A hierarchical reinforcement learning framework lets a quadruped robot automatically switch between trotting, bounding, galloping, and fall recovery based on distance to the goal, with switch distances tuned by CMA-ES.
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
-
Discovery of skill switching criteria for learning agile quadruped locomotion
A hierarchical reinforcement learning framework lets a quadruped robot automatically switch between trotting, bounding, galloping, and fall recovery based on distance to the goal, with switch distances tuned by CMA-ES.