POMDP Planning Under Object Composition Uncertainty: Application to Robotic Manipulation

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

2 Sitaatiot (Scopus)
80 Lataukset (Pure)

Abstrakti

Manipulating unknown objects in a cluttered environment is difficult because segmentation of the scene into objects, that is, object composition, is uncertain. Due to the uncertainty, prior work has either identified the "best" object composition and decided on manipulation actions accordingly or tried to greedily gather information about the "best" object composition. We instead, first, use different possible object compositions in planning, second, utilize object composition information provided by robot actions, third, consider the effect of competing object hypotheses on the desired task. We cast the manipulation planning problem as a partially observable Markov decision process (POMDP) that plans over possible object composition hypotheses. The POMDP chooses the action that maximizes long-term expected task-specific utility, and while doing so, considers informative actions and the effect of different object hypotheses on succeeding in the task. In simulation and physical robotic experiments, a probabilistic approach outperforms using the most likely object composition, and long term planning outperforms greedy decision making.

AlkuperäiskieliEnglanti
Sivut41-56
Sivumäärä16
JulkaisuIEEE Transactions on Robotics
Vuosikerta39
Numero1
Varhainen verkossa julkaisun päivämäärä20 heinäk. 2022
DOI - pysyväislinkit
TilaJulkaistu - 1 helmik. 2023
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Sormenjälki

Sukella tutkimusaiheisiin 'POMDP Planning Under Object Composition Uncertainty: Application to Robotic Manipulation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä