• 전자통신동향분석
• /
• 제39권1호
• /
• pp.95-105
• /
• 2024

In natural language processing, large language models such as GPT-4 have recently been in the spotlight. The performance of natural language processing has advanced dramatically driven by an increase in the number of model parameters related to the number of acceptable input tokens and model size. Research on multimodal models that can simultaneously process natural language and image data is being actively conducted. Moreover, natural-language and image-based reasoning capabilities of large language models is being explored in robot artificial intelligence technology. We discuss research and related patent trends in robot task planning and code generation for robot control using large language models.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권12호
• /
• pp.499-506
• /
• 2019

지능형 로봇은 사용자의 요구에 따라 상황에 맞는 작업을 선택하여 서비스를 수행할 수 있어야 하며, 다양한 상황에 대해서 현재 가장 적합한 작업이 무엇인지 비교하고 선택할 수 있어야 한다. 이를 위해 절차적 추론 시스템을 활용하는 기존의 지능형 로봇시스템은 작업 모델 내부에 우선도 함수를 정의하고 이를 활용하여 작업 간 우선도를 비교하는 방법으로 작업관리 기능을 제공하고 있었다. 하지만 이러한 기존의 방법은 다중 도메인 서비스를 수행하는 데에 있어, 우선도 결정 함수가 명시적이지 않아 일반적인 상황에 대한 우선순위를 결정할 수 없고, 유용성을 비교하기 위한 표준적인 기준이 존재하지 않아 각 서비스 간의 우선도를 비교하는 방법이 범용적이지 않으며, 이를 재사용하거나 확장할 수 없다는 한계점이 존재했다. 우리는 이를 개선하기 위해 작업관리를 위한 정책 모델과 이를 활용하여 작업의 우선도를 계산하는 방법인 정책 모델 주도 메타-플래닝을 제안한다. 정책 모델은 메타-플래닝 과정에서 작업의 유틸리티를 명시적으로 계산할 수 있는 기능을 제공하며, 기초 모델을 통해 다양한 서비스 간의 유용성을 비교할 수 있게 해준다. 또한, 모델의 구성을 온톨로지를 활용함으로써 확장성을 가지는 특징이 있다. 실험을 통해 동적 환경에서 정책 모델에 따라 로봇의 행동이 변화하는 것을 관찰할 수 있었고, 이를 통해 서비스가 필요에 따라 우선도의 비교를 통해 선택되는 것을 확인할 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제10권9호
• /
• pp.785-798
• /
• 2004

This paper introduces the development of a range sensor based integrated navigation system for a multi-functional indoor service robot, called PSR (Public Service Robot System). The proposed navigation system includes hardware integration for sensors and actuators, the development of crucial navigation algorithms like mapping, localization, and path planning, and planning scheme such as error/fault handling. Major advantages of the proposed system are as follows: 1) A range sensor based generalized navigation system. 2) No need for the modification of environments. 3) Intelligent navigation-related components. 4) Framework supporting the selection of multiple behaviors and error/fault handling schemes. Experimental results are presented in order to show the feasibility of the proposed navigation system. The result of this research has been successfully applied to our three service robots in a variety of task domains including a delivery, a patrol, a guide, and a floor cleaning task.

• 한국전자통신학회논문지
• /
• 제18권4호
• /
• pp.709-714
• /
• 2023

유연한 planning system은 로봇이 다양한 임무를 수행하기 위해서 중요한 요소이다. 본 논문에서는 변화하는 환경에 대응할 수 있는 automated planning system architecture를 소개한다. 심볼릭 기반의 task planning을 위해 PDDL을 활용하였으며 실시간 환경 정보 업데이트를 위해 그래프 데이터베이스를 이용한다. 제안한 구조는 시나리오 기반 실험을 통해 검증하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.137.1-137
• /
• 2001

A new method for a guide robot using Real-Time Linux OS is introduced in this paper. A guide robot is to guide people in museums or buildings. So it has to be more reliable and stable in its control system. In addition, it has to satisfy Real-Time operation requirement because it needs to react to changing environment prompty. The task includes localization, map building, collision avoidance, path planning, and user interface software. The modular guide robot is designed with Real-Time Linux OS, which is composed of many open sources for scheduler, interrupt dispatcher, fifos, shared memory, timer services. We developed application software to satisfy the given task. The developed guide robot moves at 0.2ms and the interrupt latency is less than 100$\mu\textrm{s}$ It is thought that the developed system can be a stable and low cost open architecture robot controller for ...

