College of Information Science and Engineering, Northeastern University, Shenyang 110819, China.
SIASUN Robot & Automation Co., Ltd., Shenyang 110168, China.
Sensors (Basel). 2023 Jun 22;23(13):5826. doi: 10.3390/s23135826.
This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved.
本文提出了一种基于注意力机制和空洞空间金字塔池化（CBAM-ASPP）的 CBAM-ASPP-SqueezeNet 模型，以解决机器人多目标抓取检测问题。首先，本文建立并扩展了一个多目标抓取数据集，并引入和使用迁移学习对单目标数据集进行网络预训练，然后使用多目标数据集对模型参数进行轻微修改。其次，使用注意力机制和空洞空间金字塔池化模块对 SqueezeNet 模型进行优化和改进。本文引入了注意力机制网络，对通道和空间维度中传输的特征图进行加权。它使用各种不同空洞率的空洞卷积并行操作，增加了感受野的大小，并保留了来自不同范围的特征。最后，使用自行构建的多目标抓取数据集验证 CBAM-ASPP-SqueezeNet 算法。当本文引入迁移学习时，经过 20 个周期的训练后，各项指标收敛。在 Kinova 和 SIASUN Arm 进行的物理抓取实验中，网络抓取成功率达到 93%。
