Online adaptation of robot dynamics via function encoders updated with recursive least squares enables real-time model learning from seconds of odometry data and reduces collisions versus static or meta-learning baselines.
How to learn and generalize from three minutes of data: Physics- constrained and uncertainty-aware neural stochastic dif- ferential equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Zero to Autonomy in Real-Time: Online Adaptation of Dynamics in Unstructured Environments
Online adaptation of robot dynamics via function encoders updated with recursive least squares enables real-time model learning from seconds of odometry data and reduces collisions versus static or meta-learning baselines.