Combined procedural generators yield 91.5% mean success for RL navigation policies across map types, A* subgoals raise it to 98.9%, and the policies outperform classical controllers at higher speeds with partial sim-to-real transfer.
2D Grid Map Generation for Deep-Learning-based Navigation Approaches,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Specialization: Robust Reinforcement Learning Navigation via Procedural Map Generators
Combined procedural generators yield 91.5% mean success for RL navigation policies across map types, A* subgoals raise it to 98.9%, and the policies outperform classical controllers at higher speeds with partial sim-to-real transfer.