Projects per year
Abstract
Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot’s physical limits. These limits are especially relevant in dynamic manipulation where high velocities and accelerations are typical. To address this problem, we propose a framework that first maps a dynamic demonstration into a motion that respects the robot’s constraints using a constrained Dynamic Movement Primitive. Second, the resulting object state is further optimized by quasi-static refinement motions to optimize task performance metrics. This allows both efficiently altering the object state by dynamic motions and stable small-scale refinements. We evaluate the framework in the challenging task of bag opening, designing the system BILBO: Bimanual dynamic manipulation using Imitation Learning for Bag Opening. Our results show that BILBO can successfully open a wide range of crumpled bags, using a demonstration with a single bag. See supplementary material at https://sites.google.com/view/bilbo-bag.
Original language | English |
---|---|
Title of host publication | 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
Publisher | IEEE |
Pages | 12655-12662 |
Number of pages | 8 |
ISBN (Electronic) | 979-8-3503-7770-5 |
DOIs | |
Publication status | Published - 2024 |
MoE publication type | A4 Conference publication |
Event | IEEE/RSJ International Conference on Intelligent Robots and Systems - ADNEC, Abu Dhabi, United Arab Emirates Duration: 14 Oct 2024 → 18 Oct 2024 https://iros2024-abudhabi.org/ |
Publication series
Name | Proceedings of the International Conference on Intelligent Robots and Systems |
---|---|
ISSN (Electronic) | 2153-0866 |
Conference
Conference | IEEE/RSJ International Conference on Intelligent Robots and Systems |
---|---|
Abbreviated title | IROS |
Country/Territory | United Arab Emirates |
City | Abu Dhabi |
Period | 14/10/2024 → 18/10/2024 |
Internet address |
Keywords
- Imitation Learning
- Dynamic Manipulation
- Intelligent robots
Fingerprint
Dive into the research topics of 'Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints'. Together they form a unique fingerprint.Projects
- 1 Finished
-
SANTTU: Kumppanuusmalli - SANTTU - Aalto
Kyrki, V. (Principal investigator), Chaubey, S. (Project Member), Verdoja, F. (Project Member), Pekkanen, M. (Project Member), Nguyen Le, T. (Project Member), Arndt, K. (Project Member), Struckmeier, O. (Project Member), Hannus, E. (Project Member) & Blanco Mulero, D. (Project Member)
01/04/2022 → 31/03/2024
Project: Business Finland: Strategic centres for science, technology and innovation (SHOK)