2023
DOI: 10.1109/tro.2022.3200138
|View full text |Cite
|
Sign up to set email alerts
|

Partially Observable Markov Decision Processes in Robotics: A Survey

Abstract: Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) provides a principled mathematical framework for modeling and solving robot decision and control tasks under uncertainty. Over the last decade, it has seen many successful applications, spanning localization and navigation, search and tracking, autonomous driving, multi-robot systems, manipulation, and human-robot interaction. This surve… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
18
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 60 publications
(18 citation statements)
references
References 157 publications
0
18
0
Order By: Relevance
“…Another strategy that can be used to reduce the per-update communications overhead of a distributed network is by using a Partially Observable Markov Decision Process (POMDP) [102]. Instead of requiring the agents to fully observe the environment in each time step, action selection for each agent is based on a probability distribution given by the model instead of directly observing the underlying state.…”
Section: B Research Opportunitiesmentioning
confidence: 99%
“…Another strategy that can be used to reduce the per-update communications overhead of a distributed network is by using a Partially Observable Markov Decision Process (POMDP) [102]. Instead of requiring the agents to fully observe the environment in each time step, action selection for each agent is based on a probability distribution given by the model instead of directly observing the underlying state.…”
Section: B Research Opportunitiesmentioning
confidence: 99%
“…5.2) Sequential decision-making models are often embedded in larger systems. Often, MDPs are part of a larger system, such as a robot [4,40,136,214], and it may be challenging to write a reward function that represents its high-level task, which may be a mixture of several objectives. Thus, we often evaluate these decisionmaking models using a task-based metric [4,45,134,200,209].…”
Section: System Evaluation and Measurementmentioning
confidence: 99%
“…Localization uncertainty can arise from perceptual degradation (Ebadi et al, 2020), noisy actuation (Thrun 2002), and inaccurate modeling (Roy et al, 1999). Decision-making or planning under uncertainty (LaValle 2006; Bry and Roy 2011; Preston et al, 2022) provides an elegant framework to formulate these problems using partially observable Markov decision processes (POMDPs) (Kaelbling et al, 1998; Cai et al, 2021; Lauri et al, 2022). A principled approach to address these problems is to plan in the belief space (Kaelbling and Lozano-Pérez 2013; Nishimura and Schwager 2021).…”
Section: Related Workmentioning
confidence: 99%