A single neural-network policy, trained in simulation, makes a humanoid climb, vault, and traverse uneven terrain from onboard depth and a velocity command, with no skill labels or runtime motion graphs.
Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Light-Loco-Parkour: Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation
A single neural-network policy, trained in simulation, makes a humanoid climb, vault, and traverse uneven terrain from onboard depth and a velocity command, with no skill labels or runtime motion graphs.