Using object affordance maps as priors and constraints improves success rates of dexterous manipulation RL policies by an average of 15.4% in simulation.
Learning generalizable dexterous manipulation from human grasp affordance,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic Manipulation
Using object affordance maps as priors and constraints improves success rates of dexterous manipulation RL policies by an average of 15.4% in simulation.