Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD, COMPUTER SYSTEM, AND COMPUTER PROGRAM FOR REINFORCEMENT LEARNING-BASED AUTONOMOUS DRIVING ADAPTABLE TO SENSOR CONFIGURATION AND ROBOT SHAPE
Document Type and Number:
WIPO Patent Application WO/2023/054929
Kind Code:
A1
Abstract:
Disclosed is a method, computer system, and computer program for reinforcement learning-based autonomous driving adaptable to a sensor configuration and a robot shape. An autonomous driving learning method may comprise a step of learning robot autonomous driving by randomly assigning robot configuration parameters, which include a robot shape and a sensor configuration, as autonomous driving parameters to at least one robot agent on a simulation.

Inventors:
CHOI JINYOUNG (KR)
HWANG SEULBIN (KR)
CHUNG SEUNGHWAN (KR)
KIM KEONWOO (KR)
BYUN JAEJUNG (KR)
Application Number:
PCT/KR2022/013355
Publication Date:
April 06, 2023
Filing Date:
September 06, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NAVER LABS CORP (KR)
International Classes:
B25J9/16; B25J5/00; B25J19/02
Foreign References:
US20200074230A12020-03-05
JP2015100866A2015-06-04
US20200368906A12020-11-26
US20200293862A12020-09-17
KR102303126B12021-09-17
Attorney, Agent or Firm:
YANG, Sungbo (KR)
Download PDF: