Robotic manipulation of multiple objects as a POMDP

Joni Pajarinen*, Ville Kyrki

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

8 Citations (Scopus)
177 Downloads (Pure)

Abstract

This paper investigates manipulation of multiple unknown objects in a crowded environment. Because of incomplete knowledge due to unknown objects and occlusions in visual observations, object observations are imperfect and action success is uncertain, making planning challenging. We model the problem as a partially observable Markov decision process (POMDP), which allows a general reward based optimization objective and takes uncertainty in temporal evolution and partial observations into account. In addition to occlusion dependent observation and action success probabilities, our POMDP model also automatically adapts object specific action success probabilities. To cope with the changing system dynamics and performance constraints, we present a new online POMDP method based on particle filtering that produces compact policies. The approach is validated both in simulation and in physical experiments in a scenario of moving dirty dishes into a dishwasher. The results indicate that: 1) a greedy heuristic manipulation approach is not sufficient, multi-object manipulation requires multi-step POMDP planning, and 2) on-line planning is beneficial since it allows the adaptation of the system dynamics model based on actual experience.

Original languageEnglish
Pages (from-to)213-228
Number of pages16
JournalArtificial Intelligence
Volume247
DOIs
Publication statusPublished - 2017
MoE publication typeA1 Journal article-refereed

Keywords

  • Cluttered environment
  • Manipulation
  • Multiple objects
  • Planning under uncertainty
  • POMDP
  • Task planning
  • Unknown objects

Fingerprint Dive into the research topics of 'Robotic manipulation of multiple objects as a POMDP'. Together they form a unique fingerprint.

Cite this