• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.363-370
• /
• 2022

Grasping a target object among clutter objects without collision requires machine intelligence. Machine intelligence includes environment recognition, target & obstacle recognition, collision-free path planning, and object grasping intelligence of robot hands. In this work, we implement such system in simulation and hardware to grasp a target object without collision. We use a RGB-D image sensor to recognize the environment and objects. Various path-finding algorithms been implemented and tested to find collision-free paths. Finally for an anthropomorphic robot hand, object grasping intelligence is learned through deep reinforcement learning. In our simulation environment, grasping a target out of five clutter objects, showed an average success rate of 78.8%and a collision rate of 34% without path planning. Whereas our system combined with path planning showed an average success rate of 94% and an average collision rate of 20%. In our hardware environment grasping a target out of three clutter objects showed an average success rate of 30% and a collision rate of 97% without path planning whereas our system combined with path planning showed an average success rate of 90% and an average collision rate of 23%. Our results show that grasping a target object in clutter is feasible with vision intelligence, path planning, and deep RL.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.60-63
• /
• 2008

본 논문에서는 신경망 모델(neural network model)과 유전자 알고리즘(genetic algorithm)을 이용한 실시간 경로 계획(real-time path-planning)과 퍼지 룰(fuzzy rule)을 이용한 효율적인 다중경로계획(multiple path-planning)을 제안한다. 실시간 경로 계획은 빠른 시간 내에 최적 경로의 생성이 반드시 수행되어야 하므로, 본 논문에서는 경로 계획 중 장애물 지역과 비장애물 지역을 빠르게 확인하기 위해 신경망 모델을 이용하여, 이동 방향 및 최적경로 탐색을 위하여 유전자 알고리즘을 이용하였다. 또한 충돌 구역에서의 효율적인 다중 경로 계획을 위해, 퍼지를 이용하여 경로를 재계획 하였다. 퍼지의 경우, 현재 위치에서 목표 지점으로의 방향을 계산하기 위한 퍼지 소속 함수와 현재 위치와 충돌 구역까지의 거리 값을 가중치로 세우고 퍼지 룰을 결정하여 경로계획을 수행하였다. 시뮬레이션을 통해 실험해본 결과, 퍼지 룰을 사용했을 때 사용하지 않았을 때 보다 좋은 성능을 나타남을 확인할 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.565-569
• /
• 2007

To find optimal path is killer application in the telematics system. The shortest path of conventional system, however, isn't always optimal path. That is, the path with minimum travelling time could be defined as optimal path in the road networks. There are techniques and algorithms for finding optimal path. Hierarchical path algorithm categorizes road networks into major layer and minor layer so that the performance of operational time increases. The path searched is accurate as much as optimal path. At above 2 system, a method to allocate minor roads to major road region influences the performance extremely. This paper proposes methods to determine search space for selecting major roads in the hierarchical path algorithm. In addition, methods which apply the proposed methods to hierarchical route algorithm is presented.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.10
• /
• pp.1203-1210
• /
• 2007

The multibeam surveillance radar is a state-of-art of 3D radar technology. It applies the stacked beam-on-received realized by a digital beamformer. In this paper, a method of a low target altitude extraction for multibeam surveillance radar in multipath environmental condition is proposed and investigated. The model of multipath propagation and radar generation produced from the low altitude target in multibeam surveillance radar and the nelder-mead simplex multipath reduction(NMSMR) method which enables a reliable low altitude target extraction in specular reflection situations are described. The proposed algorithm is simulated to confirm the effectiveness of proposed algorithm in accordance with a various of target altitudes and radar frequencies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12B
• /
• pp.1371-1379
• /
• 2009

