A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.
First, we process the output tra- jectories into videos and compute the appropriate frame rate to generate video sequences equivalent to 15 frames per trajectory pair
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields
A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.