• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.2
• /
• pp.1-8
• /
• 2019

Optimal path planning refers to find the safe route to the destination at a low cost, is a major problem with regard to autonomous navigation. Sampling Based Planning(SBP) approaches, such as Rapidly-exploring Random Tree Star($RRT^*$), are the most influential algorithm in path planning due to their relatively small calculations and scalability to high-dimensional problems. $RRT^*$-Smart introduced path optimization and biased sampling techniques into $RRT^*$ to increase convergent rate. This paper presents an improvement plan that has changed the biased sampling method to increase the initial convergent rate of the $RRT^*$-Smart, which is specified as m$RRT^*$-Smart. With comparison among $RRT^*$, $RRT^*$-Smart and m$RRT^*$-Smart in 2 & 3-D environments, m$RRT^*$-Smart showed similar or increased initial convergent rate than $RRT^*$ and $RRT^*$-Smart.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.73-82
• /
• 2023

Optimization of Construction Site Layout Planning (CSLP) heavily relies on workers' travel paths. However, traditional path generation approaches predominantly focus on the shortest path, often neglecting critical variables such as individual wayfinding tendencies, the spatial arrangement of site objects, and potential hazards. These oversights can lead to compromised path simulations, resulting in less reliable site layout plans. While Deep Reinforcement Learning (DRL) has been proposed as a potential alternative to address these issues, it has shown limitations. Despite presenting more realistic travel paths by considering these variables, DRL often struggles with efficiency in complex environments, leading to extended learning times and potential failures. To overcome these challenges, this study introduces a refined model that enhances spatial navigation capabilities and learning performance by integrating workers' visibility into the reward functions. The proposed model demonstrated a 12.47% increase in the pathfinding success rate and notable improvements in the other two performance measures compared to the existing DRL framework. The adoption of this model could greatly enhance the reliability of the results, ultimately improving site operational efficiency and safety management such as by reducing site congestion and accidents. Future research could expand this study by simulating travel paths in dynamic, multi-agent environments that represent different stages of construction.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.552-557
• /
• 2009

In this paper, we propose hybrid navigation system, for obstacle detection and avoidance in Intelligent wheelchairs (IWs). To robustly detect obstacles and avoid them on various environments, hybrid navigation system combines both range-sensor and camera information. For this, 10 range-sensors (2 ultrasonic and 8 infra-red sensors) and CCD camera are used. Through processing the informations obtained from those sensors, our system can detect obstacles with various sizes and shapes, and then avoid them. To assess the effectiveness of the proposed hybrid navigation system, it was tested on complex environments including various obstacles, then the results showed the potential of our system as mobility aids for disabled people.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.11
• /
• pp.2424-2430
• /
• 2012

The current Navigation System for the Visually Impaired Person has a short and limited communication distance and can't receive enough information from Visually Impaired Person to assist directly. In addition, because the path is dangerous and incomplete for the Visually Impaired Person, moving with White Stick is still inconvenient and dangerous. To solve this problem we implement communication that can send and receive video, voice, location information between the Visually Impaired Person's Smart Portable Navigation System Development and assistant's PC.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.7-10
• /
• 2007

This paper presents a fuzzy footstep planner for humanoid robots in complex environments. First, we define locomotion primitives for humanoid robots. A global planner finds a global path from a navigation map that is generated based on a combination of 2.5 dimensional maps of the 3D workspace. A local planner searches for an optimal sequence of locomotion primitives along the global path by using fuzzy footstep planning. We verify our approach on a virtual humanoid robot in a simulated environment. Simulation results show a reduction in planning time and the feasibility of the proposed method.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.2 no.3
• /
• pp.119-126
• /
• 2010

The response of ship roll oscillation under random ice impulsive loads modeled by Poisson arrival process is very important in studying the safety of ships navigation in cold regions. Under both external and parametric random excitations the evolution of the probability density function of roll motion is evaluated using the path integral (PI) approach. The PI method relies on the Chapman-Kolmogorov equation, which governs the response transition probability density functions at two close intervals of time. Once the response probability density function at an early close time is specified, its value at later close time can be evaluated. The PI method is first demonstrated via simple dynamical models and then applied for ship roll dynamics under random impulsive white noise excitation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.5
• /
• pp.583-589
• /
• 2013

In this paper, we proposed a system that efficiently provides support maps which includes the grid based terrain analysis information. To do this, we use the FDB which is defined as a GIS database that contains features with attributes attached to the features. The FDB is composed of a number of features and feature classes. In order to create support maps, it is necessary to classify feature classes that are associated with each support map and to search them in a grid map. The proposed system use a ontology model to classify semantically feature classes and the quad-tree data structure to find them in a grid map quickly. Therefore, our system is expected to be utilized for global path planning of UGV. In this paper, we show the possibility through an experimental implementation.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2450-2452
• /
• 2004

Map building is essential to a mobile robot navigation system. Localization and path planning methods depend on map building strategies. A topological map is commonly constructed using the GVG(Generalized Voronoi Graph). The advantage of the GVG based topological map is compactness. But the GVG method have many difficulties because it consists of collision-free path. In this paper, we proposed an extended map building method, the AVG (Areal Voronoi Graph) based topological map. The AVG based topological map consists of collision-free area. This feature can improve map building, localization and path planning performance.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1731-1732
• /
• 2008

Recently, many researchers have developed various service robots, in which the position estimation and path following of mobile objects have been raised an important problem. We should know where a mobile robot so that there are many introduced localization and path following schemes. In this paper, we propose an efficient localization algorithm for the precise localization of a mobile robot with the glaser stream sensor. We use the glaser stream sensor for following a given path in indoor environments. Since the glaser stream sensor utilizes precise optical motion estimation technology, we can achieve high speed motion detection and high resolution. The experimental results show that the glaser stream sensor may be a good sensor for many indoor service robots.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.907-908
• /
• 2006

We describe a method for localizing a mobile robot in its working environment using a vision system and Virtual Reality Modeling Language (VRML). The robot identifies landmarks in the environment, using image processing and neural network pattern matching techniques, and then its performs self-positioning with a vision system based on a well-known localization algorithm. After the self-positioning procedure, the 2-D scene of the vision is overlaid with the VRML scene. This paper describes how to realize the self-positioning, and shows the overlap between the 2-D and VRML scenes. The method successfully defines a robot's path.