Affordance-Driven Next-Best-View Planning for Robotic Grasping

TL;DR

This paper presents ACE-NBV, a novel view planning policy that improves robotic grasping of occluded objects by selecting viewpoints that enhance affordance measurement, validated through simulation and real robot experiments.

Contribution

Introduces an affordance-driven next-best-view planning policy that predicts grasp affordances from unobserved views to improve robotic manipulation in cluttered environments.

Findings

Effective in simulation and real robot experiments

Improves grasp success rate in occluded scenarios

Outperforms baseline view planning methods

Abstract

Grasping occluded objects in cluttered environments is an essential component in complex robotic manipulation tasks. In this paper, we introduce an AffordanCE-driven Next-Best-View planning policy (ACE-NBV) that tries to find a feasible grasp for target object via continuously observing scenes from new viewpoints. This policy is motivated by the observation that the grasp affordances of an occluded object can be better-measured under the view when the view-direction are the same as the grasp view. Specifically, our method leverages the paradigm of novel view imagery to predict the grasps affordances under previously unobserved view, and select next observation view based on the highest imagined grasp quality of the target object. The experimental results in simulation and on a real robot demonstrate the effectiveness of the proposed affordance-driven next-best-view planning policy. Project page: https://sszxc.net/ace-nbv/.