• 제목/요약/키워드: trajectory optimization

검색결과 241건 처리시간 0.031초

저가 Redundant Manipulator의 최적 경로 생성을 위한 Deep Deterministic Policy Gradient(DDPG) 학습 (Learning Optimal Trajectory Generation for Low-Cost Redundant Manipulator using Deep Deterministic Policy Gradient(DDPG))

  • 이승현;진성호;황성현;이인호
    • 로봇학회논문지
    • /
    • 제17권1호
    • /
    • pp.58-67
    • /
    • 2022
  • In this paper, we propose an approach resolving inaccuracy of the low-cost redundant manipulator workspace with low encoder and low stiffness. When the manipulators are manufactured with low-cost encoders and low-cost links, the robots can run into workspace inaccuracy issues. Furthermore, trajectory generation based on conventional forward/inverse kinematics without taking into account inaccuracy issues will introduce the risk of end-effector fluctuations. Hence, we propose an optimization for the trajectory generation method based on the DDPG (Deep Deterministic Policy Gradient) algorithm for the low-cost redundant manipulators reaching the target position in Euclidean space. We designed the DDPG algorithm minimizing the distance along with the jacobian condition number. The training environment is selected with an error rate of randomly generated joint spaces in a simulator that implemented real-world physics, the test environment is a real robotic experiment and demonstrated our approach.

유전자 알고리즘을 이용한 이족보행 로봇의 계단 보행 (Trajectory Optimization for Biped Robots Walking Up-and-Down Stairs based on Genetic Algorithms)

  • 전권수;권오흥;박종현
    • 한국정밀공학회지
    • /
    • 제23권4호
    • /
    • pp.75-82
    • /
    • 2006
  • In this paper, we propose an optimal trajectory for biped robots to move up-and-down stairs using a genetic algorithm and a computed-torque control for biped robots to be dynamically stable. First, a Real-Coded Genetic Algorithm (RCGA) which of operators are composed of reproduction, crossover and mutation is used to minimize the total energy. Constraints are divided into equalities and inequalities: Equality constraints consist of a position condition at the start and end of a step period and repeatability conditions related to each joint angle and angular velocity. Inequality constraints include collision avoidance conditions of a swing leg at the face and edge of a stair, knee joint conditions with respect to the avoidance of the kinematic singularity, and the zero moment point condition with respect to the stability into the going direction. In order to approximate a gait, each joint angle trajectory is defined as a 4-th order polynomial of which coefficients are chromosomes. The effectiveness of the proposed optimal trajectory is shown in computer simulations with a 6-dof biped robot that consists of seven links in the sagittal plane. The trajectory is more efficient than that generated by the modified GCIPM. And various trajectories generated by the proposed GA method are analyzed in a viewpoint of the consumption energy: walking on even ground, ascending stairs, and descending stairs.

Integration of the Engine Control into the Optimal Trajectory Determination for a Spaceplane

  • Matsunaga, Kensuke;Tanatsugu, Nobuhiro;Sato, Tetsuya;Kobayashi, Hiroaki;Okabe, Yoriji
    • 한국추진공학회:학술대회논문집
    • /
    • 한국추진공학회 2004년도 제22회 춘계학술대회논문집
    • /
    • pp.742-748
    • /
    • 2004
  • In this paper are presented TSTO system analysis including some controlled variables on the engine operation such as a fuel flow rate and a pressure ratio of compressor, as well as variables on the trajectory. TSTO studied here is accelerated up to Mach 6 by a fly-back booster powered by air breathing engines. Three different types of engine cycle were treated for propulsion system of the booster, such as a turbo ramjet, a precooled turbojet and an EXpander cycle Air Turbo Ramjet (ATREX). The history of the controlled variables on the engine operation was optimized by Sequential Quadratic Programming (SQP) to accomplish the minimum fuel consumption. The trajectory was also optimized simultaneously. The results showed that the turbo ramjet gave the best fuel consumption. The optimal trajectory was almost the same except in the transonic range and just before reaching to Mach 6. The history of the pressure ratio of compressor considerably depended on the engine type. It is concluded that simultaneous optimization for engine control and trajectory is effective especially for a high-speed airplane propelled by turbojets like the TSTO booster.

  • PDF

불법드론 탐지를 위한 PSO 기반 군집드론 최적화 정찰궤적계획 (Optimal Surveillance Trajectory Planning for Illegal UAV Detection for Group UAV using Particle Swarm Optimization)

  • 임원호;정형찬;호등;아람기르;장경희
    • 한국항행학회논문지
    • /
    • 제24권5호
    • /
    • pp.382-392
    • /
    • 2020
  • 드론기술은 민수용과 군사용 양 분야 에서 전도유망한 기술이나, 규정과 관련법의 미성숙으로 불법드론이 오남용 되고, 사회안전에 심각한 위협이 되고 있다. 본고에서는 PSO (particle swarm optimization)에 기반을 둔 군집드론 궤적계획기를 개발하여, 군집정찰드론들에게 최적화된 3차원 궤적탐지기술을 제공한다. 나아가서, 에너지소비도, 비행위험도 및 SAP (surveillance area priority)와 부합하는 군집 목적물 최적화 함수를 제시하고 평가한다. 군집 비행 시뮬레이션 결과는, 제안한 궤적계획기로 생성한 궤적은 에너지 소비도 및 비행위험도를 최소화 하며 탐색한다는 것을 입증해준다.

