SRDrone combines continuous state evaluation with hierarchical Behavior Tree repair so that LLM-based drone planners can autonomously refine their own plans after failures.
Countering reward over-optimization in LLM with demonstration-guided reinforcement learning,
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
-
LLM-Driven Self-Refinement for Embodied Drone Task Planning
SRDrone combines continuous state evaluation with hierarchical Behavior Tree repair so that LLM-based drone planners can autonomously refine their own plans after failures.