• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.363-370
• /
• 2022

Grasping a target object among clutter objects without collision requires machine intelligence. Machine intelligence includes environment recognition, target & obstacle recognition, collision-free path planning, and object grasping intelligence of robot hands. In this work, we implement such system in simulation and hardware to grasp a target object without collision. We use a RGB-D image sensor to recognize the environment and objects. Various path-finding algorithms been implemented and tested to find collision-free paths. Finally for an anthropomorphic robot hand, object grasping intelligence is learned through deep reinforcement learning. In our simulation environment, grasping a target out of five clutter objects, showed an average success rate of 78.8%and a collision rate of 34% without path planning. Whereas our system combined with path planning showed an average success rate of 94% and an average collision rate of 20%. In our hardware environment grasping a target out of three clutter objects showed an average success rate of 30% and a collision rate of 97% without path planning whereas our system combined with path planning showed an average success rate of 90% and an average collision rate of 23%. Our results show that grasping a target object in clutter is feasible with vision intelligence, path planning, and deep RL.

• Land and Housing Review
• /
• v.7 no.4
• /
• pp.225-237
• /
• 2016

This study is to investigate actual condition of passenger terminals, public facilities which are used by unspecified individuals, with high spread effect of certification system of Barrier Free introduced in 2007, evaluate possibility of the certification and prepare an effective way for certification in order to spread and settle the certification system. According to the investigation on the facilities' equipment level of 349 passenger terminals, which being nationally operated, 217 terminals could be certified and non-certified were 58. And, 29 was evaluated as the passenger terminals with high possibility to get Barrier Free certification by small scale of remodeling. The level of Barrier Free of investigated passenger terminals, according to the actual condition with certification index, were 40~55 percent. While the level of Barrier Free of internal facilities of the terminals was over 90percent, the level of sanitary facilities, information facilities, etc. fell short of 50 percents. In this study, pilot project of Barrier Free certification is proposed for enhance of passenger terminal facilities. Moreover, the selection of passenger terminals with high possibility of certification, local governments' strong will as the targets of pilot project for improvement of amenity level and Barrier Free certification and monitoring the project results are the way of the project.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of KIISE:Information Networking
• /
• v.34 no.5
• /
• pp.340-347
• /
• 2007

Vehicle safety service can be effectively achieved with inter-vehicle communication technologies, in which moving vehicles transmit a safety related urgency information such as traffic accidents, sudden stops, obstacle appearance etc. They usually utilize a broadcast of message propagation method because the communicating vehicles are not known each other. The pure broadcasting scheme does not satisfy the requirements of vehicle safety communication service due to the transmission delay with frequent message collisions. To resolve this problem, this paper presents a group based propagation method for the multi-hop transmission, in order to deliver an urgency message to the reasonable size of vehicle troop. A group header is elected in considering of the position information of vehicles and radio transmission range. And a vehicle equivalent group is formed with the header. With benefits of the group based transmission, it is possible to minimize the unnecessary transmission and the possibility of message collisions. Simulation results show that the message propagation performance is so stable regardless of vehicle's congestion degree.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1243-1248
• /
• 2016

This paper investigated the channel link budget for Wireless Avionics Intra-Communication (WAIC) in 4.4GHz. The band 4.2~4.2GHz was allocated for the communication service among aeronautical applications in world radiocommunication conference (WRC). Wireless channels in aircraft was modelled by the combination of path loss, shadowing effect caused by obstacles, and fading caused by multipath signals. In addition, wireless channels in aircraft are categorized into 6 groups according to various locations of transmitter and receiver. We analyzed the channel link budget for the 6 channel groups in terms of maximum transmission distance and outage probability. Our analysis and intensive computer simulation results show that the propagation characteristics of group A, B, and F is superior to group C, D, E, and the propagation of group E is the most vulnerable. Also, these results can be utilized as basic reference for the channel analysis of intra-aircraft or similar environment.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.2
• /
• pp.181-190
• /
• 2014

