Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
ÇѱÛÁ¦¸ñ(Korean Title) |
°ÈÇнÀÀ» ÀÌ¿ëÇÑ ¹«ÀÎ ÀÚÀ²ÁÖÇà Â÷·®ÀÇ Áö¿ª°æ·Î »ý¼º ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
Local Path Generation Method for Unmanned Autonomous Vehicles Using Reinforcement Learning |
ÀúÀÚ(Author) |
±è¹®Á¾
ÃÖ±ââ
¿Àº´È
¾çÁöÈÆ
Kim Moon Jong
Choi Ki Chang
Oh Byong Hwa
Yang Ji Hoon
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 03 NO. 09 PP. 0369 ~ 0374 (2014. 09) |
Çѱ۳»¿ë (Korean Abstract) |
¹«ÀÎ ÀÚÀ²ÁÖÇà Â÷·®¿¡¼ÀÇ °æ·Î »ý¼º ±â¹ýÀº Â÷·®ÀÌ ÀÚµ¿ÀûÀ¸·Î ¾ÈÀüÇÏ°í È¿À²ÀûÀÎ °æ·Î¸¦ »ý¼ºÇÏ°í ÁÖÇàÇÒ ¼ö ÀÖµµ·Ï ÇØ ÁØ´Ù. °æ·Î¿¡´Â Å©°Ô Àü¿ª°æ·Î¿Í Áö¿ª°æ·Î°¡ ÀÖ´Ù. Àü¿ª°æ·Î´Â Â÷·®ÀÌ Ãâ¹ßÁ¡À¸·ÎºÎÅÍ µµÂøÁ¡±îÁö °¡±â À§ÇØ ÁÖÇàÇØ¾ß ÇÏ´Â ±¸°£À», Áö¿ª°æ·Î´Â Àü¿ª°æ·Î¿¡¼ ¾òÀº ±¸°£À» ÁÖÇàÇϱâ À§Çؼ Â÷·®ÀÌ ½ÇÁ¦·Î ÁÖÇàÇØ¾ß ÇÒ °æ·Î¸¦ ÀǹÌÇÑ´Ù. º» ³í¹®¿¡¼´Â Áö¿ª°æ·Î »ý¼ºÀ» À§ÇÏ¿© È¿À²¼º ³ôÀº °î¼± ÇÔ¼ö¸¦ »ç¿ëÇÏ´Â ±âÁ¸¿¬±¸¿¡¼ ´õ ³ª¾Æ°¡ ÇнÀÀ» ÅëÇØ °æ·Î¸¦ »ý¼ºÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ¸ÕÀú °ÈÇнÀÀ» ÅëÇؼ È帰æ·Î¿¡ ´ëÇÑ ¿¹Ãø º¸»ó °ªÀ» ¾ò°í º¸»ó °ªÀÌ ÃÖ°í°¡ µÇ´Â °æ·Î¸¦ ã´Â ÀÛ¾÷À» ÇÑ´Ù. ¶ÇÇÑ Àΰø ½Å°æ¸ÁÀ» ÅëÇؼ´Â »ý¼ºµÈ °æ·Î¿¡ ÃÖÀûÈµÈ Á¶Çâ ¸í·ÉÀ» ÁÖ±â À§ÇØ Á¶Çâ °¢À» ÇнÀÇÏ´Â ÀÛ¾÷À» ÇÑ´Ù. ´õ ³ª¾Æ°¡ ÁÖÇàÇÏ´Â °æ·Î¿¡ Àå¾Ö¹°ÀÌ ¹ß°ßµÇ´õ¶óµµ À̸¦ È¿À²ÀûÀ¸·Î ȸÇÇÇÏ´Â ÃÖÀûÀÇ °æ·Î¸¦ ÇнÀ ±â¹ýÀ» ÅëÇØ ¸¸µé¾î³½´Ù. º» ³í¹®¿¡¼ Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀÇ ¿ì¼ö¼ºÀº ½ÇÁ¦ ÁÖÇà ȯ°æÀ¸·Î ¸ðµ¨¸µÇÑ ½Ã¹Ä·¹ÀÌ¼Ç ½ÇÇèÀ» ÅëÇØ °ËÁõµÇ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Path generation methods are required for safe and efficient driving in unmanned autonomous vehicles. There are two kinds of paths: global and local. A global path consists of all the way points including the source and the destination. A local path is the trajectory that a vehicle needs to follow from a way point to the next in the global path. In this paper, we propose a novel method for local path generation through machine learning, with an effective curve function used for initializing the trajectory. First, reinforcement learning is applied to a set of candidate paths to produce the best trajectory with maximal reward. Then the optimal steering angle with respect to the trajectory is determined by training an artificial neural network. Our method outperformed existing approaches and successfully found quality paths in various experimental settings, including the cases with obstacles.
|
Å°¿öµå(Keyword) |
¹«ÀÎÂ÷
°ÈÇнÀ
Àΰø½Å°æ¸Á
Áö¿ª°æ·Î
°æ·Î»ý¼º
Unmanned Autonomous Vehicle
Reinforcement Learning
Artificial Neural Networks
Local Path
Trajectory
Generation
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|