Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
ÇѱÛÁ¦¸ñ(Korean Title) |
SVMÀ» ÀÌ¿ëÇÑ °¡Á¤¿ë Çù·Â ·Îº¿ÀÇ Á¶ÀÎÆ® À§Ä¡ ±â¹Ý ½ÇÇൿÀÛ ¿¹Ãø ¸ðµ¨ °³¹ß |
¿µ¹®Á¦¸ñ(English Title) |
Development of Joint-Based Motion Prediction Model for Home Co-Robot Using SVM |
ÀúÀÚ(Author) |
Sungyeob Yoo
Dong-Yeon Yoo
Ye-Seul Park
Jung-Won Lee
À¯¼º¿±
À¯µ¿¿¬
¹Ú¿¹½½
ÀÌÁ¤¿ø
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 08 NO. 12 PP. 0491 ~ 0498 (2019. 12) |
Çѱ۳»¿ë (Korean Abstract) |
µðÁöÅÐ Æ®À©Àº Çö½Ç ¼¼°èÀÇ ¹°¸®ÀûÀÎ »ç¹°À» ÄÄÇ»ÅÍ»ó¿¡ µ¿ÀÏÇÏ°Ô °¡»óȽÃÅ°´Â ±â¼ú·Î½á, IoTÀ» ÅëÇØ ¼¾¼ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ°í, ¼öÁýÇÑ µ¥ÀÌÅ͸¦ È°¿ëÇÏ¿© ¹°¸®ÀûÀÎ »ç¹°°ú °¡»ó »ç¹°À» ¾ç¹æÇâÀ¸·Î ¿¬°áÀ» ÇÒ ¼ö ÀÖ°Ô ÇÑ´Ù. µðÁöÅÐ Æ®À© ±â¼úÀº °¡»ó ¸ðµ¨ÀÇ ½Ã¹Ä·¹À̼ÇÀ» ÅëÇØ µ¿ÀÛÀ» Á¶Á¤ÇÏ°í ȯ°æº¯È¿¡ ´ëÇÑ ´ëÀÀÀ» ¹Ì¸® ½ÇÇèÇÏ¿© À§Ç輺À» ÃÖ¼ÒÈÇÒ ¼ö ÀÖ´Â ÀåÁ¡À» Áö´Ñ´Ù. ÃÖ±Ù ÀΰøÁö´ÉÀ̳ª ±â°èÇнÀ¿¡ °ü·ÃµÈ ±â¼úµéÀÌ ÁÖ¸ñ¹Þ±â ½ÃÀÛÇϸé¼, ¹°¸®ÀûÀÎ »ç¹°ÀÇ µ¿ÀÛÀ» °¡»óÈÇÏ¿© °¡»ó ¸ðµ¨À» °üÂûÇÏ°í ´Ù¾çÇÑ ½Ã³ª¸®¿À¸¦ Àû¿ëÇÏ·Á´Â ½Ãµµ°¡ Áõ°¡ÇÏ°í ÀÖ´Ù. ƯÈ÷, Àδõ½ºÆ®¸® 4.0¿¡¼ °øÀåÀÚµ¿ÈÀÇ ÇÙ½ÉÀÎ Çù·Â ·Îº¿ÀÇ µðÁöÅÐ Æ®À©À» ±¸ÃàÇϱâ À§Çؼ´Â ·Îº¿ÀÇ µ¿ÀÛÀ» ÀÎÁöÇÏ´Â °úÁ¤ÀÌ ÇʼöÀûÀ¸·Î ¿ä±¸µÈ´Ù. ·Îº¿ÀÇ µ¿ÀÛÀ» ÀÎÁöÇϱâ À§ÇÑ ¸ðµ¨¸µ ±â¹ÝÀÇ ¿¬±¸¿¡ ºñÇØ ¼¾¼ µ¥ÀÌÅÍ ±â¹ÝÀ¸·Î µ¿ÀÛÀ» ¿¹ÃøÇÏ´Â ¿¬±¸´Â ¹ÌºñÇÑ »óȲÀÌ´Ù. µû¶ó¼ º» ³í¹®¿¡¼´Â ·Îº¿ÀÇ µ¿ÀÛÀ» ÀÎÁöÇϱâ À§ÇØ °¡Á¤¿ë Çù·Â ·Îº¿¿¡¼ Àü·ù ¹× °ü¼º ¼¾¼ µ¥ÀÌÅ͸¦ ¼öÁýÇϱâ À§ÇÑ ½ÇÇè ȯ°æÀ» ±¸ÃàÇÏ°í, ¼öÁýÇÑ ¼¾¼ µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î ÇÑ µ¿ÀÛ ¿¹Ãø ¸ðµ¨À» Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ½ÄÀº Á¶ÀÎÆ® À§Ä¡ ±â¹ÝÀ¸·Î ·Îº¿ÀÇ µ¿ÀÛ ¸í·É¾î¸¦ 9°¡Áö·Î ºÐ·ùÇÏ°í Àü·ù¿Í °ü¼º ¼¾¼°ªÀ» »ç¿ëÇÏ¿© ÇнÀÀ» ÅëÇØ ¿¹ÃøÇÏ´Â ¹æ½ÄÀÌ´Ù. À̶§, ÇнÀ¿¡ »ç¿ëµÇ´Â µ¥ÀÌÅÍ´Â Çù·Â ·Îº¿ÀÌ µ¿ÀÛ ¸í·É¾îÀÇ ÀÔ·Â ÆĶó¹ÌÅÍ¿¡ ¸¶ÁøÀ» °¡Áö°í ÀÛµ¿ÇÒ ¶§ ¼öÁýµÇ´Â ¼¾¼°ªÀÌ´Ù. À̸¦ ÅëÇØ, µ¿ÀÏÇÑ °æ·Î¸¦ µû¶ó À̵¿ÇÏ´Â 9°¡Áö µ¿ÀÛ»Ó¸¸ ¾Æ´Ï¶ó °¢ µ¿ÀÛ°ú ºñ½ÁÇÑ °æ·Î¸¦ µû¶ó À̵¿ÇÏ´Â µ¿ÀÛ¿¡ ´ëÇؼµµ ¿¹ÃøÇÏ´Â ¸ðµ¨À» ±¸ÃàÇÏ¿´´Ù. SVMÀ» ÀÌ¿ëÇÏ¿© ÇнÀÇÑ °á°ú, ¸ðµ¨ÀÇ ¼º´ÉÀº Æò±ÕÀûÀ¸·Î Á¤È®µµ, Á¤¹Ðµµ, ¹× ÀçÇöÀ²ÀÌ ¸ðµÎ 97%·Î Æò°¡µÇ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.
|
Å°¿öµå(Keyword) |
Machine Learning
IoT
Digital Twin
Big Data
Co-Robot
±â°èÇнÀ
IoT
µðÁöÅÐ Æ®À©
ºòµ¥ÀÌÅÍ
Çù·Â·Îº¿
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|