• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.411-414
• /
• 2003

Particle swarm optimization (PSO) is employed to train fuzzy-neural networks (FNN), which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. The system has been successfully employed in a real life situation for navigation of a mobile robot.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.1881_1882
• /
• 2009

Simple quadratic potential functions for unicycle robot path planning are presented, where proposed algorithm for path planning has the different environment for each robot based on LOS(Line Of Sight) between a target and an obstacle, unlike a conventional path planning. In doing so, the proposed algorithm assumes that each swarm robot equips its own vision instead of a ceiling camera. In particular, this paper presents that each robot follows its different local leader. As a result proposed algorithm reduces local minimum problems by the help of each local leader.

• ETRI Journal
• /
• 제40권4호
• /
• pp.446-457
• /
• 2018

Robot navigation allows robot mobility. Therefore, mobility is an area of robotics that has been actively investigated since robots were first developed. In recent years, interest in personal service robots for homes and public facilities has increased. As a result, robot navigation within the home environment, which is an indoor environment, is being actively investigated. However, the problem with conventional navigation algorithms is that they require a large computation time for their building mapping and path planning processes. This problem makes it difficult to cope with an environment that changes in real-time. Therefore, we propose a humanoid robot navigation algorithm consisting of an image processing and optimization algorithm. This algorithm realizes navigation with less computation time than conventional navigation algorithms using map building and path planning processes, and can cope with an environment that changes in real-time.

• 한국정밀공학회지
• /
• 제32권10호
• /
• pp.857-863
• /
• 2015

The need for human body posture robots has led researchers to develop dexterous design of exoskeleton robots. Quantitative techniques to assess human motor function and generate commands for robots were required to be developed. In this paper, we present a passivity based adaptive control algorithm for upper limb assist exoskeleton. The proposed algorithm can adapt to different subject parameters and provide efficient response against the biomechanical variations caused by subject variations. Furthermore, we have employed the Particle Swarm Optimization technique to tune the controller gains. Efficacy of the proposed algorithm method is experimentally demonstrated using a seven degree of freedom upper limb assist exoskeleton robot. The proposed algorithm was found to estimate the desired motion and assist accordingly. This algorithm in conjunction with an upper limb assist exoskeleton robot may be very useful for elderly people to perform daily tasks.

• ETRI Journal
• /
• 제40권4호
• /
• pp.471-482
• /
• 2018

This paper proposes the necessity of a walking period in footstep planning and details situations in which it should be considered. An optimization-based fast footstep planner that takes the walking period into consideration is also presented. This footstep planner comprises three stages. A binary search is first used to determine the walking period. The front stride, side stride, and walking direction are then determined using the modified rapidly-exploring random tree algorithm. Finally, particle swarm optimization (PSO) is performed to ensure feasibility without departing significantly from the results determined in the two stages. The parameters determined in the previous two stages are optimized together through the PSO. Fast footstep planning is essential for coping with dynamic obstacle environments; however, optimization techniques may require a large computation time. The two stages play an important role in limiting the search space in the PSO. This framework enables fast footstep planning without compromising on the benefits of a continuous optimization approach.

• Journal of Power Electronics
• /
• 제19권2호
• /
• pp.549-559
• /
• 2019

This paper proposes an adaptive sliding mode control (ASMC) strategy with an enhanced optimal reaching law (EORL) for the robust current tracking control of the boost converter based hybrid power source (HPS) in an electric vehicle (EV). A conventional ASMC strategy based on state observers and the hysteresis control method is used to realize the current tracking control for the boost converter based HPS. Then a novel enhanced exponential reaching law is proposed to improve the ASMC. Moreover, an enhanced exponential reaching law is optimized by particle swarm optimization. Finally, the adaptive control factor is redesigned based on the EORL. Simulations and experiments are established to validate the ASMC strategy with the EORL. Results show that the ASMC strategy with the EORL has an excellent current tracking control effect for the boost converter based HPS. When compared with the conventional ASMC strategy, the convergence time of the ASMC strategy with the EORL can be effectively improved. In EV applications, the ASMC strategy with the EORL can achieve robust current tracking control of the boost converter based HPS. It can guarantee the active and stable power distribution for boost converter based HPS.

