Robust Placeability Estimation for Model-Free Unified Pick-and-Place Reasoning

Benno Wingender, Nils Dengler, Rohit Menon, Sicong Pan, Maren Bennewitz

Keywords: Robust Manipulation Planning, Placement Planning, Object Stability

Abstract:

Reliable manipulation of previously unseen objects remains a fundamental challenge for autonomous robotic systems operating in unstructured environments.
In particular, robust pick-and-place planning directly from noisy and only partial real-world observations, where object surfaces are inherently incomplete due to occlusions is difficult.
As a result, many existing methods rely on strong object priors or assume placements on continuous, flat support surfaces such as planar tabletops, without explicitly accounting for edge proximity or inclined supports.
In this work, we introduce a robust probabilistic placeability metric that evaluates 6D object placement poses from partial observations, allowing the generation of diverse multi-orientation placement candidates and condition grasp scoring on these placements, enabling model-free unified pick-and-place reasoning.

Submission Number: 18