GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions

TL;DR

GraspALL is a novel adaptive model that compensates for illumination variations by fusing RGB and non-RGB features, significantly improving garment grasping robustness in low-light conditions for service robots.

Contribution

It introduces an illumination-structure interactive compensation mechanism that adaptively fuses multimodal features based on continuous lighting changes, enhancing grasping accuracy.

Findings

Improves grasping accuracy by 32-44% under diverse lighting conditions.

Effectively encodes illumination changes to guide adaptive feature fusion.

Demonstrates robustness in low-light garment grasping scenarios.

Abstract

Achieving accurate garment grasping under dynamically changing illumination is crucial for all-day operation of service robots.However, the reduced illumination in low-light scenes severely degrades garment structural features, leading to a significant drop in grasping robustness.Existing methods typically enhance RGB features by exploiting the illumination-invariant properties of non-RGB modalities, yet they overlook the varying dependence on non-RGB features under varying lighting conditions, which can introduce misaligned non-RGB cues and thereby weaken the model's adaptability to illumination changes when utilizing multimodal information.To address this problem, we propose GraspALL, an illumination-structure interactive compensation model.The innovation of GraspALL lies in encoding continuous illumination changes into quantitative references to guide adaptive feature fusion between RGB and non-RGB modalities according to varying lighting intensities, thereby generating illumination-consistent grasping representations.Experiments on the self-built garment grasping dataset demonstrate that GraspALL improves grasping accuracy by 32-44% over baselines under diverse illumination conditions.