Skip to content

OPAL-Grasp: Object-Part Guided Alignment for Language-Driven Robotic Grasp Detection

Oct 2026 · IEEE Robotics and Automation Letters · Vol 11, pp. 11649-11656 · 0 citations · 30 references

Abstract

Language-Driven Grasp Detection aims to generate executable robotic grasp rectangles based on user instructions described in natural language and visual inputs. User commands typically specify not only the target object but also fine-grained constraints such as specific parts or functional regions. Most existing methods implicitly treat language as a whole rather than as structured semantic descriptions, limiting the ability of language to guide precise grasp generation. In this paper, we propose OPAL-Grasp, a novel end-to-end framework that explicitly learns object-level and part-level semantics to strengthen perceptual understanding. We design an Object-Part Guidance Module that uses joint object- and part-level segmentation supervision to learn fine-grained vision–language representations, with the object branch serving as auxiliary supervision and only part-aware features propagated to the grasp prediction module. A Grasp Imbalance-Aware Loss is introduced to reweight sparse yet critical grasp regions, thereby improving optimization stability and detection accuracy. Extensive experiments on large-scale language-driven grasp benchmarks and real-world robotic setups demonstrate that OPAL-Grasp achieves state-of-the-art performance and exhibits strong robustness and generalization across challenging scenes.

View source

Similar papers

2026

Efficient Mamba-Centered Global-Local Refinement for Language-Guided Visual Grounding in Robotic Grasping

Enabling robots to understand natural language and locate referred objects for grasping remains a key challenge. Language-guided visual grounding connects visual perception and language understanding. As a fine-grained setting, Referring Image Segmentation (RIS) further provides pixel-level masks, which are particularl...

Xiao-Zheng Liu, Ke-Chen Song, Zeng-Lin Xu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

HiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path Planning

This paper describes the original point-based formulation of the framework and its relationship to the subsequent GeneralVLA extension, and describes the original point-based formulation of the framework's relationship to the subsequent GeneralVLA extension.

Guo-Qing Ma, Ming-Qi Yuan, Chen Gao et al. · 0 citations
Preprint Aug 2026

Gripper-aware Vision Language Action Models

This work introduces MiGA, a multi-gripper-aware dataset spanning five distinct gripper types across multiple robots with 103,000 demonstrations, and proposes GVLA, which combines a new multi-gripper tokenizer with adapter-based policy routing that improves zero-shot generalization or few-shot adaptation to new objects...

Hanyi Zhang, Zihong Luo, Tianyu Li et al. · 1 citation
Conference Open access Aug 2026

VLEG: Embodied Vision-Language Grasping for a Quadruped Manipulator

This paper presents VLEG, an embodied vision-language grasping framework for quadruped manipulators that explicitly incorporates body motion into grasp decision making and guides the robot to continuously adjust its body pose during approach and optimize local observations before grasping, thereby improving perception...

Yu-Xing Ji, Fei Meng, Zishang Ji et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis

The results indicate that decoupling physical grasp synthesis from task-dependent understanding provides a scalable paradigm for robotic grasping, allowing future advances in foundation models to be directly translated into improved grasp capabilities without redesigning or retraining the underlying grasp policy.

Si-Xu Yan, Shi-Kang Wang, Bin-Hua Huang et al. · 1 citation
Sep 2026

ArtManip: Category-Level Articulated In-Hand Manipulation

This work presents ArtManip, the first category-level articulated in-hand manipulation method that generalizes across object instances and diverse initial grasps and proposes a robust two-stage training strategy that incorporates articulation physics randomization, reward curriculum, and latent representation distillat...

Yang Yang, Teng-Yu Liu, Pu-Hao Li et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.