Skip to main navigation Skip to search Skip to main content

Learning Model Preconditions for Planning with Multiple Models

  • Carnegie Mellon University

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations

Abstract

Different models can provide differing levels of fidelity when a robot is planning. Analytical models are often fast to evaluate but only work in limited ranges of conditions. Meanwhile, physics simulators are effective at modeling complex interactions between objects but are typically more computationally expensive. Learning when to switch between the various models can greatly improve the speed of planning and task success reliability. In this work, we learn model deviation estimators (MDEs) to predict the error between real-world states and the states outputted by transition models. MDEs can be used to define a model precondition that describes which transitions are accurately modeled. We then propose a planner that uses the learned model preconditions to switch between various models in order to use models in conditions where they are accurate, prioritizing faster models when possible. We evaluate our method on two real-world tasks: placing a rod into a box and placing a rod into a closed drawer.

Original languageEnglish
Pages (from-to)491-500
Number of pages10
JournalProceedings of Machine Learning Research
Volume164
StatePublished - 2021
Event5th Conference on Robot Learning, CoRL 2021 - London, United Kingdom
Duration: 8 Nov 202111 Nov 2021

Keywords

  • manipulation
  • planning

Fingerprint

Dive into the research topics of 'Learning Model Preconditions for Planning with Multiple Models'. Together they form a unique fingerprint.

Cite this