The optimized flight path planning which is appropriate for UAV operation with high performance and multiplex sensors is required for efficient ISR missions. Furthermore, a mission visualization tool is necessary for the assessment of MoE(Measures of Effectiveness) prior to mission operation and the urgent tactical decision in peace time and wartime. A mission visualization and analysis tool was developed by combining STK and MATLAB, whose tool was used for UAV ISR mission analyses in this study. In this mission analysis tool, obstacle avoidance and FoM(Figure of Merit) analysis algorithms were applied to enable the optimized mission planning.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.224-233
• /
• 2000

An important feature of virtual reality is the facility for the user to move around a virtual environment in a natural and easily controlled manner, Navigation. Navigation involves changing the perspective of the user in the virtual environment (VE). Natural locomotion methods are able to contribute to a sense of presence and reality. This paper focuses on the navigation method in the virtual environment, one of the major interfaces for the interactivity between human and virtual environments in virtual reality circumstances and worlds. It proposes a new navigation method: Intelligent Cruise-Control Navigation (ICCN), which provides a natural and user-centered navigation method in virtual environment and can improve the reality and the presence. Intelligent Cruise-Control Navigation is composed of three major phases: Constant Velocity Navigation, Collision Detection and Avoidance, and Path Adjustment. The ICCN can reduce the user's fatigue and improve the user's presence and reality in the virtual environment. Through the experimental study it has been determined that the ICCN will be a natural, straightforward, and useful interface in VE.

• Spatial Information Research
• /
• v.21 no.1
• /
• pp.87-100
• /
• 2013

Recently, the use of locational information is growing rapidly. GPS technology has been adopted generally for obtaining locational information in outdoor spaces. In the other hand, the researches on indoor positioning have been carried out applying WLAN, RFID or Bluetooth technology because of the multi-path interference of GPS signal caused by the physical obstacles such as walls or columns in buildings. However, such technologies for indoor positioning cost too much to build sensing infrastructure and compute-intensive processes are involved. Furthermore, the accuracy of location estimation is variable caused by interior structures in buildings. In this study, to make up for the limitations, descriptive data such as phone number, unique room numbers, or business names readily available in mixed-use buildings is used for extracting location information. Furthermore, during the process, a geocoding method using character matching is applied to this study enabling prompt location estimation and sublating the fluctuation of accuracy caused by interior structures. Based on the proposed method in this study, an architecture is designed, and three-dimensional viewer program is developed for the implementation of this study. Also, this research is quantitatively analyzed through match rate and processing time of proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.396-399
• /
• 2018

In this paper, we propose a motion recognition system for identification and interaction with simulator used in the realistic biathlon simulator. The proposed system tried to improve the motions data which is obstructed by the obstacles or overlapping joints and the motion due to the fast motion in the process of recognizing the various motion patterns in the biathlon. In this paper, we constructed a multi-camera motion recognition system based on IoT devices, and then we applied a skeletal area interpolation method for normal motion identification. We designed a system that can increase the recognition rate of motion from the biathlon. The proposed system can be applied to the analysis of snow sports motion and it will be used to develop realistic biathlon simulator system.

• Journal of Digital Contents Society
• /
• v.15 no.1
• /
• pp.129-136
• /
• 2014

Wi-Fi fingerprinting system is a very popular positioning method used in indoor spaces. The system depends on Wi-Fi Received Signal Strength (RSS) from Access Points (APs). However, the Wi-Fi RSS is changeable by multipath fading effect and interference due to walls, obstacles and people. Therefore, the Wi-Fi fingerprinting system produces low position accuracy. Also, Wi-Fi signals pass through walls. For this reason, the existing system cannot distinguish users' floor. To solve these problems, this paper proposes a LED fingerprinting system for accurate indoor positioning. The proposed system uses a received optical power from LEDs and LED-Identification (LED-ID) instead of the Wi-Fi RSS. In training phase, we record LED fingerprints in database at each place. In serving phase, we adopt a K-Nearest Neighbor (K-NN) algorithm for comparing existing data and new received data of users. We show that our technique performs in terms of CDF by computer simulation results. From simulation results, the proposed system shows that a positioning accuracy is improved by 8.6 % on average.