Compressing 10-step action chunks into discrete latent codes lets an 8B multimodal model drive a quadruped at controller frequency and raises average task success by about 65%.
Vinl: Visual navigation and locomotion over obstacles,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
Compressing 10-step action chunks into discrete latent codes lets an 8B multimodal model drive a quadruped at controller frequency and raises average task success by about 65%.