SCP integrates diffusion-based imitation learning with Gaussian-encoded surface constraints and dynamic movement primitives to generate actions with improved success rates and contact stability on free-form surfaces.
Learning a High-quality Robotic Wiping Policy Using Systematic Reward Analysis and Visual-Language Model Based Curriculum[J]
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
-
Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills
SCP integrates diffusion-based imitation learning with Gaussian-encoded surface constraints and dynamic movement primitives to generate actions with improved success rates and contact stability on free-form surfaces.