We introduce a soft-tissue simulation framework that replicates the preliminary steps of partial nephrectomy procedure. Furthermore, we show that an end-to-end reinforcement learning algorithm can be trained in the simulation without any user demonstration to accomplish a tissue manipulation task. To the best of our knowledge, this is one of the first attempts of using DRL agents to manipulate soft tissues for autonomous surgical action execution.
Framework for soft tissue manipulation and control using Deep Reinforcement Learning
Ameya Pore
;Eleonora Tagliabue;Diego Dall’Alba;Paolo Fiorini
In corso di stampa
Abstract
We introduce a soft-tissue simulation framework that replicates the preliminary steps of partial nephrectomy procedure. Furthermore, we show that an end-to-end reinforcement learning algorithm can be trained in the simulation without any user demonstration to accomplish a tissue manipulation task. To the best of our knowledge, this is one of the first attempts of using DRL agents to manipulate soft tissues for autonomous surgical action execution.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
