Tactile Object Recognition With Recurrent Neural Networks Through a Perceptive Soft Gripper

Soft robot perception integrates information from distributed, multi-modal sensors, broadening their application to active interaction. Our work introduces recurrent learning models for tactile-based object recognition, demonstrating comparable performance in virtual and real-world scenarios. The wo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 10; H. 7; S. 7023 - 7030
Hauptverfasser: Donato, Enrico, Pelliccia, David, Hosseinzadeh, Matin, Amiri, Mahmood, Falotico, Egidio
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.07.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Classification algorithms
Fingers
Grippers
Long short term memory
multi-modal integration
Object recognition
Recurrent neural networks
Robot sensing systems
Sensors
soft gripper
Soft robotics
Spatial distribution
Tactile sensing
Training
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Soft robot perception integrates information from distributed, multi-modal sensors, broadening their application to active interaction. Our work introduces recurrent learning models for tactile-based object recognition, demonstrating comparable performance in virtual and real-world scenarios. The work focuses on soft grippers, which facilitate adaptation to objects of varying shapes and sizes thanks to passive finger compliance. Our model successfully identifies over sixteen heterogeneous objects. Findings underscore the significance of sensory multi-modality over single. We highlight how spatial distribution and sensory signal dynamics influence overall estimation accuracy, and what the minimal grasp set is to achieve certain recognition.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2025.3572422