• 한국항공운항학회지
• /
• 제24권1호
• /
• pp.1-9
• /
• 2016

In this paper, we integrate three degree of freedom(3DOF) point-mass model for aircraft and three-dimensional path generation algorithms using dubins curve and nonlinear path tracking law. Through this integration, we apply the path generation algorithm to the path planning, and verify tracking performance and feasibility of using the aircraft 3DOF point-mass model for air traffic management. The accuracy of modeling 6DOF aircraft is more accurate than that of 3DOF model, but the complexity of the calculation would be raised, in turn the rate of computation is more likely to be slow due to the increase of degree of freedom. These obstacles make the 6DOF model difficult to be applied to simulation requiring real-time path planning. Therefore, the 3DOF point-mass model is also sufficient for simulation, and real-time path planning is possible because complexity can be reduced, compared to those of the 6DOF. Dubins curve used for generating the optimal path has advantage of being directly available to apply path planning. However, we use the algorithm which extends 2D path to 3D path since dubins curve handles the two dimensional path problems. Control law for the path tracking uses the nonlinear path tracking laws. Then we present these concomitant simulation results.

• 센서학회지
• /
• 제33권4호
• /
• pp.196-202
• /
• 2024

Path-planning, a critical component of mobile robot navigation, comprises both local and global planning. Previous studies primarily focused on enhancing the individual performance of these planners, avoiding obstacles, and computing an optimal global path from a starting position to a target position. In this study, we introduce a practical path-planning framework that employs a target planner to bridge the local and global planners; this enables mobile robots to navigate seamlessly and efficiently toward a global target position. The proposed target planner assesses the visibility of waypoints along the global path, and it selects a reachable navigation target, which can then be used to generate efficient control commands for the local planners. A visibility-based target planner can handle situations, wherein the current, target waypoint is occupied by unknown obstacles. Real-world experiments demonstrated that the proposed pathplanning framework with the visibility-based target planner allowed the robot to navigate to the final target position along a more efficient path than the framework without a target planner.

• International Journal of Control, Automation, and Systems
• /
• 제5권6호
• /
• pp.674-680
• /
• 2007

The probabilistic roadmap (PRM) method, which is a popular path planning scheme, for a manipulator, can find a collision-free path by connecting the start and goal poses through a roadmap constructed by drawing random nodes in the free configuration space. PRM exhibits robust performance for static environments, but its performance is poor for dynamic environments. On the other hand, reinforcement learning, a behavior-based control technique, can deal with uncertainties in the environment. The reinforcement learning agent can establish a policy that maximizes the sum of rewards by selecting the optimal actions in any state through iterative interactions with the environment. In this paper, we propose efficient real-time path planning by combining PRM and reinforcement learning to deal with uncertain dynamic environments and similar environments. A series of experiments demonstrate that the proposed hybrid path planner can generate a collision-free path even for dynamic environments in which objects block the pre-planned global path. It is also shown that the hybrid path planner can adapt to the similar, previously learned environments without significant additional learning.

• 제어로봇시스템학회논문지
• /
• 제20권2호
• /
• pp.211-217
• /
• 2014

This paper addresses an algorithm of path planning for autonomous driving of a ground vehicle in waypoint navigation. The proposed algorithm is flexible in utilization under a large GPS positioning error and generates collision-free multiple paths while pursuing minimum traveling time. An optimal path reduces inefficient steering by minimizing lateral changes in generated waypoints along a path. Simulation results compare the proposed algorithm with the A* algorithm by manipulation of the steering wheel and traveling time, and show that the proposed algorithm realizes real-time obstacle avoidance by quick processing of path generation, and minimum time traveling by producing paths with small lateral changes while overcoming the very irregular positioning error from the GPS.

