• Title/Summary/Keyword: Small robot

Search Result 492, Processing Time 0.041 seconds

Robot Locomotion via RLS-based Actor-Critic Learning (RLS 기반 Actor-Critic 학습을 이용한 로봇이동)

  • Kim, Jong-Ho;Kang, Dae-Sung;Park, Joo-Young
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.15 no.7
    • /
    • pp.893-898
    • /
    • 2005
  • Due to the merits that only a small amount of computation is needed for solutions and stochastic policies can be handled explicitly, the actor-critic algorithm, which is a class of reinforcement learning methods, has recently attracted a lot of interests in the area of artificial intelligence. The actor-critic network composes of tile actor network for selecting control inputs and the critic network for estimating value functions, and in its training stage, the actor and critic networks take the strategy, of changing their parameters adaptively in order to select excellent control inputs and yield accurate approximation for value functions as fast as possible. In this paper, we consider a new actor-critic algorithm employing an RLS(Recursive Least Square) method for critic learning, and policy gradients for actor learning. The applicability of the considered algorithm is illustrated with experiments on the two linked robot arm.

Development of a vaccine automation injection system for flatfish using a template matching (템플릿 매칭을 이용한 넙치용 백신자동접종시스템 개발)

  • Lee, Dong-Gil;Yang, Young-Su;Park, Seong-Wook;Cha, Bong-Jin;Xu, Guo-Cheng;Kim, Jong-Rak
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.48 no.2
    • /
    • pp.165-173
    • /
    • 2012
  • Nationally, flatfish vaccination has been performed manually, and is a laborious and time-consuming procedure with low accuracy. The handling requirement also makes it prone to contamination. With a view to eliminating these drawbacks, we designed an automatic vaccine system in which the injection is delivered by a Cartesian coordinate robot guided by a vision system. The automatic vaccine injection system is driven by an injection site location algorithm that uses a template-matching technique. The proposed algorithm was designed to derive the time and possible angles of injection by comparing a search area with a template. The algorithm is able to vaccinate various sizes of flatfish, even when they are loaded at different angles. We validated the performance of the proposed algorithm by analyzing the injection error under randomly generated loading angles. The proposed algorithm allowed an injection rate of 2000 per hour on average. Vaccination of flatfish with a body length of up to 500mm was possible, even when the orientation of the fish was random. The injection errors in various sizes of flatfish were very small, ranging from 0 to 0.6mm.

Area-Based Q-learning Algorithm to Search Target Object of Multiple Robots (다수 로봇의 목표물 탐색을 위한 Area-Based Q-learning 알고리즘)

  • Yoon, Han-Ul;Sim, Kwee-Bo
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.15 no.4
    • /
    • pp.406-411
    • /
    • 2005
  • In this paper, we present the area-based Q-learning to search a target object using multiple robot. To search the target in Markovian space, the robots should recognize their surrounding at where they are located and generate some rules to act upon by themselves. Under area-based Q-learning, a robot, first of all, obtains 6-distances from itself to environment by infrared sensor which are hexagonally allocated around itself. Second, it calculates 6-areas with those distances then take an action, i.e., turn and move toward where the widest space will be guaranteed. After the action is taken, the value of Q will be updated by relative formula at the state. We set up an experimental environment with five small mobile robots, obstacles, and a target object, and tried to search for a target object while navigating in a unknown hallway where some obstacles were placed. In the end of this paper, we presents the results of three algorithms - a random search, area-based action making (ABAM), and hexagonal area-based Q-teaming.

