EndoVLA-OOV: Language-Conditioned Out-of-View Target Acquisition in Robotic Endoscopy
EndoVLA-OOV: Language-Conditioned Out-of-View Target Acquisition in Robotic Endoscopy
This research presents EndoVLA-OOV, a vision-language-action policy for robotic endoscopy that translates anatomical descriptions into camera motions. The policy uses a pretrained backbone adapted to continuous distal bending commands and combines images to guide search. An open-source dataset with 1,050 episodes and 262k observation-action pairs supports policy learning. Physical evaluations show 93.3% success in cross-embodiment transfer, with success rates improving from 40.0% to 90.0% with more training data.
The paper introduces EndoVLA-OOV, a language-conditioned policy for robotic endoscopy that enables out-of-view target acquisition. It demonstrates improved success rates with more training data and cross-embodiment transfer to an ex-vivo environment.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
episodes
1,050 episodes
View original evidence
ioned vision-language-action policy for out-of-view target acquisition in robotic endoscopy. The policy adapts a pretrained backbone to continuous two-degree-of-freedom distal bending commands and combines initial, intermediate, and current images to guide search. To support policy learning, we provide an open-source VLA dataset containing 1,050 episodes across six tasks and approximately 262k observation-action pair
Open source S3observation-action pairs
≈262,000
View original evidence
ioned vision-language-action policy for out-of-view target acquisition in robotic endoscopy. The policy adapts a pretrained backbone to continuous two-degree-of-freedom distal bending commands and combines initial, intermediate, and current images to guide search. To support policy learning, we provide an open-source VLA dataset containing 1,050 episodes across six tasks and approximately 262k observation-action pair
Open source S3
- code: not_reported
- dataset: not_reported
- paper: not_reported
- weights: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
s. Physical evaluation spans wet-lens and low-light conditions, two unseen stomach phantoms, and cross-embodiment transfer to an unseen ex-vivo environment. In the cross-embodiment evaluation, the full-data policy achieves 93.3% target acquisition success (28/30). In a controlled training-data comparison, expanding the corpus from 312 to 1,050 episodes increases acquisition success from 40.0% to 90.0% under the same
Open source S4
ioned vision-language-action policy for out-of-view target acquisition in robotic endoscopy. The policy adapts a pretrained backbone to continuous two-degree-of-freedom distal bending commands and combines initial, intermediate, and current images to guide search. To support policy learning, we provide an open-source VLA dataset containing 1,050 episodes across six tasks and approximately 262k observation-action pair
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org