Locationing of telemanipulator based on task capability

  • Park, Young-Soo;Yoon, Jisup;Cho, Hyung-Suck
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
    • /
    • pp.392-395
    • /
    • 1995
  • This paper presents a time efficient method for determining a sequence of locations of a mobile manipulator that facilitates tracking of continuous path in cluttered environment. Given the task trajectory in the form of octree data structure, the algorithm performs characterization of task space and subsequent multistage optimization process to determine task feasible locations of the robot. Firstly, the collision free portion of the trajectory is determined and classified according to uniqueness domains of the inverse kinematics solutions. Then by implementing the extent of task feasible subspace into an optimization criteria, a multistage optimization problem is formulated to determines the task feasible locations of the mobile manipulator. The effectiveness of the proposed method is shown through a simulation study performed for a 3-d.o.f. manipulator with generic kinematic structure.

  • PDF

유전 알고리즘을 이용한 선박의 최적 항로 결정에 관한 연구 (A Study on the Optimal Trajectory Planning for a Ship Using Genetic algorithm)

  • 이병결;김종화;김대영;김태훈
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2000년도 제15차 학술회의논문집
    • /
    • pp.255-255
    • /
    • 2000
  • Technical advance of electrical chart and cruising equipment make it possible to sail without a man. It is important to decide the cruising route in view of effectiveness and stability of a ship. So we need to study on the optimal trajectory planning. Genetic algorithm is a strong optimization algorithm with adaptational random search. It is a good choice to apply genetic algorithm to the trajectory planning of a ship. We modify a genetic algorithm to solve this problem. The effectiveness of the revised genetic algorithm is assured through computer simulations.

  • PDF

타워워커: 보행 경로 최적화와 극대화된 다리 길이를 통한 속도 향상 (TowerWalker: Speed improvement through trajectory optimization and maximally elongated leg)

  • 남지원
    • EDISON SW 활용 경진대회 논문집
    • /
    • 제5회(2016년)
    • /
    • pp.389-396
    • /
    • 2016
  • In order to maximize the speed of Theo Jansen Mechanism in an given design space and prototyping material, the trajectory path was maximized according to several literature reviews, and the lower leg was elongated maximally in order to minimize the shift between support phase and transfer phase.

  • PDF

다수 위협에 대한 무인항공기 최적 경로 계획 (Optimal Path Planning for UAVs under Multiple Ground Threats)

  • 김부성;방효충;유창경;정을호
    • 한국항공우주학회지
    • /
    • 제34권1호
    • /
    • pp.74-80
    • /
    • 2006
  • 본 논문은 레이더와 같은 지상의 다수위협이 존재하는 상황에서 무인항공기의 비행경로 최적화에 관한 것이다. 레이더에 의한 피탐성, 즉 비행체에 의해 반사되는 레이더 신호강도를 최소화하면서 목적지까지의 비행시간을 최소화하는 관점에서 성능지수를 제안하였다. 1차의 시간지연 시스템으로 가정된 비행체의 경사각을 제어입력으로 고려하였으며, Sequential Quadratic Programming기법에 기반한 입력 파라미터 최적화 기법을 사용하여 궤적최적화를 수행하였다. 제안된 무인 항공기 경로계획 기법은 Voronoi 선도기법과 비교하였을 때, 생존성을 증대시키면서도 항공기의 역학적 특성을 고려한 비행경로를 제공한다.

두 로보트의 협력제어를 위한 최적조작가능 경로의 결정 방법 (An Optimal Admissible Trajectory Determination for a Cooperating Two-Robot System)

  • Lim, Joon-Hong
    • 대한전자공학회논문지
    • /
    • 제26권9호
    • /
    • pp.1332-1339
    • /
    • 1989
  • The problem of finding an admissible object trajectory for a cooperating two-robot system is investigated. The method is based on reformulating the problem as a nonlinear optimization problem with equality constraints in terms of the joint variables. The optimization problem is then solved numerically on a computer. The solution automatically gives the corresponding joint variable trajectories as well, thus eliminating the need for solving the inverse kinematic problem. The performance indices are chose in joint and cartesian spaces and computer simulations are performed.

  • PDF

유전알고리즘을 이용한 궤적 최적화에 관한 연구 (Trajectory Optimization Using Genetic Algorithm)

  • 최석민;손진우;원태현;배종일;이만형
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1998년도 하계학술대회 논문집 B
    • /
    • pp.703-705
    • /
    • 1998
  • In this paper, we have suggested the method of genetic algorithm to solve the trajectory optimization. The given nonlinear method is so complex and modeling is not easy. Also, we have suggested the nonlinear programming combined with genetic algorithm. The proposed algorithm gives simple and time-reducing method in solving nonlinear dynamic systems.

  • PDF