To bridge the gap between semantic AI and industrial reliability, this thesis proposes an architecture that decouples high-level Vision-Language reasoning from deterministic motion control. Validated through an automated benchmark in NVIDIA Isaac Sim, it enables safe zero-shot manipulation by preemptively blocking infeasible actions.
To bridge the gap between semantic AI and industrial reliability, this thesis proposes an architecture that decouples high-level Vision-Language reasoning from deterministic motion control. Validated through an automated benchmark in NVIDIA Isaac Sim, it enables safe zero-shot manipulation by preemptively blocking infeasible actions.
EMBODIED REASONING AND DETERMINISTIC MOTION PLANNING FOR ZERO-SHOT ROBOTIC PICK-AND-PLACE
CANTARO, GIADA
2025/2026
Abstract
To bridge the gap between semantic AI and industrial reliability, this thesis proposes an architecture that decouples high-level Vision-Language reasoning from deterministic motion control. Validated through an automated benchmark in NVIDIA Isaac Sim, it enables safe zero-shot manipulation by preemptively blocking infeasible actions.| File | Dimensione | Formato | |
|---|---|---|---|
|
CantaroGiadaTesi.pdf
non disponibili
Descrizione: Tesi di Laurea Magistrale in Ingegneria Informatica (Elaborato soggetto a secretazione/NDA)
Dimensione
6.89 MB
Formato
Adobe PDF
|
6.89 MB | Adobe PDF |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14253/110793