COTRATE is an online self-supervised framework that uses proprioceptive terrain assessment to supervise visual traversability estimation with alignment loss and diversity-aware replay for continual robot-agnostic learning.
Salon: Self-supervised adaptive learning for off-road navigation,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A robotics framework combines VLMs and kernel regression for online learning from embodiment-specific disturbances to enable better adaptation in unstructured environments.
citing papers explorer
-
Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
COTRATE is an online self-supervised framework that uses proprioceptive terrain assessment to supervise visual traversability estimation with alignment loss and diversity-aware replay for continual robot-agnostic learning.
-
Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
A robotics framework combines VLMs and kernel regression for online learning from embodiment-specific disturbances to enable better adaptation in unstructured environments.