• 제어로봇시스템학회논문지
• /
• 제5권3호
• /
• pp.249-256
• /
• 1999

The conventional robot manipulability is decomposed into linear manipulability and angular manipulability so that they may be analysed and visualized in easy way even in the case of 3 dimensional task space with 6 variables. After the Jacobian matrix is decomposed into linear part and angular part, constraint on joint velocities is transformed into linear task velocity and angular task velocity through the decomposed Jacobian matrices. Under the assumption of redundant robot manipulators, several optimization problems which utilize the redundancy are formulated to be solved by linear programming technique or sequential quadratic programming technique. After deriving the solutions of the optimization problems, we give graphical interpretations for the solutions.

• 제어로봇시스템학회논문지
• /
• 제18권5호
• /
• pp.445-452
• /
• 2012

With the increasing number of high-rise and large-scale buildings, modern buildings are becoming intelligent, and are incurring high construction costs and requiring careful maintenance. Maintenance works for high-rise buildings significantly depend on human labor, unlike other construction processes that are gradually being automated. The resulting accidents may produce very high social and economic losses. To address this problem, herein, this paper proposes robotic building maintenance system using multi-robot concept, in specific, cleaning a building facade which is directly subjected to minimize human labor; that improves the process efficiency and economic feasibility. The sensor for detecting contamination of building's outer-wall glass is proposed; Kalman filter was used for estimating robots' status with the contamination of the window glass. Task allocation of the sensor based multi-robots for an effective way of task execution is introduced and the feasibility was verified through the simulations.

• 제어로봇시스템학회논문지
• /
• 제15권12호
• /
• pp.1232-1239
• /
• 2009

This paper proposes an exploration strategy to efficiently find a specific place in large unknown environments with wall-following based path planning. Many exploration methods proposed so far showed good performance but they focused only on efficient planning for modeling unknown environments. Therefore, to successfully accomplish the room finding task, two additional requirements should be considered. First, suitable path-planning is needed to recognize the room number. Most conventional exploration schemes used the gradient method to extract the optimal path. In these schemes, the paths are extracted in the middle of the free space which is usually far from the wall. If the robot follows such a path, it is not likely to recognize the room number written on the wall because room numbers are usually too small to be recognized by camera image from a distance. Second, the behavior which re-explores the explored area is needed. Even though the robot completes exploration, it is possible that some rooms are not registered in the constructed map for some reasons such as poor recognition performance, occlusion by a human and so on. With this scheme, the robot does not have to visit and model the whole environment. This proposed method is very simple but it guarantees that the robot can find a specific room in most cases. The proposed exploration strategy was verified by various experiments.

• Advances in robotics research
• /
• 제1권2호
• /
• pp.171-183
• /
• 2014

Distributed planning and decision making can be beneficial from the robustness, adaptability and fault tolerance in multi-robot systems. Distributed mechanisms have not been employed in three dimensional transportation systems namely aerial and underwater environments. This paper presents a distributed cooperation mechanism on multi robot transportation problem in three dimensional environments. The cooperation mechanism is based on artificial capital market, a newly introduced market based negotiation protocol. In the proposed mechanism contributing in transportation task is defined as asset. Each robot is considered as an investor who decides if he is going to invest on some assets. The decision is made based on environmental constraint including fuel limitation and distances those are modeled as capital and cost. Simulations show effectiveness of the algorithm in terms of robustness, speed and adaptability.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.40-43
• /
• 1996

An off-line programming, OLP, system is widely used in automation fines. To help an on-line robot system to carry out desirable tasks planned by the off-line simulation, an approach to the real-time communication is presented. The OLP system developed consists of a software, a host computer(PC), a SCARA robot body, four servo drivers, and four independent joint controllers. This study focuses on the software where real-time communication is included. The software, can be used in teaching, trajectory planning, real-time running, and performance evaluation. The evaluation of different control algorithms is one of the merits of the software. The software can give servo commands for task running. A comparison of generated and corresponding actual trajectories provides the evaluation of task performance. The safety, of the OLP system is ensured by alarming malfuntions of the system. The OLP system developed can reduce the teaching time and increase the user's convenience.