• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.349-351
• /
• 2007

A concept of the semi-autonomous tele-weeding-system which performs weeding tasks through co-operation of human and machine intelligence is proposed. The tele-weeding system consists of weeding robot, communication networks and operating server. The images of plants taken by the weeding robot are transferred through the communication networks to the human operator. Positions of the weeds are indicated at the operating host by the operator and transferred back to the weeding robot. Such position informations are converted to the world space and the weeding is done based on the robot intelligence. Feasibility of such concept has been tested through development of a laboratory model of the system.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.27-34
• /
• 2023

Weeding in orchards is closely associated with productivity and quality. The customary weeding process is both labor-intensive and time-consuming. To solve the problems, there is need for automation of agricultural robots and machines in the agricultural field. On the other hand, orchards have complicated working areas due to narrow spaces between trees and amorphous terrain. Therefore, it is necessary to develop customized robot technology for unmanned weeding work within the department. This study developed a path generation and path control method for unmanned weeding according to the orchard environment. For this, the width of the weeding span, the number of operations, and the width of the weeding robot were used as input parameters for the orchard environment parameters. To generate a weeding path, a weeding robot was operated remotely to obtain GNSS-based location data along the superheated center line, and a driving performance test was performed based on the generated path. From the results of orchard field tests, the RMSE in weeding period sections was measured at 0.029 m, with a maximum error of 0.15 m. In the steering period within row and steering to the next row sections, the RMSE was 0.124 m, and 0.047 m, respectively.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.325-332
• /
• 2000

The objective of this research work is to develop an autonomous levee-weeding robot. In this paper, pathway control system for the robot is developed and simulated. A prototype autonomous vehicle for levee weeding is also developed and used in the actual test. The results obtained in this research work is summarized as follows; 1) The simulated typical time history of lateral displacements and heading angle of the vehicle in straight run shows that the vehicle tendency is always to achieve the target path from any of its deviated position and heading angle. 2) The test run on an asphalt surface by the prototype crawler-type vehicle is in good agreement with the simulation results.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.1
• /
• pp.43-50
• /
• 2014

This paper introduces a robot platform which can do weeding while traveling between rice seedlings stably against irregular land surface of a paddy field. Also, an autonomous navigation technique that can track on stable state without any damage of the seedlings in the working area is proposed. Detection of the rice seedlings and avoidance knocking down by the robot platform is achieved by the sensor fusion of a laser range finder (LRF) and an inertial measurement unit (IMU). These sensors are also used to control navigating direction of the robot to keep going along the column of rice seedling consistently. Deviation of the robot direction from the rice column that is sensed by the LRF is fed back to a proportional and derivative controller to obtain stable adjustment of navigating direction and get proper returning speed of the robot to the rice column.

• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.1557-1558
• /
• 2013

• The Journal of Korea Robotics Society
• /
• v.9 no.3
• /
• pp.147-153
• /
• 2014

In this paper, we proposed a new algorithm of the guidance line extraction for autonomous weeding robot based on infrared vision sensor in wet paddy. It is the critical process for guidance line extraction which finds the central point or area of rice row. In order to improve accuracy of the guidance line, we are trying to use the morphological characteristics of rice that the direction of rice leaves have convergence to central area of rice row. Using Hough transform, we were represented the curved leaves as a combination of segmented straight lines on binary image that has been skeletonized and segmented object. A slope of the guidance line was gotten as calculate the average slope of all segmented lines. An initial point of the guidance line was determined that is the maximum pixel value of the accumulated white columns of a binary image which is rotated the slope of guidance line in the opposite direction. We also have verified an accuracy of the proposed algorithm by experiments in the real wet paddy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1651-1656
• /
• 2005

This paper describes a natural frequency analysis conducted to find out a suitable working area for a spring-manipulator system generating a large vibrating force with mechanical resonance. Large force generation is one of the functions that we hope for a robot. For example, a weeding robot is required to generate a large force, because some weeds have roots spreading deeply and tightly. The spring-manipulator system has a spring element as an end-effector, so it can be in a state of resonance with the elasticity of the spring element and the inertial characteristics of the manipulator. A force generation method utilizing the mechanical resonance has potential to produce a large force that cannot be realized by a static method. A method for calculating a natural frequency of a spring-manipulator system with the generalized inertia tensor is proposed. Then the suitable working area for the spring-manipulator system is identified based on a natural frequency analysis. If a spring-manipulator system operates in the suitable working area, it can sustain mechanical resonance and generate a large vibrating force. Moreover, it is shown that adding a mass at the tip of the manipulator expands the suitable working area.

• Korean Journal of Weed Science
• /
• v.31 no.1
• /
• pp.8-23
• /
• 2011

Weeds are one of the major constraints to crop production in organic farming systems. This paper reviews major results and techniques achieved with physical, cultural, and biological weed control and their perspectives in organic agriculture. Physical methods includes mechanical, thermal, lighting, electrocution, pneumatic, autonomous robot weeding control techniques. Cultural weed control methods includes mulching, tillage, crop rotation, cover crops and crop competition. Physical and cultural weed control techniques are especially important in organic farming crops where other weed control options are limited or not available without use of herbicides. Biological weed control includes mycoherbicides, innundative biological control, broad-spectrum biological control and allelopathy. Successful weed management in organic farming requires well managed integrated systems of mechanical control using newly developed machines, cultural control and biological control methods. Weed management decision-aid models may also needed to develop to provide greater assurance of achieving profitability and appropriate long-term weed management in organic farming in the future.