A New Wheel Design for Miniaturized Terrain Adaptive Robot (험지 주행용 소형 로봇을 위한 바퀴의 설계)

  • Kim, Yoo Seok;Kim, Haan;Jung, Gwang Pil;Kim, Seong Han;Cho, Kyu Jin;Chu, Chong Nam
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.30 no.1
    • /
    • pp.32-38
    • /
    • 2013
  • Small mobile robots which use round wheels are suitable for driving on a flat surface, but it cannot climb the obstacle whose height is greater than the radius of wheels. As an alternative, legged-wheels have been proposed by many researchers due to its better climbing performance. However, driving and climbing performances have a trade-off relationship so that their driving performance should be sacrificed. In this study, in order to achieve both driving and climbing performances, a new transformable wheel was developed. The developed transformable wheel can have a round shape on a flat surface and change its shape into legged-wheel when it makes a contact with an obstacle. For design of the transformable wheel, the performance of legged-wheel was analyzed with respect to the number and curvature of the leg, and then the new transformable wheel was designed based on the analysis. Contrary to the existing transformable wheels that contain additional actuators for the transformation, the developed transformable wheel can be unfolded without any additional actuator. In this study, in order to validate the transformable wheel, a simple robot platform was fabricated. Consequently, it climbed the obstacle whose height is 2.6 times greater than the wheel radius.

Intracorporeal Esophagojejunostomy during Reduced-port Totally Robotic Gastrectomy for Proximal Gastric Cancer: a Novel Application of the Single-Site® Plus 2-port System

  • Choi, Seohee;Son, Taeil;Song, Jeong Ho;Lee, Sejin;Cho, Minah;Kim, Yoo Min;Kim, Hyoung-Il;Hyung, Woo Jin
    • Journal of Gastric Cancer
    • /
    • v.21 no.2
    • /
    • pp.132-141
    • /
    • 2021
  • Purpose: Intracorporeal esophagojejunostomy during reduced-port gastrectomy for proximal gastric cancer is a technically challenging technique. No study has yet reported a robotic technique for anastomosis. Therefore, to address this gap, we describe our reduced-port technique and the short-term outcomes of intracorporeal esophagojejunostomy. Materials and Methods: We conducted a retrospective review of patients who underwent a totally robotic reduced-port total or proximal gastrectomy between August 2016 and March 2020. We used an infra-umbilical Single-Site® port with two additional ports on both sides of the abdomen. To transect the esophagus, a 45-mm endolinear stapler was inserted via the right abdominal port. The common channel of the esophagojejunostomy was created between the apertures in the esophagus and proximal jejunum using a 45-mm linear stapler. The entry hole was closed with a 45-mm linear stapler or robot-sewn continuous suture. All anastomoses were performed without the aid of an assistant or placement of stay sutures. Results: Among the 40 patients, there were no conversions to open, laparoscopic, or conventional 5-port robotic surgery. The median operation time and blood loss were 254 min and 50 mL, respectively. The median number of retrieved lymph nodes was 40.5. The median time to first flatus, soft diet intake, and length of hospital stay were 3, 5, and 7 days, respectively. Three (7.5%) major complications, including two anastomosis-related complications and a case of small bowel obstruction, were treated with an endoscopic procedure and re-operation, respectively. No mortality occurred during the study period. Conclusions: Intracorporeal esophagojejunostomy during reduced-port gastrectomy can be safely performed and is feasible with acceptable surgical outcomes.

On the Integrated Operation Concept and Development Requirements of Robotics Loading System for Increasing Logistics Efficiency of Sub-Terminal

  • Lee, Sang Min;Kim, Joo Uk;Kim, Young Min
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.14 no.1
    • /
    • pp.85-94
    • /
    • 2022
  • Recently, consumers who prefer contactless consumption are increasing due to pandemic trends such as Corona 19. This is the driving force for developing the last mile-based logistics ecosystem centered on the online e-commerce market. Lastmile led to the continued development of the logistics industry, but increased the amount of cargo in urban area, and caused social problems such as overcrowding of logistics. The courier service in the logistics base area utilizes the process of visiting the delivery site directly because the courier must precede the loading work of the cargo in the truck for the delivery of the ordered product. Currently, it's carried out as automated logistics equipment such as conveyor belt in unloading or classification stage, but the automation system isn't applied, so the work efficiency is decreasing and the intensity of the courier worker's labor is increased. In particular, small-scale courier workers belonging to the sub-terminal unload at night at underdeveloped facilities outside the city center. Therefore, the productivity of the work is lowered and the risk of safety accidents is exposed, so robot-based loading technology is needed. In this paper, we have derived the top-level concept and requirements of robot-based loading system to increase the flexibility of logistics processing and to ensure the safety of courier drivers. We defined algorithms and motion concepts to increase the cargo loading efficiency of logistics sub-terminals through the requirements of end effector technology, which is important among concepts. Finally, the control technique was proposed to determine and position the load for design input development of the automatic conveyor system.

