• 제어로봇시스템학회논문지
• /
• 제8권4호
• /
• pp.338-344
• /
• 2002

In this paper, neural network force tracking control is proposed. The conventional impedance function is reformulated to have direct farce tracking capability. Neural network is used to compensate for all the uncertainties such as unknown robot dynamics, unknown environment stiffness, and unknown environment position. On line training signal of farce error for neural network is formulated. A large x-y table is built as a test-bed and neural network loaming algorithm is implemented on a DSP board mounted in a PC. Experimental studies of farce tracking on unknown environment for x-y table robot are presented to confirm the performance of the proposed technique.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.907-912
• /
• 1990

An approach to robot force control, which allows force manipulations to be realized without overshot and overdamping while in the presence of unknown environment, is given in this paper. The main idea is to use dynamic compensation for known robot parts and fuzzy compensation for unknown environment so as to improve system performance. The fuzzy compensation is implemented by using rule based fuzzy approach to identify unknown environment. The establishment of proposed control system consists of following two stages. First, similar to the resolved acceleration control method, dynamic compensation and PID control based on known robot dynamics, kinematics and estimated environment compliance is introduced. To avoid overshoot the whole control system is constructed overdamped. In the second stage, the unknown environment stiffness is estimated by using fuzzy reasoning, where the fuzzy estimation rules are obtained priori as the expression of the relationship between environment stiffness and system response. Based on simulation result, comparisons between cases with or without fuzzy identifications are given, which illustrate the improvement achieved.

• 한국지능시스템학회논문지
• /
• 제5권3호
• /
• pp.36-51
• /
• 1995

An approach to robot hybrid position/force control, which allows force manipulations to be realized without overshoot and overdamping while in the presence of unknown environment, is given in this paper. The manin idea is to used dynamic compensation for known robot parts and fuzzy compensation for unknown environment so as to improve system performance. The fuzzy compensation is implemented by using rule based fuzzy approach to identify the unknown environment. The establishment of proposed control system consists of following two stages. First, similar to the resovled acceleration control method, dynamic compensation and PD control based on known robot dynamics, kinematics and estimated environment stiffness is introduced. To avoid overshoot the whole control system is constructed with overdamping. In the second stage, the unknown environment stiffness is identified by using fuzzy reasoning, where the fuzzy compensation rules are obtained priori as the expression of the relationship betweenenvironment stiffness and system. Based on the simulation result, comparison between cases with or without fuzzy identifications are given, which illustrate the improvement achieced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4909-4926
• /
• 2020

Cyberattacks penetrate the server and perform various malicious acts such as stealing confidential information, destroying systems, and exposing personal information. To achieve this, attackers perform various malicious actions by infecting endpoints and accessing the internal network. However, the current countermeasures are only anti-viruses that operate in a signature or pattern manner, allowing initial unknown attacks. Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking. If you fail to respond to the initial attack, it is difficult to respond additionally because malicious behavior like Advanced Persistent Threat (APT) attack does not occur immediately, but occurs over a long period of time. In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus. The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning. The experiment trained a dataset collected over a month in a real-world commercial endpoint environment, and tested the data collected over the next month. As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through VirusTotal (VT). In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.560-563
• /
• 1997

The conventional impedance control has been known to have the following problems: it has lack of specifying force directly and unknown environment stiffness has to be known priori in order to specify the reference trajectory. In this paper, new impedance force control that can control a desired force directly under unknown stiffness is proposed. A new nonlinear impedance function is developed based on estimation of unknown stiffness from force and position measurements. The nonlinear characteristics of the proposed impedance function are analyzed based on unknown environment position. Simulation studies with robot manipulator are carried out to test analytical results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.8-11
• /
• 1996

In impedance control for contact force tracking it is well known that the reference trajectory of the robot is calculated from known environment stiffness. The accuracy of estimating the environment stiffness determines the performance of the resulting force tracking. Here we present a simple technique, called the trajectory modification technique(TMT), of determining the reference trajectory under the condition that the environment stiffness is unknown. Computer simulation studies have shown that force tracking using the proposed technique is excellent for unknown environment with time varying stiffness.

• 한국지능시스템학회논문지
• /
• 제7권5호
• /
• pp.67-76
• /
• 1997

In this paper, a theoretical study is presented for the force control of a miniature robotic manipulator which is driven by a pair of piezo-electric bimorph cells. In the theoretical analysis, one finger is modeled as a flexible cantilevers with a force sensor at the tip and the finger is a solid beam. The robotic finger is used to hold the objects with different stiffness such as an iron block and a living insect and a moving objcet. So it is very important to develop an adequate controller for the holding operation of the finger. The main problems in force controlling are overdamping, overshoot and unknown environment(such as the stiffness of object and unknown plant parameters). So, the main target is propose the new fuzzy compensation for unknown environment and incease the system performance. The fuzzy compensation is implemented by using PI-type fuzzy approach to identified unknown environment. And the result of proposed controller was compared with the conventaional PID and optimal controller.

• 한국물환경학회지
• /
• 제29권4호
• /
• pp.568-573
• /
• 2013

In this study, we conducted whole effluent toxicity (WET) proficiency testing based on the results which $EC_{50}$ value of 3 types (A, B, C) unknown samples calculated from 32 water quality measurement agencies in Korea. WET proficiency testing was expected to their improve of analysis skill and ensure reliability of analysis results. Ultimately, it is intended to promote the reliable enforcement of WET. WET proficiency testing was evaluated using the z-score, robust z-score and the results showed that 30 participating agencies were "compliance". In addition, $EC_{50}$ values of "unknown sample A" were the normal distribution. Therefore, "unknown sample A" was considered as the most suitable standard toxicity substance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.20-25
• /
• 1998

This paper proposes a new compliant contact control strategy for the robot manipulators accidentally interacting with an unknown environment. The main features of the proposed method are summarized as follows: First, each entry in the diagonal stiffness matrix corresponding to the task coordinate in Cartesian space is adaptively adjusted during con-tact along the corresponding axis based on the contact force with its environment. Second, it can be used for both unconstrained and constrained motions without any switching mechanism which often causes undesirable instability and/or vibrational motion of the end effector. Third, the adjusted stiffness gains are automatically recovered to initially specified stiffness gains when the task is changed from constrained motion to unconstrained motion. The simulation results show the effectiveness of the proposed method by employing a two-link direct drive manipulator interacting with an unknown environment.

• 전기학회논문지
• /
• 제67권2호
• /
• pp.285-292
• /
• 2018

In this paper, we propose a distributed search of a cluster robot using tree structure in an unknown environment. In the proposed method, the cluster robot divides the unknown environment into 4 regions by using the LRF (Laser Range Finder) sensor information and divides the maximum detection distance into 4 regions, and detects feature points of the obstacle. Also, we define the detected feature points as Voronoi Generators of the Voronoi Diagram and apply the Voronoi diagram. The Voronoi Space, the Voronoi Partition, and the Voronoi Vertex, components of Voronoi, are created. The generated Voronoi partition is the path of the robot. Voronoi vertices are defined as each node and consist of the proposed tree structure. The root of the tree is the starting point, and the node with the least significant bit and no children is the target point. Finally, we demonstrate the superiority of the proposed method through several simulations.