• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.365-372
• /
• 2022

The accurate object recognition is important for the precise and accurate manipulation. To enhance the recognition performance, we can use various types of sensors. In general, acquired data from sensors have a high sampling rate. So, in the past, the RNN-based model is commonly used to handle and analyze the time-series sensor data. However, the RNN-based model has limitations of excessive parameters. CNN-based model also can be used to analyze time-series input data. However, CNN-based model also has limitations of the small receptive field in early layers. For this reason, when we use a CNN-based model, model architecture should be deeper and heavier to extract useful global features. Thus, traditional methods like RN N -based and CN N -based model needs huge amount of learning parameters. Recently studied result shows that Fast Fourier Convolution (FFC) can overcome the limitations of traditional methods. This operator can extract global features from the first hidden layer, so it can be effectively used for feature extracting of sensor data that have a high sampling rate. In this paper, we propose the algorithm to recognize objects using tactile sensor data and the FFC model. The data was acquired from 11 types of objects to verify our posed model. We collected pressure, current, position data when the gripper grasps the objects by random force. As a result, the accuracy is enhanced from 84.66% to 91.43% when we use the proposed FFC-based model instead of the traditional model.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.10
• /
• pp.168-177
• /
• 2001

Reverse engineering has been widely used for the shape reconstruction of an object without CAD data and the measurement of clay or wood models fur the development of new products. To generate a surface from measured points by a laser scanner, typical steps include the scanning of a clay or wood model, the generation of compatible input curves, the generation of a surface and manufacturing data like G code or STL file. A laser scanner has a great potential to get geometrical data of a model for its frost measuring speed and higher precision. The data from a laser scanner are composed of many line stripes of points including small spikes and noise. A new approach using automated surface generating algorithm is introduced to deal with problems during reverse engineering process. And the input data and the generated surface are represented in IGES format, thus can be supplied to other CAD/CAM software without any data manipulation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.4
• /
• pp.365-372
• /
• 2001

The general rule of boundary delimitation is a the principle of equidistant. The principle of equidistant is a method that determine boundary delimitation from fixed distant of baseline or basepoint. In this paper, study Two-Point Algorithm and Three-Point Algorithm that are widely used. and developed the Boundary Delimitation Program to verify the result and error. This program is specially useful for maritime boundary delimitation problem because there is no artificial and natural object in sea to determine boundary. As a result The mid-points computed on Ellipsoid have small error rather than mid-points on plane or sphere without any distortion by map projection. Through developing boundary delimitation program, can eliminate the various manipulation error using paper map, and quickly cope with maritime boundary delimitation negotiation. Also, verify that the error of basepoint in baseline is propagate the mid-point in mid-line, and determine suitable reference plane.