigation services, road network is the most important component when it comes to creating route and guidance information. In particular, pedestrian network requires modeling methods for more detailed and vast space compared to road network. Therefore, more efficient method is needed to establish pedestrian network that was constructed by existing field survey and manual editing process. This research proposed a pedestrian network creation method appropriate for pedestrians, based on CNS(Car Navigation Systems) data that already has been broadly constructed. Pedestrian network was classified into pedestrian link(sidewalk, side street, walking facility) and openspace link depending on characteristics of walking space, and constructed by applying different methodologies in order to create path that similar to the movements of actual pedestrians. The proposed algorithm is expected to become an alternative for reducing the time and cost of pedestrian network creation.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• Archives of design research
• /
• v.19 no.2 s.64
• /
• pp.81-90
• /
• 2006

Pedestrians perceive differently from the sideway views or the exteriors of the buildings on the way to their destinations. Therefore, the navigation experience can become much different when the path was chosen based on the individual's preference from it is not. By focusing on the effects of the individual pedestrian' path choice on their navigation, this paper presents an algorithm designed for pedestrians to be able to explore their preferred path and proposes a prototype of navigation system based on the algorithm. The navigation support system searches for the best path upon their individual preferences and information of the destination. The system provides the process of retrieving the final path via the pedestrian-support system interaction. The path retrieval is peformed with the combinational matrix of keywords that are formulates Fuzzy theory from the correlations between the terms describing preferences used in the path preference survey. This paper presents the potentials of the path finding method tailored to pedestrians' preferences by a simulation of the proposed path retrieval algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.103-111
• /
• 2023

Mountains area, especially walking in open space is important for special active field which is based on mountain terrain. Recent research on pedestrian-path includes elements about pedestrian and various environment by analyzing network, but it is mainly focusing on limited space except for data-poor terrain like a mountain terrain. This paper proposes an architecture to generate walking path considering the slope for mountain terrain open space through virtual network made of mesh. This architecture shows that it reflects real terrain more effective when measuring distance using slope and is possible to generate mountain walking path using open space unlike other existing services, and is verified through the test. The proposed architecture is expected to utilize for pedestrian-path generation way considering mountain terrain open space in case of distress, mountain rescue and tactical training and so on.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.566-571
• /
• 2008

In this paper, we propose a footstep planning method of biped robot based on the Particle Swarm Optimization(PSO). We define configuration and locomotion primitives for biped robots in the 2 dimensional workspace. A footstep planning method is designed using learning process of PSO that is initialized with a population of random objects and searches for optima by updating generations. The footstep planner searches for a feasible sequence of locomotion primitives between a starting point and a goal, and generates a path that avoids the obstacles. We design a path optimization algorithm that optimizes the footstep number and planning cost based on the path generated in the PSO learning process. The proposed planning method is verified by simulation examples in cluttered environments.