An end-to-end reinforcement learning controller with attention-based map encoding achieves precise, robust, generalized locomotion on sparse terrains for quadruped and humanoid robots.
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
-
Attention-Based Map Encoding for Learning Generalized Legged Locomotion
An end-to-end reinforcement learning controller with attention-based map encoding achieves precise, robust, generalized locomotion on sparse terrains for quadruped and humanoid robots.