Modeling for robot task planning based on light-weighted Markov decision process

被引：0

作者：

Wang, Wenshan ^{[1
]}

Cao, Qixin ^{[1
]}

机构：

[1] Research Institute of Robotics, Shanghai Jiaotong University, Shanghai

来源：

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2015年 / 43卷

关键词：

Markov decision process; Modeling; Planning; Robot; Task; Uncertainty;

D O I：

10.13245/j.hust.15S1014

中图分类号：

学科分类号：

摘要：

To overcome the deficiencies of the classical planning model and the Markov Decision Process (MDP) model, a light-weighted Markov decision process (LMDP) model was proposed. This is a simplification of the MDP model, retains the uncertainty feature for realistic environment, and is able to handle large-scale problems by reducing the branching factor of state transitions. Besides, the convergence time is greatly reduced by initialization methods based on heuristic functions in classical planning domain. The planning method based on LMDP model was compared with the Prost planner, which is based on MDP model. The results show that using LMDP model, the planning efficiency is improved, and the planning results better adapt the physical world. ©, 2015, Huazhong University of Science and Technology. All right reserved.

引用

页码：58 / 61

页数：3

共 8 条

[1] Galindo C., Fernandez-Madrigal J.A., Gonzalez J., Et al., Robot task planning using semantic maps, Robotics and Autonomous Systems, 56, 11, pp. 955-966, (2008)
[2] Radaschin A., Voda A., Minca E., Et al., Task planning algorithm in hybrid assembly/disassembly process, Proc of 14th IFAC Symposium on Information Control Problems in Manufacturing, pp. 571-576, (2012)
[3] Sherwood R., Mishkin A., Chien S., Et al., An integrated planning and scheduling prototype for automated Mars rover command generation, Proc of Sixth European Conference on Planning, pp. 292-302, (2014)
[4] Loetzsch M., Risler M., Jungel M., XABSL-a pragmatic approach to behavior engineering, Proc of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5124-5129, (2006)
[5] Ghallab M., Nau D., Traverso P., Automated Planning: Theory and Practice, (2004)
[6] Barto A.G., Reinforcement Learning: An Introduction, (1998)
[7] Hoffmann J., Nebel B., The FF planning system: fast plan generation through heuristic search, Journal of Artificial Intelligence Research, 14, pp. 253-302, (2001)
[8] Keller T., Helmert M., Trial-based heuristic tree search for finite horizon MDPs, Proc of 23rd International Conference on Automated Planning and Scheduling, pp. 135-143, (2013)

← 1 →