A behavior control method based on hierarchical POMDP for intelligent wheelchair
A behavior control method based on hierarchical POMDP for intelligent wheelchair
复制标题
DOI：
10.1109/aim.2009.5229898
复制
发表时间：
2009-07
期刊：
影响因子：
--
通讯作者：
Yong Tao;Tianmiao Wang;Hongxing Wei;Diansheng Chen
中科院分区：
文献类型：
--
作者：
Yong Tao;Tianmiao Wang;Hongxing Wei;Diansheng Chen
描述了一种智能轮椅在不确定环境中的行为控制方法。介绍了智能轮椅，给出了部分可观决策过程(POMDP)的模型和原理。提出了一种层次化的POMDP模型，该模型将决策过程分解为一组可以更有效地完成的小过程。该模型可以同时考虑状态转换和观测不确定性。在智能轮椅上实现了基于层次化POMDP的行为控制方法，并在交互服务任务中进行了测试。在辅助生活设施进行的实验过程中，智能轮椅成功地展示了它可以自主地为用户提供服务和信息。
This paper describes a behavior control method for intelligent wheelchair in uncertain environments. The intelligent wheelchair is introduced, and the model and principle of Partially Observable Decision Process (POMDP) are given. A hierarchical POMDP model is proposed, which decomposes the decision making process into a set of small ones that can be done more efficiently. The model can account for both state transition and observation uncertainty. This behavior control method based on hierarchical POMDP is implemented and tested onboard an intelligent wheelchair in the context of an interactive service task. During the course of experiments conducted in an assisted living facility, the intelligent wheelchair successfully demonstrated that it could autonomously provide service and information to the users.