QuadPiPS combines semantic affordance prediction with an egocentric legged egocan representation and trajectory optimization to produce kinodynamically feasible foothold plans that outperform baselines in limited-foothold settings and run on hardware.
Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
QuadPiPS: A Perception-informed Footstep Planner for Quadrupeds With Semantic Affordance Prediction
QuadPiPS combines semantic affordance prediction with an egocentric legged egocan representation and trajectory optimization to produce kinodynamically feasible foothold plans that outperform baselines in limited-foothold settings and run on hardware.