Autonomous navigation of an over-actuated marine platform using reinforcement learning

被引：1

作者：

Tziortziotis, Konstantinos ^{[1
]}

Tziortziotis, Nikolaos ^{[2
]}

Vlachos, Kostas ^{[1
]}

Blekas, Konstantinos ^{[1
]}

机构：

[1] Univ Ioannina, Dept Comp Sci & Engn, Ioannina, Greece

[2] Ecole Polytech, Comp Sci Lab LIX, Paris, France

来源：

9TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE (SETN 2016) | 2016年

关键词：

Reinforcement Learning; Autonomous navigation; over-actuated marine vehicle;

D O I：

10.1145/2903220.2903254

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper investigates the use of reinforcement learning for the navigation of an over-actuated marine platform in unknown environments. The proposed approach uses an online least-squared policy iteration scheme for value function approximation in order to estimate optimal policy. We evaluate our approach in a simulation platform and report some initial results concerning its performance on estimating optimal navigation policies to unknown environments under different environmental disturbances. The results are promising.

引用

页数：7

共 21 条

[1] [Anonymous], 2003, J. Mach. Learn. Res.
[2] Antonelli G., 2014, UNDEDWATER ROBOTS, V96
[3] Busoniu L, 2010, P AMER CONTR CONF, P486
[4] A behavior-based scheme using reinforcement learning for autonomous underwater vehicles
Carreras, M
Yuh, J
Batlle, J
Ridao, P
[J]. IEEE JOURNAL OF OCEANIC ENGINEERING, 2005, 30 (02) : 416 - 427
[5] Engel Y., 2005, P 22 INT C MACHINE L, P201, DOI [10.1145/1102351.1102377, /10.1145/1102351.1102377]
[6] Fossen T.I., 1994, Guidance and Control of Ocean Vehicles
[7] Hoerner S.F., 1965, Fluid-Dynamic Drag
[8] Kawano H., 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, P996
[9] Konidaris George, 2011, P AAAI C ARTIFICIAL, P380385
[10] Li L., 2009, Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems, V2, P733

← 1 2 3 →