This doctoral thesis addresses the development of novel methodologies and technologies for artificial tactile perception and haptic feedback in robotic systems, with particular emphasis on medical and surgical applications. Starting from the study of the principles underlying the human sense of touch, this work proposes approaches inspired by biological perceptual mechanisms to identify efficient tactile representations that can be transferred to artificial systems. The research introduces innovative frameworks for object compliance estimation using vision-based soft tactile sensors, exploiting perceptually relevant descriptors such as tactile flow and contact area variation, combined with active exploration strategies, adaptive control, and machine learning techniques. In parallel, a wearable haptic device for the delivery of tactile information through cutaneous stimulation is developed and validated. The device is capable of reproducing perceptual attributes such as softness and sliding, while implementing a feel-through paradigm that enables the modulation of tactile perception during interaction with real objects. The proposed technologies are integrated into robotic platforms for telepalpation and surgical simulation, demonstrating the potential of combining tactile sensing, haptic feedback, and intelligent control to enhance human–robot interaction. The results contribute to the development of robotic systems with advanced perceptual and adaptive capabilities, supporting the evolution of medical robotics toward safer, more intuitive, and more effective solutions.
HUMAN-INSPIRED TACTILE SENSING AND FEEDBACK FOR EXTENDED REALITY AND ROBOTICS-ENABLED MEDICAL APPLICATIONS
PAGNANELLI, GIULIA
2026
Abstract
This doctoral thesis addresses the development of novel methodologies and technologies for artificial tactile perception and haptic feedback in robotic systems, with particular emphasis on medical and surgical applications. Starting from the study of the principles underlying the human sense of touch, this work proposes approaches inspired by biological perceptual mechanisms to identify efficient tactile representations that can be transferred to artificial systems. The research introduces innovative frameworks for object compliance estimation using vision-based soft tactile sensors, exploiting perceptually relevant descriptors such as tactile flow and contact area variation, combined with active exploration strategies, adaptive control, and machine learning techniques. In parallel, a wearable haptic device for the delivery of tactile information through cutaneous stimulation is developed and validated. The device is capable of reproducing perceptual attributes such as softness and sliding, while implementing a feel-through paradigm that enables the modulation of tactile perception during interaction with real objects. The proposed technologies are integrated into robotic platforms for telepalpation and surgical simulation, demonstrating the potential of combining tactile sensing, haptic feedback, and intelligent control to enhance human–robot interaction. The results contribute to the development of robotic systems with advanced perceptual and adaptive capabilities, supporting the evolution of medical robotics toward safer, more intuitive, and more effective solutions.| File | Dimensione | Formato | |
|---|---|---|---|
|
01_PhD_Thesis.pdf
embargo fino al 13/07/2029
Licenza:
Tutti i diritti riservati
Dimensione
99.3 MB
Formato
Adobe PDF
|
99.3 MB | Adobe PDF |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14242/385757
URN:NBN:IT:UNIPI-385757