Permeability of the Lateral Air Flow through Unstructured Pillar-like Nanostructures (비정형 기둥 형상을 가진 나노구조에서의 가스 투과성 실험 연구)

  • Hyewon Kim;Hyewon Lim;Jeong Woo Park;Sangmin Lee;Hyungmo Kim
    • Tribology and Lubricants
    • /
    • v.39 no.5
    • /
    • pp.197-202
    • /
    • 2023
  • Recently, research on experimental and analytical techniques utilizing microfluidic devices has been pursued. For example, lab-on-a-chip devices that integrate micro-devices onto a single chip for processing small sample quantities have gained significant attention. However, during sample preparation, unnecessary gases can be introduced into the internal channels, thus, impeding device flow and compromising specific function efficiency, including that of analysis and separation. Several methods have been proposed to mitigate this issue, however, many involve cumbersome procedures or suffer from complexities owing to intricate structures. Recently, some approaches have been introduced that utilize hydrophobic device structures to remove gases within channels. In such cases, the permeability of gases passing through the structure becomes a crucial performance factor. In this study, a method involving the deposition and sintering of diluted Ag-ink onto a silicon wafer surface is presented. This is followed by unstructured nano-pattern creation using a Metal Assisted Chemical Etching (MACE) process, which yields a nanostructured surface with unstructured pillar shapes. Subsequently, gas permeability in the spaces formed by these surface structures is investigated. This is achieved by experiments conducted to incorporate a pressure chamber and measure gas permeability. Trends are subsequently analyzed by comparing the results with existing theories. Finally, it can be confirmed that the significance of this study primarily lies in its capability to effectively evaluate gas permeability through unstructured pillar-like nanostructures, thus, providing quantitative values for the appropriate driving pressure and expected gas removal time in practical device operation.

Initial Experience of Robotic Cardiac Surgery (수술로봇을 이용한 심장수술 첫 체험)

  • Cho Sung Woo;Chung Cheol Hyun;Kim Kyoung Sun;Choo Suk Jung;Song Hyung;Song Meong Gun;Lee Jae Won
    • Journal of Chest Surgery
    • /
    • v.38 no.5 s.250
    • /
    • pp.366-370
    • /
    • 2005
  • Background: In general, cardiac surgery has been performed via median sternotomy. During the past decade, improvements in endoscopic equipment and operative techniques have resulted in development of minimally invasive cardiac operation using small incisions. With the advent of a voice controlled camera-holding robotic arm (AESOP 3000, Automated Endoscope System for Optimal Positioning), cardiac surgery entered the robotic age. Material and Method: Between April 2004 and December 2004, a total of seventy eight patients underwent robotic cardiac surgery, of whom sixty four patients underwent robot-assisted minimally invasive cardiac surgery via 5cm right lateral minithoracotomy using voice controlled robotic arm, femoral vessels cannulation, percutaneous internal jugular cannulation, transthoracic aortic cross clamp. Other fourteen patients underwent MIDCAB via internal mammary artery harvesting using AESOP. Result: Robotic cardiac surgery were mitral valve repair in 37 cases, mitral valve replacement in 10 cases, aortic valve replacement in 1 case, MIDCAB in 14 cases, ASD operation in 9 cases, and isolated Maze procedure in 1 case. In mitral operation, mean CPB time was $165.3\pm43.1$ minutes and mean ACC time was $110.4\pm48.2$ minutes. Median length of hospital stay was 6 days (range 3 to 30) in mitral operation, 4 days (range 2 to 7) in MIDCAB, and 4 days (range 2 to 6) in ASD operation. For complications, 3 patients were required by reoperation for bleeding. There was no hospital mortality. Conclusion: Our experience of robot cardiac surgery suggests that many cardiovascular surgeons will be able to perform minimally invasive cardiac operations through small incisions with robot-assisted video-direction. Well-designed studies and close long-term follow-up will be required to analyze the benefits of robot-assisted operation.

