VMGNet: A Low Computational Complexity Robotic Grasping Network Based on VMamba With Multiscale Feature Fusion

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 vision mamba grasping network (VMGNet) for 2-D planar robotic grasping. For the first time, we introduce the visual state space (VSS) 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 multiscale feature fusion module, named fusion bridge module (FBM), 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 8.7 gigafloating point operations and an inference time (IT) of 8.1 ms on our devices. VMGNet also achieved state-of-the-art (SOTA) performance on the Cornell and Jacquard public datasets. To validate VMGNet’s effectiveness in practical applications, we conducted real grasping experiments in multiobject scenarios, and VMGNet achieved an excellent performance with a 94.4% success rate in real-world grasping tasks.