• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.256-256
• /
• 2000

In this parer, we present a real-time path planning algorithm which is integrated the artificial potential field(APF) and simulated annealing(SA) methods for mobile robot. The APF method in path planning has gained popularity since 1990's. It doesn't need the modeling of the complex configuration space of robot, and is easy to apply the path planning with simple computation. However, there is a major problem with APF method. It is the formation of local minima that can trap the robot before reaching its goal. So, to provide local minima recovery, we apply the SA method. The effectiveness of the proposed algorithm is verified through simulation.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제25권4호
• /
• pp.149-161
• /
• 2021

This study proposes a methodology for mission/path planning of an unmanned aerial vehicle (UAV) using an artificial potential field with the Markov Decision Process (MDP). The planning problem is formulated as an MDP. A low-resolution solution of the MDP is obtained and used to define an artificial potential field, which provides a continuous UAV mission plan. A numerical case study is conducted to demonstrate the validity of the proposed technique.

• 한국지능시스템학회논문지
• /
• 제22권4호
• /
• pp.476-480
• /
• 2012

본 논문에서는 선도 로봇을 추종하는 군집 로봇의 대형 제어를 인공 포텐셜 장을 사용하여 제안한다. 또한, 인공 포텐셜 장은 물리적으로 해석하기 쉬운 전기장을 모델링하여 구성하고, 장애물을 더욱 효과적으로 모델링하기 위해서, 장애물의 모양에 따라 전기장의식을 달리한다. 제안하는 방법은 선도 로봇의 경로를 인공 포텐셜 장을 통해 계획한 뒤, 선도 로봇을 추종 로봇이 뒤따라가는 형태로 구성된다. 마지막으로 시뮬레이션 예제를 통해 제안하는 기법의 타당성을 검증한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.339-346
• /
• 2005

Artificial potential field (APF) is a widely used method for local path planning of autonomous mobile robot. So far, many different types of APF have been implemented. Once the artificial potential functions are selected, how to choose appropriate parameters of the functions is also an important work. In this paper, a detailed analysis is given on how to choose proper parameters of artificial functions to eliminate free path local minima and avoid collision between robots and obstacles. Two kinds of potential functions: Gaussian type and Quadratic type of potential functions are used to solve the above local minima problem respectively. To avoid local minima occurred in realistic situations such as 1) a case that the potential of the goal is affected excessively by potential of the obstacle, 2) a case that the potential of the obstacle is affected excessively by potential of the goal, the design guidelines for selecting appropriate parameters of potential functions are proposed.

• 전기학회논문지
• /
• 제60권11호
• /
• pp.2147-2151
• /
• 2011

In this paper, we propose the formation control algorithm for swarm robots. The proposed algorithm uses the artificial potential field(APF) to plan the global path of swarm robots and to control the formation movement. The navigation function generates a global APF for a leader robot to reach a given destination and an avoidance function generates a local APF for follow robots to avoid obstacles. Finally, some simulations show the validity of the proposed method.

• Journal of Mechanical Science and Technology
• /
• 제17권12호
• /
• 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.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2023년도 춘계학술대회
• /
• pp.265-266
• /
• 2023

With the development of science and technology, various research on ship collision avoidance has also developed rapidly. The research and development of ship collision avoidance technology has also received high attention from many researchers. This paper proposes a new collision avoidance algorithm for ships based on the artificial force field collision avoidance method. Using the simulation platform, the simulation results show that ships can successfully avoid collision in open water under single ship and multi ship situations, and the research results are relatively ideal.

• 한국자동차공학회논문집
• /
• 제19권4호
• /
• pp.8-15
• /
• 2011

This paper proposes a real-time navigation algorithm which integrates the artificial potential field (APF) for an unmanned vehicle in the unknown environment. This approach uses repulsive potential function around the obstacles to force the vehicle away and an attractive potential function around the goal to attract the vehicle. In this research, laser range finder is used as range sensor. An obstacle detected by the sensor creates repulsive vector. Differential global positioning system (DGPS) and digital compass are used to measure the current vehicle position and orientation. The measured vehicle position is also used to create attractive vector. This paper proposes a new concept of potential field based navigation which controls unmanned vehicle's speed and steering. The magnitude of repulsive force based on the proposed algorithm is designed not to be over the magnitude of attractive force while the magnitude is increased linearly as being closer to obstacle. Consequently, the vehicle experiences a generalized force toward the negative gradient of the total potential. This force drives the vehicle downhill towards its goal configuration until the vehicle reaches minimum potential and it stops. The effectiveness of the proposed APF for unmanned vehicle is verified through simulation and experiment.

• 한국전자통신학회논문지
• /
• 제7권2호
• /
• pp.401-407
• /
• 2012

본 논문에서는 대표적인 이동 로봇의 장애물 회피 방법들의 성능을 분석한다. 이를 위해 장애물 회피 성능 지수로서 목표점까지 이동한 거리, 이동 시간, 장애물과의 거리, 로봇 동작의 평활도(smoothness)를 제시한다. 특히 로봇 동작의 평활도는 로봇 동작 시 조향 방향의 각가속도와 저크(jerk)를 사용하여 로봇의 실질적 이동 효율성을 측정하는 성능 지수이다. 주어진 성능 지수에 의하여 4가지의 주요한 장애물 회피 방법을 비교하였다. 주요한 장애물 회피 방법은 인공 전위계 방법, 탄성력(elastic force) 방법, 가상 거리(virtual distance)에 의한 인공전위계 방법, 그리고 가상 거리에 의한 탄성력 방법이다. 시뮬레이션을 통하여 각 방법의 성능을 비교 분석하여 각각의 장애물 회피 특성을 파악하였다.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.890-903
• /
• 2017

The problem of determining a smooth and collision-free path with maximum possible speed for a Mobile Robot (MR) which is chasing a moving target in a dynamic environment is addressed in this paper. Genetic Network Programming with Reinforcement Learning (GNP-RL) has several important features over other evolutionary algorithms such as it combines offline and online learning on the one hand, and it combines diversified and intensified search on the other hand, but it was used in solving the problem of MR navigation in static environment only. This paper presents GNP-RL based on predicting collision positions as a first attempt to apply it for MR navigation in dynamic environment. The combination between features of the proposed collision prediction and that of GNP-RL provides safe navigation (effective obstacle avoidance) in dynamic environment, smooth movement, and reducing the obstacle avoidance latency time. Simulation in dynamic environment is used to evaluate the performance of collision prediction based GNP-RL compared with that of two state-of-the art navigation approaches, namely, Q-Learning (QL) and Artificial Potential Field (APF). The simulation results show that the proposed GNP-RL outperforms both QL and APF in terms of smooth movement and safer navigation. In addition, it outperforms APF in terms of preserving maximum possible speed during obstacle avoidance.