ÇѱÛÁ¦¸ñ(Korean Title) |
½ºÅ×·¹¿À ºñÀüÀ» ÀÌ¿ëÇÑ ½Ç½Ã°£ Àΰ£Çü ·Îº¿ ±ËÀû ÃßÃâ ¹× ³×ºñ°ÔÀÌ¼Ç |
¿µ¹®Á¦¸ñ(English Title) |
Real-time Humanoid Robot Trajectory Estimation and Navigation with Stereo Vision |
ÀúÀÚ(Author) |
¹ÚÁöȯ
Á¶¼ºÈ£
Jihwan Park
Sungho Jo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 37 NO. 08 PP. 0641 ~ 0646 (2010. 08) |
Çѱ۳»¿ë (Korean Abstract) |
½ºÅ×·¹¿À Ä«¸Þ¶ó¸¦ °®Ãá Àΰ£Çü ·Îº¿ÀÌ ÀÚÀ²ÀûÀ¸·Î ÁÖº¯ »óȲÀ» ÀÎÁöÇÏ¸é¼ ¸ñÀûÁö±îÁöÀÇ °æ·Î¸¦ ½Ç½Ã°£À¸·Î »ý¼º ¹× ¼öÁ¤ÇÏ´Â °£´ÜÇÑ ¾Ë°í¸®ÁòÀ» Á¦½ÃÇÑ´Ù. Ư¡Á¡µéÀ» ½Ã°¢Àû À̹ÌÁö¿¡¼ ÃßÃâÇÔÀ¸·Î½á ÁÖÀ§ÀÇ Àå¾Ö¹°µéÀ» ÀÎÁöÇÑ´Ù. Àΰ£Çü ·Îº¿ÀÇ µÚ¶×°Å¸®´Â º¸Çà ¿òÁ÷ÀÓÀ» ¸ðµ¨¸µÇÔÀ¸·Î½á ·Îº¿ÀÇ Á߽ɺΠ±âÁØ¿¡¼ÀÇ ½ÇÁ¦ °æ·Î¸¦ À¯ÃßÇÏ¿© °èȹµÈ °æ·Î¿Í ºñ±³ÇÔÀ¸·Î½á ½Ã°¢Àû Çǵå¹é Á¦¾î¸¦ ±¸ÇöÇÏ°í ¼º°øÀûÀÎ ³×ºñ°ÔÀ̼ÇÀ» ¼öÇàÇÑ´Ù. ½ÇÁ¦ Àΰ£Çü ·Îº¿ÀÇ ³×ºñ°ÔÀÌ¼Ç ½ÇÇèÀ» ÅëÇØ Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀÇ °¡´É¼ºÀ» ÀÔÁõÇÑ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
This paper presents algorithms for real-time navigation of a humanoid robot with a stereo vision but no other sensors. Using the algorithms, a robot can recognize its 3D environment by retrieving SIFT features from images, estimate its position through the Kalman filter, and plan its path to reach a destination avoiding obstacles. Our approach focuses on estimating the robot¡¯s central walking path trajectory rather than its actual walking motion by using an approximate model. This strategy makes it possible to apply mobile robot localization approaches to humanoid robot localization. Simple collision free path planning and motion control enable the autonomous robot navigation. Experimental results demonstrate the feasibility of our approach. |
Å°¿öµå(Keyword) |
½ºÅ×·¹¿À ºñÀü ³×ºñ°ÔÀ̼Ç
ÈÞ¸Ó³ëÀÌµå ·Îº¿ ³×ºñ°ÔÀ̼Ç
Ä®¸¸ÇÊÅÍ ±â¹Ý ÀÚ±â À§Ä¡ Ç¥Çö ¾Ë°í¸®Áò
Stereo vision navigation
Humanoid robot navigation
Kalman-filter based localization algorithm
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|