期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 31, 期 4, 页码 948-961出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2015.2441511
关键词
Autonomous vehicles; partially observable Markov decision process (POMDP); plan execution; robotics; uncertainty
类别
资金
- NSF [1139011, IIS 1317849]
- U.S. Army Research Laboratory
- U.S. Army Research Office [W911NF-09-1-0383]
- Data Analysis and Visualization Cyberinfrastructure - NSF [OCI-0959097]
- NSF
- Direct For Computer & Info Scie & Enginr [1317849] Funding Source: National Science Foundation
Partially observable Markov decision processes (POMDPs) are used in many robotic task classes from soccer to household chores. Determining an approximately optimal action policy for POMDPs is PSPACE-complete, and the exponential growth of computation time prohibits solving large tasks. This paper describes two techniques to extend the range of robotic tasks that can be solved using a POMDP. Our first technique reduces the motion constraints of a robot and, then, uses state-of-the-art robotic motion planning techniques to respect the true motion constraints at runtime. We then propose a novel task decomposition that can be applied to some indoor robotic tasks. This decomposition transforms a long time horizon task into a set of shorter tasks. We empirically demonstrate the performance gain provided by these two techniques through simulated execution in a variety of environments. Comparing a direct formulation of a POMDP to solving our proposed reductions, we conclude that the techniques proposed in this paper can provide significant enhancement to current POMDP solution techniques, extending the POMDP instances that can be solved to include large continuous-state robotic tasks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据