Robotic grasping is a fundamental skill required for object manipulation in robotics. Multi-fingered robotic hands, which mimic the structure of the human hand, can potentially perform complex object manipulations. Nevertheless, current techniques for multi-fingered robotic grasping frequently predict only a single grasp for each inference time, limiting their versatility and efficiency. This paper proposes a differentiable multi-fingered grasp generation network (DMFC-GraspNet) with two main contributions to address this challenge. Firstly, a novel neural grasp planner is proposed, which predicts a new grasp representation to enable versatile and dense grasp predictions. Secondly, a scene creation and label mapping method is developed for dense labeling of multi-fingered robotic hands, which allows a dense association of ground truth grasps. The proposed approach is evaluated through simulation studies and compared to existing approaches. The results demonstrate the effectiveness of the proposed approach in predicting versatile and dense grasps, and in advancing the field of robotic grasping.

翻译：机器人抓取是物体操控中一项基本技能。多指机器人手模仿人手结构，能够执行复杂的物体操作。然而，当前的多指机器人抓取技术通常每次推理仅预测单个抓取，限制了其多功能性和效率。本文提出一种可微分多指抓取生成网络（DMFC-GraspNet），包含两项主要贡献以解决这一挑战。首先，提出一种新型神经抓取规划器，预测新的抓取表示以实现多功能且密集的抓取预测。其次，开发了一种场景创建与标签映射方法，用于多指机器人手的密集标注，从而实现对真实抓取样本的密集关联。通过仿真研究评估所提方法，并与现有方法进行对比。结果表明，该方法在预测多功能密集抓取方面具有有效性，并推动了机器人抓取领域的发展。