• International Journal of Control, Automation, and Systems
• /
• 제2권1호
• /
• pp.107-117
• /
• 2004

A new algorithm for planning a collision-free path based on an algebraic curve as well as the concept of path space is developed. Robot path planning has so far been concerned with generating a single collision-free path connecting two specified points in a given robot workspace with appropriate constraints. In this paper, a novel concept of path space (PS) is introduced. A PS is a set of points that represent a connection between two points in Euclidean metric space. A geometry mapping (GM) for the systematic construction of path space is also developed. A GM based on the 2$^{nd}$ order base curve, specifically Bezier curve of order two is investigated for the construction of PS and for collision-free path planning. The Bezier curve of order two consists of three vertices that are the start, S, the goal, G, and the middle vertex. The middle vertex is used to control the shape of the curve, and the origin of the local coordinate (p, $\theta$) is set at the centre of S and G. The extreme locus of the base curve should cover the entire area of actual workspace (AWS). The area defined by the extreme locus of the path is defined as quadratic workspace (QWS). The interference of the path with obstacles creates images in the PS. The clear areas of the PS that are not mapped by obstacle images identify collision-free paths. Hence, the PS approach converts path planning in Euclidean space into a point selection problem in path space. This also makes it possible to impose additional constraints such as determining the shortest path or the safest path in the search of the collision-free path. The QWS GM algorithm is implemented on various computer systems. Simulations are carried out to measure performance of the algorithm and show the execution time in the range of 0.0008 ~ 0.0014 sec.

• 로봇학회논문지
• /
• 제15권2호
• /
• pp.100-106
• /
• 2020

In the agricultural field, interests in research using robots for fruit harvesting are continuously increasing. Dual arm manipulators are promising because of its abilities like task-distribution and role-sharing. To operate it efficiently, the task sequence must be planned adequately. In our previous study, a collision-free path planning method based on a genetic algorithm is proposed for dual arm manipulators doing tasks cooperatively. However, in order to simplify the complicated collision-check problem, the movement between tasks of two robots should be synchronized, and thus there is a problem that the robots must wait and resume their movement. In this paper, we propose a heuristic algorithm that can reduce the total time of the optimal solution obtained by using the previously proposed genetic algorithm. It iteratively desynchronizes the task sequence of two robots and reduces the waiting time. For evaluation, the proposed algorithm is applied to the same work as the previous study. As a result, we can obtain a faster solution having 22.57 s than that of the previous study having 24.081 s. It will be further studied to apply the proposed algorithm to the fruit harvesting.

• 제어로봇시스템학회논문지
• /
• 제6권11호
• /
• pp.1003-1012
• /
• 2000

When a robot hand grasp an object, the number of ways to grasp it stably are infinite and thus an optimal grasp planning is needed to find the optimal grasp points for satisfying the objective of the given task. In this paper, we first define some grasp indices to evaluate the quality of each feasible grasp and then a weighted composite grasp index by combining all of the grasp indices is also defined. Next, we propose a method to find the optimal grasp points of the given object by comparing the defined weighted composite grasp index for each feasible grasp points. By simulation results, we show the effectiveness of the proposed optimal grasp planning method and also discuss the trend of each grasp index as the grasp polygon.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.68-75
• /
• 2003

This paper presents an effective trajectory planning algorithm for industrial robot manipulators. Given the end-effector trajectory in Cartesian space, together with the relevant constraints and task specifications, the proposed method is capable of planning the optimum end-effector trajectory. The proposed trajectory planning algorithm considers the joint acceleration limit, end-effector velocity limits, and trajectory allowance. A feedforward compensator is also incorporated in the proposed algorithm to counteract the delay in joint dynamics. The algorithm is carefully designed so that it can be directly adopted with the existing industrial manipulators. The proposed algorithm can be easily programmed for various tasks given the specifications and constraints. A three-dimensional test trajectory was planned with the proposed algorithm and tested with the Performer MK3s industrial manipulator. The results verified effective manipulator performance within the constraints.

• Journal of Mechanical Science and Technology
• /
• 제18권1호
• /
• pp.92-105
• /
• 2004

A new algorithm for planning a collision-free path based on algebraic curve is developed and the concept of collision-free Path Space (PS) is introduced. This paper presents a Geometry Mapping (GM) based on two straight curves in which the intermediate connection point is organized in elliptic locus ($\delta$, $\theta$). The GM produces two-dimensional PS that is used to create the shortest collision-free path. The elliptic locus of intermediate connection point has a special property in that the total distance between the focus points through a point on ellipse is the same regardless of the location of the intermediate connection point on the ellipse. Since the radial distance, a, represents the total length of the path, the collision-free path can be found as the GM proceeds from $\delta$=0 (the direct path) to $\delta$=$\delta$$\_$max/(the longest path) resulting in the minimum time search. The GM of elliptic workspace (EWS) requires calculation of interference in circumferential direction only. The procedure for GM includes categorization of obstacles to .educe necessary calculation. A GM based on rectangular workspace (RWS) using Cartesian coordinate is also considered to show yet another possible GM. The transformations of PS among Circular Workspace Geometry Mapping (CWS GM) , Elliptic Workspace Geometry Mapping (EWS GM) , and Rectangular Workspace Geometry Mapping (RWS GM), are also considered. The simulations for the EWS GM on various computer systems are carried out to measure performance of algorithm and the results are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.503-506
• /
• 1996

