SemGrasp: Semantic Grasp Generation via Language Aligned Discretization
This addresses the limitation of prior grasp generation methods in downstream tasks by enabling semantic-aware grasps, representing an incremental improvement in robotics and human-computer interaction.
The paper tackles the problem of generating human grasps by incorporating semantic information, not just object geometry, and introduces SemGrasp, which uses a language-aligned discrete representation to produce grasp poses based on instructions, achieving efficient generation aligned with linguistic intentions.
Generating natural human grasps necessitates consideration of not just object geometry but also semantic information. Solely depending on object shape for grasp generation confines the applications of prior methods in downstream tasks. This paper presents a novel semantic-based grasp generation method, termed SemGrasp, which generates a static human grasp pose by incorporating semantic information into the grasp representation. We introduce a discrete representation that aligns the grasp space with semantic space, enabling the generation of grasp postures in accordance with language instructions. A Multimodal Large Language Model (MLLM) is subsequently fine-tuned, integrating object, grasp, and language within a unified semantic space. To facilitate the training of SemGrasp, we have compiled a large-scale, grasp-text-aligned dataset named CapGrasp, featuring about 260k detailed captions and 50k diverse grasps. Experimental findings demonstrate that SemGrasp efficiently generates natural human grasps in alignment with linguistic intentions. Our code, models, and dataset are available publicly at: https://kailinli.github.io/SemGrasp.