• 한국산업정보학회논문지
• /
• 제24권5호
• /
• pp.115-120
• /
• 2019

본 논문에서는 이동 구간 입자 군집 최적화 (Receding horizon particle swarm optimization; RHPSO) 알고리즘 기반 다개체 로봇 편대 제어 알고리즘의 통계적 성능 분석 결과를 제시한다. 다개체 로봇의 편대 제어 문제는 로봇 간 충돌 회피를 고려할 경우, 구속 조건이 있는 비선형 최적화 문제로 정의될 수 있다. 일반적으로 구속 조건이 있는 비선형 최적화 문제는 최적해를 찾는데 많은 시간이 걸리는 문제점이 있다. 이동 구간 입자 군집 최적화 알고리즘은 로봇 편대 제어의 최적화 문제에 대한 준최적해를 빠르게 찾기 위해 제안된 알고리즘이다. 이동 구간 입자 군집 최적화 알고리즘은 알고리즘에 사용되는 후보해의 개수와 세대 수가 증가함에 따라 계산 복잡도가 증가한다. 따라서 최소의 후보해와 세대 수만으로 실시간 제어에 사용될 수 있는 준최적해를 찾는 것이 중요하다. 본 논문에서는 이동 구간 입자 군집 최적화 알고리즘의 후보해의 수와 세대 수에 따른 제어 오차를 비교하였다. 다양한 조건의 시뮬레이션 실험을 통해서 통계적으로 결과를 분석하고, 허용 가능한 편대 오차 범위 내에서 이동 구간 입자 군집 최적화 알고리즘의 최소 후보해의 수와 세대 수를 도출한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• pp.1894-1895
• /
• 2011

본 논문에서는 군집 로봇을 이용하여 주어진 공간을 효율적으로 탐색하기 위한 행동 제어 알고리즘을 제안한다. 제안한 방법은 군집 로봇의 운동방정식을 이용하여 각 로봇의 이동 상태를 파악하고 로봇에 장착된 센서 범위를 이용하여 군집 로봇간의 이동 규칙을 계획한다. 계획된 이동 규칙은 초기의 밀집된 위치에서 로봇이 자율적으로 이동하여 로봇간의 충돌을 회피하고 최적의 거리를 유지하면서 공간을 효율적으로 탐색하기 위한 행동 제어 방법을 제안한다. 마지막으로 시뮬레이션을 통하여 그 응용 가능성을 증명한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2015년도 제46회 하계학술대회
• /
• pp.1325-1326
• /
• 2015

본 논문에서는 마커 인식을 이용한 깊이 영상 기반 군집로봇 대형제어 방법을 제안한다. 제안한 방법은 먼저, follower 로봇들의 입력 영상에서 마커 인식 알고리즘을 이용하여 마커를 인식 한 뒤 인식된 마커를 분석하여 등록된 ID를 찾는다. 검출된 마커의 ID가 leader로봇의 ID일 경우 해당 마커의 위치와 기울기 값을 깊이 영상 센서로부터들어오는 깊이 정보를 통해 계산 한 뒤 마커의 위치와 기울기를 이용하여 대형제어를 한다. 마지막으로 제안한 알고리즘을 실제 로봇을 이용한 대형 제어실험을 통해 응용 가능성을 증명한다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1433-1436
• /
• 2008

Flagellate bacteria such as Escherichia coli or Serratia marcescens possess a remarkable motility system based on a reversible rotary motor. We have employed S. marcescens as microactuators in low Reynolds number fluidic environments to move a larger engineering element around. Microstructures fabricated using conventional microfabrication techniques are blotted on the swarm plate, which leaves a bacterial monolayer on the surface of the microstructure. We have investigated microstructures powered by bacteria to determine how cell orientation on the microstructure surface relates to the swarming patterns as well as how the orientation is affected by the blotting process. This study will help to refine directional control of bacterial transporters by exploiting bacterial sensory mechanisms.