Autonomous Navigation with Improved Hierarchical Neural Network Based on Deep Reinforcement Learning
文献类型：会议论文
| 作者 | Zhang HY(张海莹); Qiu TH(丘滕海); Li SX(李书晓); Zhu CF(朱承飞); Lan XS(兰晓松); Chang HX(常红星); Zhu, Chengfei ; Qiu, Tenghai; Li, Shuxiao; Chang, Hongxing
|
| 出版日期 | 2019-07 |
| 会议日期 | 2019.07.27-2019.07.30 |
| 会议地点 | 中国 广州 |
| 关键词 | Autonomous Navigation DDPG Improved Hierarchical Neural Network Curriculum Learning |
| 英文摘要 | Compared with traditional navigation strategies in normal environments, the unmanned vehicles in battlefield environments require better navigation strategies. This research formulates the autonomous navigation in battlefield environments as a markov decision process (MDP) and introduces deep deterministic policy gradient (DDPG) to obtain the continuous control signal. Meanwhile, the curriculum learning is employed to increase utilization of samples in this research. Inspired by the biological mechanism, an improved hierarchical neural network is proposed to refine the input information, which plays a better role in coordinating the choice of agent’sbehavior.Experimental results show that the models we proposed are able to acquire effective navigation strategies without knowing the whole information of environment. At the same time, it is proved that the hierarchical neural network and the curriculum learning are effective for improving efficiency of learning and generalization capability of models. |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/39100]  |
| 专题 | 自动化研究所_综合信息系统研究中心 |
| 通讯作者 | Qiu TH(丘滕海); Qiu, Tenghai |
| 作者单位 | 中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Zhang HY,Qiu TH,Li SX,et al. Autonomous Navigation with Improved Hierarchical Neural Network Based on Deep Reinforcement Learning[C]. 见:. 中国 广州. 2019.07.27-2019.07.30. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。