In this paper, we propose a new multi-path routing protocol to provide reliable and stable data transmission in MANET that is composed of high-mobility nodes. The new multi-path routing establishes the main route by the mechanism based on AODV, and then finds the backup route that node-disjoint from the main route by making add nodes in the main route not participate in it. The data transmission starts immediately after finding the main route. And the backup route search process is taking place while data is transmitted to reduce the transmission delay. When either of the main route or the backup route is broken, data is transmitted continuously through the other route and the broken route is recovered to node-disjoint route by the route maintenance process. The result of the simulation based on the Qualnet simulator shows that the backup route exists 62.5% of the time when the main route is broken. And proposed routing protocol improved the packet transmission rate by 2~3% and reduced the end-to-end delay by 10% compared with AODV and AODV-Local Repair.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.824-829
• /
• 2006

한정된 자원을 사용할 수 있는 게임 AI 분야에서는 시스템 자원을 적절하게 활용하여 현실감을 극대화 시키려는 노력이 중요한 이슈이며, 3D 게임에서 캐릭터들의 자연스러운 경로 탐색은 현실성을 높이는 중요한 척도 중 하나이다. 기존 연구에서는 주로 정적인 지형, 객체들을 적절하게 회피하는 경로에 대한 연구가 많이 진행되었다. 그러나 최근 널리 이용되고 있는 다중사용자가 접속하는 온라인 RPG 게임에서는 기존 방법을 그대로 적용하기에 많은 연산량이 필요한 문제점이 있다. 본 논문에서는 네비게이션 메시(Navigation Mesh) 기반으로 최적화된 A*, 그리고 밀개(Repulsors)의 방법을 통하여 동적인 환경에서 자연스러운 경로탐색을 수행하며 3D 게임에 적용 가능한 연산량을 충족하는 경로탐색 시스템을 제안하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06d
• /
• pp.58-62
• /
• 2007

기존의 무선 Ad-hoc 네트워크의 연구는 라우팅기법에 중심으로 이뤄지고 있다. 그러나 기존의 연구들은 네트워크를 구성하는 각 요소들이 우호적이며 상호 협력적인 상황을 가정하여 연구가 이루어지고 있다. 그러나 최근 연구에는 안전한 통신을 보장하기 위한 보안 알고리즘의 필요성에 집중되고 있다. 무선 Ad-hoc 네트워크에서의 악의적인 노드를 식별하는 방안들은 정상적인 노드임에도 불구하고 거짓으로 신고했을 때 확인절차 없이 경로를 재탐색하여 최적의 경로를 변경시킴으로서 최적의 전송환경을 활용하지 못하는 문제점이 있다. 본 논문에서는 다중경로 기반의 보안경로 탐색 프로토콜인 MP-SAR 프로토콜을 이용하여 보안경로에서는 악의적인 노드를 검증하고, 유효한 최단경로를 통해 데이터전송을 하는 기법을 제안하고자 한다. 제안한 기법을 적용함으로써 노드에 대한 신고가 있을 때 확인과정을 거쳐 불필요하게 경로를 재탐색하는 과정을 줄일 수 있다.

• Journal of Korean Society of Transportation
• /
• v.18 no.3
• /
• pp.77-86
• /
• 2000

The shortest path problem is one of the mathematical Programming models that can be conveniently solved through the use of networks. The common shortest Path Problem is to minimize a single objective function such as distance, time or cost between two specified nodes in a transportation network. The sing1e objective model is not sufficient to reflect any Practical Problem with multiple conflicting objectives in the real world applications. In this paper, we consider the shortest Path Problem under multiple objective environment. Wile the shortest path problem with single objective is solvable in Polynomial time, the shortest Path Problem with multiple objectives is NP-complete. A genetic a1gorithm approach is developed to deal with this Problem. The results of the experimental investigation of the effectiveness of the algorithm are also Presented.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1145-1151
• /
• 2014

In this paper, we propose MPLO(Multi-Path routing with Local Optimization) for load balancing in the tactical backbone network. The MPLO manages global metric and local metric separately. The global metric is propagated to other routers via a routing protocol and is used for configuring loop-free multi-path. The local metric reflecting link utilization is used to find an alternate path when congestion occurs. We verified MPLO could effectively distribute user traffic among available routers by simulation.