A modular ATACOM safety layer is added to robot foundation models pi0 and OCTO, yielding provably safe actions with minimal performance loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Safe Robot Foundation Models Using Inductive Biases
A modular ATACOM safety layer is added to robot foundation models pi0 and OCTO, yielding provably safe actions with minimal performance loss.