An incremental Koopman algorithm that grows both dataset and latent dimension enables linear-MPC walking on five simulated legged robots, but its monotonic convergence theorem assumes the learned embedding is already the true eigenfunction basis.
These hyperparameters are selected when the robot is on the verge of falling and entering an unrecoverable state
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual Learning and Lifting of Koopman Dynamics for Linear Control of Legged Robots
An incremental Koopman algorithm that grows both dataset and latent dimension enables linear-MPC walking on five simulated legged robots, but its monotonic convergence theorem assumes the learned embedding is already the true eigenfunction basis.