Reusing the entire previous subtree in receding horizon tree search improves sample efficiency and final planning performance for real-time robot control, demonstrated on a nonprehensile manipulation task.
Improved monte-carlo search,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Model Predictive Trees: Sample-Efficient Receding Horizon Planning with Reusable Tree Search
Reusing the entire previous subtree in receding horizon tree search improves sample efficiency and final planning performance for real-time robot control, demonstrated on a nonprehensile manipulation task.