Partially Observable Markov Decision Processes in Robotics: A Survey

TL;DR

This survey reviews how POMDPs are used in robotics to handle uncertainty in tasks like navigation, manipulation, and interaction, highlighting recent advances and future research directions.

Contribution

It bridges the gap between POMDP model development and practical robot applications, providing insights for both practitioners and algorithm designers.

Findings

POMDPs are effective in various robot decision tasks under uncertainty.

The survey identifies key task characteristics influencing POMDP application.

It suggests promising research directions for POMDP algorithms in robotics.

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 survey aims to bridge the gap between the development of POMDP models and algorithms at one end and application to diverse robot decision tasks at the other. It analyzes the characteristics of these tasks and connects them with the mathematical and algorithmic properties of the POMDP framework for effective modeling and solution. For practitioners, the survey provides some of the key task characteristics in deciding when and how to apply POMDPs to robot tasks successfully. For POMDP algorithm designers, the survey provides new insights into the unique challenges of applying POMDPs to robot systems and points to promising new directions for further research.