• 한국정보처리학회논문지
• /
• 제2권3호
• /
• pp.343-353
• /
• 1995

자율 운송 장치나 이동 로보트에 대한 경로 이동 문제는 이동하고자 하는 환경을 완전히 알고 있거나, 장애물이 고정된것으로 가정해 왔다. 따라서, 임의의 환경에 대해 부분적으로 알고 있거나 미지의 환경에서의 자율 운송 장치의 운항을 위해서는 이들 경로 기법은 직접적인 적용이 불가능하고, 확장이 어렵다. 본 논문에서는 이들 문제점을 개선하기 위해서 쿼드트리 기법을 도입하였으며, 임의의 환경에서 자율적으 로 경로 계획을 할 수 있는 알고리즘을 제안하였고, 알고리즘의 타당성을 시뮬레이션 을 통해 증명하였다.

• 대한인간공학회지
• /
• 제24권2호
• /
• pp.71-77
• /
• 2005

In spite of the importance of nuclear power as one of major electric energies in Korea, the nuclear safety has become the most serious social issue in the operation of the nuclear power plant. In this paper, a virtual work simulation program was developed to predict exposure dose during radiation work in radwaste storage. The work simulation program was developed. using $Java ^{TM}$applet and VRML-virtual reality modeling language. A numerical algorithm to find the optimal work path which minimize exposure dose during the given work, was developed and exposure dose on the optimal work path was compared with that on the shortest path. Comparing with the shortest path for the given work, the predicted optimal path consumed longer work time by II% but reduced total exposure dose by 46%. The simulation result showed that the exposure dose depended on not only work time, but also the distance between the worker and the radiation source. The developed simulation program could be a useful tool for the planning of radioactive waste work to increase the radiation safety of workers.

• 한국정보통신학회논문지
• /
• 제13권8호
• /
• pp.1483-1490
• /
• 2009

본 논문에서는 수정된 유전자 알고리즘과 퍼지 추론 시스템을 이용한 무인 자율주행 이송장치의 다중경로계획을 연구하였다. 기존의 다중경로계획을 위한 방법으로는 최적화 알고리즘들을 이용한 작업별회귀 방법과 매시간 각 개체마다 경로를 재계획하는 방법이 있다. 이러한 방법들은 한 대의 이송장치가 작업을 하기 위해서는 한 대 이상의 이송장치가 정지해야하므로 시간과 에너지 측면에서 비효율적이며, 연산량이 많아 오류가 발생할 가능성이 있다. 본 논문에서는 이러한 문제점들을 해결하기 위해 수정된 유전자 알고리즘과 퍼지 추론 시스템을 이용한 다중경로계획을 제안한다. 제안한 알고리즘의 성능 평가를 위하여 무인 자율주행이 가능한 2대의 이송장치를 설계 제작하였고 지게차와 동일한 주행 제어부를 탑재하여 다중경로계획을 실험하였다. 실험 결과, 빠르고 최적화된 경로 계획과 효율적인 충돌 회피가 가능함을 확인 할 수 있었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• 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.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.743-747
• /
• 1996

A Potential Field Method is applied to the proposed algorithm for the planning of collision-free paths of redundant manipulators. The planning is carried out on the base of kinematic configuration. To make repulsive potentials, sources are distributed on the boundaries of obstacles. To escape from local minimum of the main potential and to attack other difficulties of the planning, various potentials are defined simultaneously, Inverse Kinematics Problems of the redundant manipulators are solved by unconstrained optimization method. Computer simulation result of the path planning is presented.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권3호
• /
• pp.203-209
• /
• 2010

This paper presents a hierarchical fuzzy motion planner for humanoid robots in 3D uneven environments. First, we define both motion primitives and locomotion primitives of humanoid robots. A high-level planner finds a global path from a global navigation map that is generated based on a combination of 2.5 dimensional maps of the workspace. We use a passage map, an obstacle map and a gradient map of obstacles to distinguish obstacles. A mid-level planner creates subgoals that help the robot efficiently cope with various obstacles using only a small set of locomotion primitives that are useful for stable navigation of the robot. We use a local obstacle map to find the subgoals along the global path. A low-level planner searches for an optimal sequence of locomotion primitives between subgoals by using fuzzy motion 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.