TU Darmstadt / ULB / TUprints

Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks

Veiga, Filipe ; Akrour, Riad ; Peters, Jan (2024)
Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks.
In: Frontiers in Robotics and AI, 2020, 7
doi: 10.26083/tuprints-00016159
Article, Secondary publication, Publisher's Version

Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (2MB) | Preview
Item Type: Article
Type of entry: Secondary publication
Title: Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks
Language: English
Date: 8 March 2024
Place of Publication: Darmstadt
Year of primary publication: 19 November 2020
Place of primary publication: Lausanne
Publisher: Frontiers Media S.A.
Journal or Publication Title: Frontiers in Robotics and AI
Volume of the journal: 7
Collation: 12 Seiten
DOI: 10.26083/tuprints-00016159
Corresponding Links:
Origin: Secondary publication DeepGreen

In-hand manipulation and grasp adjustment with dexterous robotic hands is a complex problem that not only requires highly coordinated finger movements but also deals with interaction variability. The control problem becomes even more complex when introducing tactile information into the feedback loop. Traditional approaches do not consider tactile feedback and attempt to solve the problem either by relying on complex models that are not always readily available or by constraining the problem in order to make it more tractable. In this paper, we propose a hierarchical control approach where a higher level policy is learned through reinforcement learning, while low level controllers ensure grip stability throughout the manipulation action. The low level controllers are independent grip stabilization controllers based on tactile feedback. The independent controllers allow reinforcement learning approaches to explore the manipulation tasks state-action space in a more structured manner. We show that this structure allows learning the unconstrained task with RL methods that cannot learn it in a non-hierarchical setting. The low level controllers also provide an abstraction to the tactile sensors input, allowing transfer to real robot platforms. We show preliminary results of the transfer of policies trained in simulation to the real robot hand.

Uncontrolled Keywords: tactile sensation and sensors, robotics, in-hand manipulation, hierarchical control, reinforcement learning
Identification Number: Artikel-ID: 521448
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-161591
Additional Information:

Specialty section: This article was submitted to Sensor Fusion and Machine Perception, a section of the journal Frontiers in Robotics and AI

Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
Date Deposited: 08 Mar 2024 13:19
Last Modified: 08 Mar 2024 13:19
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/16159
Actions (login required)
View Item View Item