Articulated Object Manipulation with Coarse-to-fine Affordance for Mitigating the Effect of Point Cloud Noise

TL;DR

This paper introduces a coarse-to-fine affordance learning method for manipulating 3D articulated objects using noisy real-world point clouds, improving robustness over existing approaches.

Contribution

It proposes a novel two-stage pipeline that leverages the property of noise reduction when closer to objects, enhancing affordance prediction in real-world noisy point clouds.

Findings

Outperforms existing methods in simulated noisy environments.

Effective in real-world manipulation scenarios.

Robustness to point cloud noise demonstrated.

Abstract

3D articulated objects are inherently challenging for manipulation due to the varied geometries and intricate functionalities associated with articulated objects.Point-level affordance, which predicts the per-point actionable score and thus proposes the best point to interact with, has demonstrated excellent performance and generalization capabilities in articulated object manipulation. However, a significant challenge remains: while previous works use perfect point cloud generated in simulation, the models cannot directly apply to the noisy point cloud in the real-world. To tackle this challenge, we leverage the property of real-world scanned point cloud that, the point cloud becomes less noisy when the camera is closer to the object. Therefore, we propose a novel coarse-to-fine affordance learning pipeline to mitigate the effect of point cloud noise in two stages. In the first stage, we learn the affordance on the noisy far point cloud which includes the whole object to propose the approximated place to manipulate. Then, we move the camera in front of the approximated place, scan a less noisy point cloud containing precise local geometries for manipulation, and learn affordance on such point cloud to propose fine-grained final actions. The proposed method is thoroughly evaluated both using large-scale simulated noisy point clouds mimicking real-world scans, and in the real world scenarios, with superiority over existing methods, demonstrating the effectiveness in tackling the noisy real-world point cloud problem.