RL-RRT learns an RL policy for local planning and a reachability estimator to guide RRT expansion, yielding faster kinodynamic planning than prior methods on three robot systems including hardware.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies
RL-RRT learns an RL policy for local planning and a reachability estimator to guide RRT expansion, yielding faster kinodynamic planning than prior methods on three robot systems including hardware.