• Journal of Mechanical Science and Technology
• /
• v.17 no.12
• /
• pp.1876-1885
• /
• 2003

The artificial potential field (APF) methods provide simple and efficient motion planners for practical purposes. However, these methods have a local minimum problem, which can trap an object before reaching its goal. The local minimum problem is sometimes inevitable when an object moves in unknown environments, because the object cannot predict local minima before it detects obstacles forming the local minima. The avoidance of local minima has been an active research topic in the potential field based path planing. In this study, we propose a new concept using a virtual obstacle to escape local minima that occur in local path planning. A virtual obstacle is located around local minima to repel an object from local minima. We also propose the discrete modeling method for the modeling of arbitrary shaped objects used in this approach. This modeling method is adaptable for real-time path planning because it is reliable and provides lower complexity.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.726-730
• /
• 1990

In this paper, assuming that local range information is available, a collision-free path planning algorithm for multiple mobile robots is presented by using Hopfield neural optimization network. The energy function of the network is built using the present position and the goal position of each robot as well as its local range information. The proposed algorithm has several advantages such as the effective passing around obstacles with the directional safety distance, the easy implementation of robot motion planning including its rotation, the real-time path planning capability from the totally localized computations of path for each robot, and the adaptivity on arbitrary environment since any special shape of obstacles is not assumed.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.1-8
• /
• 2008

Automatic parking assist system is one of the key technologies of the future automobiles. Control problem of a car-like vehicle is not easy due to the nonholonomic constraints. In this paper, a practical solution for planning a car-parking path is proposed according to the proposed motion space (M-space) approach. The M-space is the extension of the conventional configuration space (C-space). A collision-free, nonholonomic feasible path can be directly computed by the M-space conversion and a back-propagation of reachable regions from the goal. The proposed planning scheme provide not a single solution, but also a candidate solution set, therefore, optimization of the parking path can be easily carried out with respect to performance criteria such as safety, maneuvering, and so on. Presented simulation results clearly show that the proposed scheme provides various practical solutions.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.05a
• /
• pp.39-40
• /
• 2018

The goal of site layout planning(SLP) is to maximize the productivity and efficiency of the construction by reducing travel distance and material handling cost and manpower. However, SLPs are static layout schemes, which cannot be reorganized during the construction process to correspond with errors, phase transition, changing working environments on the site. To solve this problem, researches on dynamic site layout planning(DSLP) are emerging. This preliminary study clarifies characteristics of temporary facility's variables to develop the vertical DSLP algorithm of high-rise building construction.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.715-718
• /
• 1998

There are a lot of paths which connect between the mobile robot and the goat point. To make a mobile robot arrive at the goal point fastly, The optimal path is needed and a path palnning is necessary. In this paper, we propose a new method of path planning to find a path for mobile robot. It is based on Ginetic Algorithm for serching the optimal grobal path planning. Simulations show the efficiency for the grobal path planning.

• 한국IT서비스학회:학술대회논문집
• /
• 2003.05a
• /
• pp.215-221
• /
• 2003

In today's rapidly changing business environment, quality of responsiveness to customer requirements for short order cycles and on time delivery is becoming more important and considered as one of critical success factors in supply chain management. Yet despite its importance on reducing transportation cost and improving customer service, little attention has been given to the transportation planning system in Korea SI industry. In this paper, we present development of transportation planning system especially to deal with vehicle routing problem which has the goal to minimize the costs of daily transportation operation and to maximize customer delivery service. The system architecture with other enterprise application is presented and real-world constraints are well incorporated into the system by combining constraints programming and meta heuristics.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2342-2344
• /
• 1998

In this paper, the path planner is presented for a robot to achieve an efficient path forward the given goal position in two dimensional environment which is involved with partially unknown obstacles. The path planner consists of three major components: off-line path planning, on-line path planning, and modification of planned path. Off-line path planning is based on known environment and creates the shortest path. On-line path planning is for finding unknown obstacles. The modification can be accomplished, by genetic algorithm, to be smooth path for preventing slippage and excessive centrifugal force.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.2 no.6
• /
• pp.57-65
• /
• 1994

A collision-free path planning algorithm between an articulated robot and polyhedral obstacles using configuration space is presented. In configuration space, a robot is treated as a point and obstacles are treated as grown forbidden regions. Hence path planning problem is transformed into moving a point from start position to goal position without entering forbidden regions. For mapping to 3D joint space, slice projection method is used for first revolute joint and inverse kinematics is used for second and third revolute joint considering kinematic characteristics of industrial robot. Also, three projected 2D joint spaces are used in search of collision-free path. A proper example is provided to illustrate the proposed algorithm.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.193-194
• /
• 2019

The main purpose of the study is to reduce the accident death rate in the construction industry. To achieve this goal, the safety planning tasks were analyzed and assessed in terms of the importance and preventive effects of the tasks. Through the extensive literature reviews, the safety planning tasks were identified and reviewed by safety managers. Based on the data collected, a survey was conducted in order to receive responses by experts with knowledge on the effects and importance of preventive measures for safety. Then, the IPA method was employed to identify the safety manager's tasks that have an effect on performance indicators. The effective safety tasks identified are expected to have a critical role in reducing the accident death rate in the construction industry.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.