An integrated Robot control system for SCARA robot is developed. The system consists of an off-line programming(OLP), software and a robot controller using four digital signal processor(TMS32OC50). The OLP has functions of teaching task, dynamic simulator, three dimensional animation, and trajectory planning. To develop robust dynamic control algorithm, a new sliding mode control algorithm for the robot is proposed. The trajectory tracking performance of these algorithm is evaluated by implementing to SCARA robot(SM5 type) using DSP controller which has conventional PI-FF control algorithm. To make SCARA robot operate according to off-line teaching, an interface between OLP and robot controller in the integrated system is designed. To demonstrate performance of the integrated system, the proposed control algorithm is applied to the system.

• 한국전자통신학회논문지
• /
• 제18권2호
• /
• pp.231-240
• /
• 2023

심층 강화 학습(Deep Reinforcement Learning)을 사용한 경로 계획에서 장애물을 자동으로 회피하기 위해 로봇을 학습시키는 일은 쉬운 일이 아니다. 많은 연구자가 DRL을 사용하여 주어진 환경에서 로봇 학습을 통해 장애물 회피하여 경로 계획을 수립하려는 가능성을 시도하였다. 그러나 다양한 환경에서 로봇과 장착된 센서의 오는 다양한 요인 때문에 주어진 시나리오에서 로봇이 모든 장애물을 완전히 회피하여 이동하는 것을 실현하는 일은 흔치 않다. 이러한 문제 해결의 가능성과 장애물을 회피 경로 계획 실험을 위해 테스트베드를 만들었고 로봇에 카메라를 장착하였다. 이 로봇의 목표는 가능한 한 빨리 벽과 장애물을 피해 시작점에서 끝점까지 도달하는 것이다. 본 논문에서는 벽과 장애물을 회피하기 위한 DRL의 가능성을 검증하기 위해 이중 심층 Q 네트워크(DDQN)를 제안하였다. 실험에 사용된 로봇은 Jetbot이며 자동화된 경로 계획에서 장애물 회피가 필요한 일부 로봇 작업 시나리오에 적용할 수 있을 것이다.

• 제어로봇시스템학회논문지
• /
• 제10권4호
• /
• pp.350-356
• /
• 2004

This paper presents a farce manipulability analysis of multi-legged walking robots, which calculates force or acceleration workspace attainable from joint torque limits of each leg. Based on the observation that the kinematic structure of the multi-legged walking robots is basically the same as that of multiple cooperating robots, we derive the proposed method of analyzing the force manipulability of walking robot. The force acting on the object in multiple cooperating robot systems is taken as reaction force from ground to each robot foot in multi-legged walking robots, which is converted to the force of the body of walking robot by the nature of the reaction force. Note that each joint torque in multiple cooperating robot systems is transformed to the workspace of force or acceleration of the object manipulated by the robots in task space through the Jacobian matrix and grasp matrix. Assuming the torque limits are given in infinite norm-sense, the resultant dynamic manipulability is derived as a polytope. The validity of proposed method is verified by several examples, and the proposed method is believed to be useful for the optimal posture planning and gait planning of walking robots.

• 로봇학회논문지
• /
• 제16권1호
• /
• pp.56-63
• /
• 2021

As the use of robots in service area increases, research has been conducted to replace human tasks in daily life with robots. Among them, this study focuses on the tidy-up task on a desk using a robot arm. The order in which tidy-up motions are carried out has a great impact on the success rate of the task. Therefore, in this study, a neural network-based method for determining the priority of the tidy-up motions from the input image is proposed. Reinforcement learning, which shows good performance in the sequential decision-making process, is used to train such a task planner. The training process is conducted in a virtual tidy-up environment that is configured the same as the actual tidy-up environment. To transfer the learning results in the virtual environment to the actual environment, the input image is preprocessed into a segmented image. In addition, the use of a neural network that excludes unnecessary tidy-up motions from the priority during the tidy-up operation increases the success rate of the task planner. Experiments were conducted in the real world to verify the proposed task planning method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권2호
• /
• pp.138-142
• /
• 2007

This paper presents an algorithm which extends the rapidly-exploring random tree (RRT) framework to deal with change of the task environments. This algorithm called the Retrieval RRT Strategy (RRS) combines a support vector machine (SVM) and RRT and plans the robot motion in the presence of the change of the surrounding environment. This algorithm consists of two levels. At the first level, the SVM is built and selects a proper path from the bank of RRTs for a given environment. At the second level, a real path is planned by the RRT planners for the: given environment. The suggested method is applied to the control of $KUKA^{TM}$, a commercial 6 DOF robot manipulator, and its feasibility and efficiency are demonstrated via the cosimulatation of $MatLab^{TM}\;and\;RecurDyn^{TM}$.