arXiv 2411.125202025-09-09cs.ROcs.CV

VMGNet：基于VMamba与多尺度特征融合的低计算复杂度机器人抓取网络

VMGNet: A Low Computational Complexity Robotic Grasping Network Based on VMamba with Multi-Scale Feature Fusion

Yuhao Jin, Qizhong Gao, Xiaohui Zhu, Yong Yue, Eng Gee Lim, Yuqing Chen, Prudence Wong, Yijie Chu

备注：: This work is part of ongoing research, and we are further developing new techniques based on these results. To avoid premature disclosure of incomplete content, we request withdrawal of the current version and will resubmit once the study is more complete

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出VMGNet，一种基于VMamba的低计算复杂度机器人抓取网络，通过视觉状态空间和Fusion Bridge多尺度融合模块，在Cornell和Jacquard数据集上达到最先进性能，真实抓取成功率达94.4%。

摘要：

尽管基于深度学习的机器人抓取技术已展现出强大的适应性，但其计算复杂度也显著增加，使其不适用于对实时性要求较高的场景。因此，我们提出了一种名为VMGNet的低计算复杂度、高精度的机器人抓取模型。我们首次将视觉状态空间引入机器人抓取领域，以实现线性计算复杂度，从而大幅降低模型的计算成本。同时，为提高模型精度，我们提出了一种高效轻量的多尺度特征融合模块，命名为Fusion Bridge Module，用于提取和融合不同尺度的信息。我们还提出了一种新的损失函数计算方法，以增强子任务之间的重要性差异，提高模型的拟合能力。实验表明，VMGNet在我们的设备上仅有8.7G浮点运算量，推理时间为8.1毫秒。VMGNet还在Cornell和Jacquard公共数据集上取得了最先进的性能。为验证VMGNet在实际应用中的有效性，我们在多物体场景中进行了真实抓取实验，VMGNet在真实世界抓取任务中取得了94.4%成功率的优异表现。真实机器人抓取实验的视频可在https://youtu.be/S-QHBtbmLc4获取。

英文摘要：

While deep learning-based robotic grasping technology has demonstrated strong adaptability, its computational complexity has also significantly increased, making it unsuitable for scenarios with high real-time requirements. Therefore, we propose a low computational complexity and high accuracy model named VMGNet for robotic grasping. For the first time, we introduce the Visual State Space into the robotic grasping field to achieve linear computational complexity, thereby greatly reducing the model's computational cost. Meanwhile, to improve the accuracy of the model, we propose an efficient and lightweight multi-scale feature fusion module, named Fusion Bridge Module, to extract and fuse information at different scales. We also present a new loss function calculation method to enhance the importance differences between subtasks, improving the model's fitting ability. Experiments show that VMGNet has only 8.7G Floating Point Operations and an inference time of 8.1 ms on our devices. VMGNet also achieved state-of-the-art performance on the Cornell and Jacquard public datasets. To validate VMGNet's effectiveness in practical applications, we conducted real grasping experiments in multi-object scenarios, and VMGNet achieved an excellent performance with a 94.4% success rate in real-world grasping tasks. The video for the real-world robotic grasping experiments is available at https://youtu.be/S-QHBtbmLc4.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。