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

2026-03-15

AI Summary

This work addresses the significant degradation of garment structural features under low-light conditions, which severely undermines robotic grasping robustness. Existing approaches overlook the dynamic impact of illumination variations on the reliance of non-RGB modalities within multimodal fusion frameworks. To overcome this limitation, we propose a lighting-structure interaction compensation model that encodes continuous illumination intensity as a quantitative guidance signal to drive adaptive fusion between RGB and non-RGB modalities according to ambient lighting conditions, thereby generating illumination-consistent grasping representations. Integrating multimodal perception, quantified illumination encoding, and deep learning–based grasping policies, our method substantially outperforms baseline approaches on a newly curated garment grasping dataset, achieving 32%–44% higher grasping accuracy across diverse low-light environments and significantly enhancing model generalization.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• garment grasping
• illumination variation
• low-light conditions
• multimodal fusion
• structural features

Innovation

• adaptive feature fusion
• illumination-structure interaction
• multimodal compensation
• low-light grasping
• garment manipulation