首页|Study Data from Jozef Stefan Institute Update Knowledge of Robotics (Hierarchica l Learning of Robotic Contact Policies)
Study Data from Jozef Stefan Institute Update Knowledge of Robotics (Hierarchica l Learning of Robotic Contact Policies)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics is the subjec t of a report. According to news reporting originating from Ljubljana, Slovenia, by NewsRx correspondents, research stated, “The paper addresses the issue of le arning tasks where a robot maintains permanent contact with the environment. We propose a new methodology based on a hierarchical learning scheme coupled with t ask representation through directed graphs.” Financial supporters for this research include European Union (EU), Slovenian Re search and Innovation Agency. Our news editors obtained a quote from the research from Jozef Stefan Institute, “These graphs are constituted of nodes and branches that correspond to the stat es and robotic actions, respectively. The upper level of the hierarchy essential ly operates as a decision- making algorithm. It leverages reinforcement learning (RL) techniques to facilitate optimal decision-making. The actions are generate d by a constraintspace following (CSF) controller that autonomously identifies feasible directions for motion. The controller generates robot motion by adjusti ng its stiffness in the direction defined by the Frenet-Serret frame, which is a ligned with the robot path.”
LjubljanaSloveniaEuropeEmerging Te chnologiesMachine LearningRobotRoboticsRobotsJozef Stefan Institute
NETL
NSTL
