Ahmad Rahmanijavinani
Data-Driven Dynamic Control of a Soft Robot for Pick and Throw Tasks.
Rel. Alessandro Rizzo, Egidio Falotico, Daniele Somma, Diego Bianchi. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2026
|
|
PDF (Tesi_di_laurea)
- Tesi
Accesso limitato a: Solo utenti staff fino al 27 Marzo 2027 (data di embargo). Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (13MB) |
Abstract
Soft robotic manipulators offer distinctive advantages over rigid counterparts, providing inherent safety, mechanical compliance, and adaptability that make them ideal for complex environments and safe human-robot interaction (HRI). However, their continuous, viscoelastic nature and theoretically infinite degrees of freedom pose significant challenges for conventional analytical modeling and control techniques. Traditional kinematic and dynamic models are based on simplifying assumptions and often fail to capture the highly nonlinear, time dependent behaviors and hysteresis inherent to soft materials, thus limiting the robot’s ability to perform highly dynamic tasks such as ballistic throwing, which could vastly extend its effective workspace. Ballistic throwing, is crucial for reducing cycle times and extending the effective operational workspace of the robot beyond its physical reach.
This thesis proposes a data driven, model free approach to achieve accurate "pick and place" and "pick and throw" operations using a simulated soft robotic arm
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
