BAM! Base Abstracted Modeling with Universal Notice Network: Fast Skill Transfer Between Mobile Manipulators - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

BAM! Base Abstracted Modeling with Universal Notice Network: Fast Skill Transfer Between Mobile Manipulators

Mehdi Mounsif
  • Function : Author
Sebastien Lengagne
Benoit Thuilot

Abstract

Following recent trends, it appears that robot presence within human day-today lives is likely to grow and become ubiquitous. As many actors are engaged in this automation effort, it is plausible that the various cultural backgrounds of these actors will result in a broad range of different robots that will nevertheless need to perform similar tasks. Due to the excessively large number of experiences samples needed to successfully train a learning-based control policy, it would be remarkably useful to be able to efficiently transfer the skills acquired by a given agent to other, structurally distinct, robots. Accordingly, the BAM (Base-Abstracted Modeling) methodology proposed in this paper is a fast transfer learning approach that relies on a clear segmentation between the task model, that is a learned policy for solving a specific task and the learned robot control policy. The evaluation on two manipulation tasks using twelve different configurations of mobile manipulators demonstrates the strong potential of this approach as the segmentation results for more robust policies than naive methods and that an efficient transfer can be done in a fraction of the initial training time.
Fichier principal
Vignette du fichier
codit_vfinale.pdf (2.18 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02947365 , version 1 (06-12-2020)

Identifiers

Cite

Mehdi Mounsif, Sebastien Lengagne, Benoit Thuilot, Lounis Adouane. BAM! Base Abstracted Modeling with Universal Notice Network: Fast Skill Transfer Between Mobile Manipulators. 7th International Conference on Control, Decision and Information Technologies (CoDIT 2020), Jun 2020, Prague, Czech Republic. pp.926-932, ⟨10.1109/CoDIT49905.2020.9263931⟩. ⟨hal-02947365⟩
78 View
107 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More