• 한국산업융합학회 논문집
• /
• 제19권1호
• /
• pp.1-9
• /
• 2016

In this paper, we propose a new learning control scheme for various walk motion control of biped robot with same learning-base by neural network. We show that learning control algorithm based on the neural network is significantly more attractive intelligent controller design than previous traditional forms of control systems. A multi layer back propagation neural network identification is simulated to obtain a dynamic model of biped robot. Once the neural network has learned, the other neural network control is designed for various trajectory tracking control with same learning-base. The biped robots have been received increased attention due to several properties such as its human like mobility and the high-order dynamic equation. These properties enable the biped robots to perform the dangerous works instead of human beings. Thus, the stable walking control of the biped robots is a fundamentally hot issue and has been studied by many researchers. However, legged locomotion, it is difficult to control the biped robots. Besides, unlike the robot manipulator, the biped robot has an uncontrollable degree of freedom playing a dominant role for the stability of their locomotion in the biped robot dynamics. From the simulation and experiments the reliability of iterative learning control was illustrated.

• 대한안전경영과학회지
• /
• 제23권4호
• /
• pp.93-104
• /
• 2021

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

• 로봇학회논문지
• /
• 제2권3호
• /
• pp.242-248
• /
• 2007

Robot system development consists of several sub-tasks such as layout design, motion planing, and sensor programming etc. In general, on-line programming and debugging for such tasks demands burdensome time and labor costs, which motivates an off-line graphic simulation system. MSRS(Microsoft Robotics Studio) released in recent years is an appropriate tool for the graphic simulation system since it supports CCR(Concurrency and Coordination Runtime), DSS(Decentralized System Services), and dynamics simulation based on PhysX and graphic animation as well. In this paper, we developed an MSRS based network simulation system for quadruped walking robots, which controls virtual 3D graphic robots existing in remote side through internet.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 추계학술대회
• /
• pp.579-582
• /
• 2010

본 연구에서는 복도 내에서 주행하는 로봇에 탑재된 카메라로 입력된 영상은 3차원 특징정보에 의해 장애물과 복도의 코너, 문으로 검출되어진다. 바닥의 문자정보 인식을 통한 이동로봇의 주행경로를 구하는데 있어 이들 세 가지는 최적의 경로 생성과 장애물 회피를 위한 매우 중요한 정보로 사용될 수 있다. 따라서, 본 논문에서는 입력영상을 전처리 후에 제안된 알고리즘을 기반으로 한 이동로봇의 주행방향결정과, 입력 영상에서 신경망을 통하여 바닥의 문자정보를 인식 및 특징정보 검출을 통한 이동로봇의 주행을 위한 선행 실험결과를 제시하였다.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.134-141
• /
• 2003

A major research issue associated with service robots is the creation of an environment recognition system for mobile robot navigation that is robust and efficient on various environment situations. In recent years, intelligent autonomous mobile robots have received much attention as the types of service robots for serving people and industrial robots for replacing human. To help people, robots must be able to sense and recognize three dimensional space where they live or work. In this paper, we propose a three dimensional environmental modeling method based on an edge enhancement technique using a planar fitting method and a neural network technique called "Growing Neural Gas Network." Input data pre-processing provides probabilistic density to the input data of the neural network, and the neural network generates a graphical structure that reflects the topology of the input space. Using these methods, robot's surroundings are autonomously clustered into isolated objects and modeled as polygon patches with the user-selected resolution. Through a series of simulations and experiments, the proposed method is tested to recognize the environments surrounding the robot. From the experimental results, the usefulness and robustness of the proposed method are investigated and discussed in detail.in detail.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권4호
• /
• pp.160-166
• /
• 2002

Since conventional mobile robot control with one module has limitation to solve complex problems, there have been a variety of works on combining multiple modules for solving them. Recently, many researchers attempt to develop mobile robot controllers using artificial life techniques. In this paper, we develop a mobile robot controller using cellular automata based neural networks, where complex tasks are divided to simple sub-tasks and optimal neural structure of each sub-task is explored by genetic algorithm. Neural network modules are combined dynamically using the action selection mechanism, where basic behavior modules compete each other by inhibition and cooperation. Khepera mobile robot simulator is used to verify the proposed model. Experimental results show that complex behaviors emerge from the combination of low-level behavior modules.

• 한국산학기술학회논문지
• /
• 제15권7호
• /
• pp.4482-4488
• /
• 2014

본 논문은 로봇 전역경로계획을 위하여 위협맵을 생성하는 기법을 제안한다. 로봇의 무장 정보와 적 또는 장애물의 위험정보를 비교하고 신경망 이론 기반의 학습을 수행하여 절대적인 수치로 정량화한 위협맵을 생성한다. 또한 로봇이 제안된 기법으로 생성된 위협맵을 기반으로 경로를 이동한 결과와 기존의 결과를 비교하여 로봇의 위협정도를 파악하여 성능을 검증한다.

• 제어로봇시스템학회논문지
• /
• 제10권12호
• /
• pp.1249-1255
• /
• 2004

A new parameter adaptation scheme for RBF Neural Network (NN) has been developed in this paper. Even though the RBF Neural Network (NN) based controllers are robust against both un-modeled dynamics and external disturbances, the performance is not satisfactory for a fast and precise mobile robot. To improve the tracking performance as well as robustness, all the parameters of RBF NN are updated in real time. The stability of this control law is rigorously proved by following the Lyapunov stability theory and shown by the experimental simulations. The fact that all of the weighting factors, width and center of RBF NN have been updated implies that this scheme utilizes all the possibilities in RBF NN to make the controller robust and precise while the mobile robot is following un-known trajectories. The performance of this new algorithm has been compared to the conventional RBF NN controller where some of the parameters are adjusted for robustness.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.183-187
• /
• 2002

This paper proposes a remote control system that combines computer network and an autonomous mobile robot. We control remotely an autonomous mobile robot with vision via the internet to guide it under unknown environments in the real time. The main feature of this system is that local operators need a World Wide Web browser and a computer connected to the internet communication network and so they can command the robot in a remote location through our Home Page. This system offers an image compression method using motion H.263 concept which reduces large time delay that occurs in network during image transmission.

• ETRI Journal
• /
• 제45권2호
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.