Memory-based Parameterized Skills Learning For Mapless Visual Navigation

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Memory-based Parameterized Skills Learning For Mapless Visual Navigation
	Liu YY(刘宇阳)1,2,3; Cong Y(丛杨)2,3 ; Sun G(孙干)1,2,3
	2019
会议日期	September 22-25, 2019
会议地点	Taipei, Taiwan
关键词	Mapless visual navigation Deep reinforcement learning (DRL) Long short term memory AI2THOR
页码	1890-1894
英文摘要	The recently-proposed reinforcement learning for mapless visual navigation can generate an optimal policy for searching different targets. However, most state-of-the-art deep reinforcement learning (DRL) models depend on hard rewards to learn the optimal policy, which can lead to the lack of previous diverse experiences. Moreover, these pre-trained DRL models cannot generalize well to un-trained tasks. To overcome these problems above, in this paper, we propose a Memory-based Parameterized Skills Learning (MPSL) model for mapless visual navigation. The parameterized skills in our MPSL are learned to predict critic parameters for un-trained tasks in actor-critic reinforcement learning, which can be achieved by transferring memory sequence knowledge from long short term memory network. In order to generalize into un-trained tasks, MPSL aims to capture more discriminative features by using a scene-specific layer. Finally, experiment results on an indoor photographic simulation framework AI2THOR demonstrate the effectiveness of our proposed MPSL model, and the generalization ability to un-trained tasks.
产权排序	1
会议录	2019 IEEE International Conference on Image Processing (ICIP)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	2381-8549
ISBN号	978-1-5386-6249-6
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/26065]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Liu YY(刘宇阳)
作者单位	1.University of Chinese Academy of Sciences, 100049, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016, China 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China
推荐引用方式 GB/T 7714	Liu YY,Cong Y,Sun G. Memory-based Parameterized Skills Learning For Mapless Visual Navigation[C]. 见:. Taipei, Taiwan. September 22-25, 2019.