首页|Findings in Robotics and Automation Reported from Zhejiang University (Learning Hierarchical Graph-based Policy for Goal-reaching In Unknown Environments)
Findings in Robotics and Automation Reported from Zhejiang University (Learning Hierarchical Graph-based Policy for Goal-reaching In Unknown Environments)
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 – Current study results on Robotics - Ro botics and Automation have been published. According to news reporting originati ng from Zhejiang, People’s Republic of China, by NewsRx correspondents, research stated, “Reaching in unknown environments is one of the essential tasks in robo t applications. Large-scale perception and long-horizon decision-making are the keys to solving this task as the operation scope expands or complexity rises.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC).Our news editors obtained a quote from the research from Zhejiang University, “E xisting navigation methods may suffer from degraded performance in complicated e nvironments induced by scalabilitylimited map representation or greedy decision strategy. We propose the path-extended graph as a compact map representation pr oviding sufficient structural information within a reasonable receptive field an d incorporate it into a hierarchical policy for higher efficiency and generaliza bility. The path-extended graph contains the concise topology of environment str ucture and frontier layout for large-scale perception, avoiding the impact of re dundant information. The hierarchical policy solves long-horizon non-myopic deci sion-making through a high-level frontier selection policy using deep reinforcem ent learning (DRL) and a low-level motion controller that handles path planning and collision avoidance.”
ZhejiangPeople’s Republic of ChinaAs iaRobotics and AutomationRoboticsZhejiang University
NETL
NSTL