A Study on the Factors Affecting the Acceptance of Logistics Robot in the Fulfillment Center Using the Technology Acceptance Model (기술수용모형을 통한 물류센터 내 물류로봇 구매의도에 영향을 미치는 요인에 관한 연구)

  • Hwang, Hyeon-Chul;Song, Sang-Hwa
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.20 no.12
    • /
    • pp.287-297
    • /
    • 2019
  • Responding to the rapid delivery demands and variety of small-volume products through human resource-dependent logistics operations in online markets is difficult. Logistics robots in fulfillment centers are expected to increase due to difficulties in hiring workers and rising labor costs. Amazon operates more than 100,000 robots in its Fulfillment centers. Alibaba, DHL, and UPS are also introducing robot technology to improve the logistics efficiency. Logistics robots are being used actively in the fierce online market competition of the global distribution industry. On the other hand, Korea is relatively sluggish. To revitalize the introduction of logistics robots in Korea, it is necessary to examine the factors that influence acceptance. The description of acceptability was based on an expanded technology acceptance model that has been verified through various studies. Studies have shown that both the ease and usefulness of purchasing have significant effects, and that ease has the greatest effect. The more experience involved, the more innovative, the more positive. The usefulness was shown to be positive as the perceived risks are low, price efficiency is good, and social impact is greater. This study provides theoretical and practical implications for logistics robot development and marketing.

Development of an Automatic Grafting Robot for Fruit Vegetables using Image Recognition (영상인식 기술 이용 과채류 접목로봇 개발)

  • Kang, Dong Hyeon;Lee, Si Young;Kim, Jong Koo;Park, Min Jung;Son, Jin Kwan;Yun, Sung-Wook
    • Journal of Bio-Environment Control
    • /
    • v.28 no.4
    • /
    • pp.322-327
    • /
    • 2019
  • This study was conducted to improve the performance of automatic grafting robot using image recognition technique. The stem diameters of tomatoes and cucumber at the time of grafting were $2.5{\pm}0.3mm$ and $2.2{\pm}0.2mm$ for scions and $3.1{\pm}0.7mm$ and $3.6{\pm}0.3mm$ for rootstocks, respectively. The grafting failure was occurred when the different height between scions and rootstocks were over 4 mm and below 2 mm due to the small contact area of both cutting surface. Therefore, it was found that the height difference at the cutting surface of 3 mm is appropriate. This study also found that grafting failure was occurred when the stem diameters of both scions and rootstocks were thin. Therefore, it was suggested to use at least one stem with thicker than the average stem diameter. Field survey on the cutting angle of stems by hand were ranged from 13 to 55 degree for scions and 15 to 67 degree for rootstocks, respectively, which indicates that this could cause the grafting failure problem. However, the automatic grafting robot developed in this study rotates the seedlings 90 degree and then the stems are cut using a cutting blade. The control part of robot use all images taken from grafting process to determine the distance between a center of both ends of stem and a gripper center and then control the rotation angle of a gripper. Overall, this study found that The performance of automatic grafting robot using image recognition technique was superior with the grafting success rates of cucumber and tomato as $96{\pm}3.2%$ and $95{\pm}4%$, respectively.