Using 3D Convolutional Neural Networks for Tactile Object Recognition with Robotic Palpation
Using 3D Convolutional Neural Networks for Tactile Object Recognition with Robotic Palpation
复制标题
DOI：
10.3390/s19245356
复制
发表时间：
2019-12-02
期刊：
影响因子：
3.9
通讯作者：
Gomez-de-Gabriel, Jesus M.
中科院分区：
文献类型：
--
作者：
Pastor, Francisco;Gandarias, Juan M.;Gomez-de-Gabriel, Jesus M.
提出了一种基于三维神经网络和高分辨率触觉传感器的主动触觉感知方法。基于机器人触诊的触觉探索程序进行，以获得压力图像在不同的把握力，提供信息，不仅关于物体的外部形状，但也关于其内部特征。夹持器由两个欠驱动的手指与触觉传感器阵列在拇指。描述了一种新的触觉信息表示为三维触觉张量。在挤压和释放过程中，从触觉传感器读取的压力图像被连接形成张量，该张量包含关于压力矩阵沿着抓握力的变化的信息。这些张量被用于馈送一个名为3D TactNet的3D卷积神经网络（3D CNN），该网络能够通过主动交互对抓取的对象进行分类。结果表明，3D CNN表现更好，并且以更少的训练数据提供更好的识别率。
In this paper, a novel method of active tactile perception based on 3D neural networks and a high-resolution tactile sensor installed on a robot gripper is presented. A haptic exploratory procedure based on robotic palpation is performed to get pressure images at different grasping forces that provide information not only about the external shape of the object, but also about its internal features. The gripper consists of two underactuated fingers with a tactile sensor array in the thumb. A new representation of tactile information as 3D tactile tensors is described. During a squeeze-and-release process, the pressure images read from the tactile sensor are concatenated forming a tensor that contains information about the variation of pressure matrices along with the grasping forces. These tensors are used to feed a 3D Convolutional Neural Network (3D CNN) called 3D TactNet, which is able to classify the grasped object through active interaction. Results show that 3D CNN performs better, and provide better recognition rates with a lower number of training data.