A single reinforcement-learned controller uses masked motion demonstrations to catch up, combine, and complete humanoid motions from sparse multi-modal directives.
ACM SIGGRAPH 2023 Conference Proceedings (2023)
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
-
Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs
A single reinforcement-learned controller uses masked motion demonstrations to catch up, combine, and complete humanoid motions from sparse multi-modal directives.