Skip to Main content Skip to Navigation
Conference papers

Learning to combine primitive skills: A step towards versatile robotic manipulation

Robin Strudel 1, 2 Alexander Pashevich 3 Igor Kalevatykh 1, 2 Ivan Laptev 1, 2 Josef Sivic 1, 2 Cordelia Schmid 3
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria de Paris
3 Thoth [2020-....] - Apprentissage de modèles à partir de données massives [2020-....]
Inria Grenoble - Rhône-Alpes, LJK [2020-....] - Laboratoire Jean Kuntzmann [2020-....]
Abstract : Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve complex tasks but require full state observability and are not adapted to dynamic scene changes. Recent learning methods can operate directly on visual inputs but typically require many demonstrations and/or task-specific reward engineering. In this work we aim to overcome previous limitations and propose a reinforcement learning (RL) approach to task planning that learns to combine primitive skills. First, compared to previous learning methods, our approach requires neither intermediate rewards nor complete task demonstrations during training. Second, we demonstrate the versatility of our vision-based task planning in challenging settings with temporary occlusions and dynamic scene changes. Third, we propose an efficient training of basic skills from few synthetic demonstrations by exploring recent CNN architectures and data augmentation. Notably, while all of our policies are learned on visual inputs in simulated environments, we demonstrate the successful transfer and high success rates when applying such policies to manipulation tasks on a real UR5 robotic arm.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02274969
Contributor : Alexander Pashevich <>
Submitted on : Friday, August 30, 2019 - 1:26:02 PM
Last modification on : Tuesday, September 22, 2020 - 3:57:44 AM

Links full text

Identifiers

  • HAL Id : hal-02274969, version 1
  • ARXIV : 1908.00722

Collections

Citation

Robin Strudel, Alexander Pashevich, Igor Kalevatykh, Ivan Laptev, Josef Sivic, et al.. Learning to combine primitive skills: A step towards versatile robotic manipulation. ICRA 2020 - IEEE International Conference on Robotics and Automation, May 2020, Paris / Virtuel, France. ⟨hal-02274969⟩

Share

Metrics

Record views

274