A visual reinforcement-learning policy with a compact height-map observation and a dense 'delta' reward shapes granular media into target reliefs, outperforming heuristic baselines and transferring to a real robot in a single demonstration.
Au- tomated excavator based on reinforcement learning and multibody system dynamics,
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
unclear 1representative citing papers
citing papers explorer
-
Interactive Shaping of Granular Media Using Reinforcement Learning
A visual reinforcement-learning policy with a compact height-map observation and a dense 'delta' reward shapes granular media into target reliefs, outperforming heuristic baselines and transferring to a real robot in a single demonstration.