English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Knowledge of interaction forces during teleoperated robot-assisted surgerycould be used to enable force feedback to human operators and evaluate tissuehandling skill. However, direct force sensing at the end-effector ischallenging because it requires biocompatible, sterilizable, and cost-effectivesensors. Vision-based deep learning using convolutional neural networks is apromising approach for providing useful force estimates, though questionsremain about generalization to new scenarios and real-time inference. Wepresent a force estimation neural network that uses RGB images and robot stateas inputs. Using a self-collected dataset, we compared the network to variantsthat included only a single input type, and evaluated how they generalized tonew viewpoints, workspace positions, materials, and tools. We found thatvision-based networks were sensitive to shifts in viewpoints, while state-onlynetworks were robust to changes in workspace. The network with both state andvision inputs had the highest accuracy for an unseen tool, and was moderatelyrobust to changes in viewpoints. Through feature removal studies, we found thatusing only position features produced better accuracy than using only forcefeatures as input. The network with both state and vision inputs outperformed aphysics-based baseline model in accuracy. It showed comparable accuracy butfaster computation times than a baseline recurrent neural network, making itbetter suited for real-time applications.

Toward Force Estimation in Robot-Assisted Surgery using Deep Learning with Vision and Robot State