Recent advances in the field of intelligent robotic manipulation pursue providing robotic hands with touch sensitivity. Haptic perception encompasses the sensing modalities encountered in the sense of touch (e.g., tactile and kinesthetic sensations). This letter focuses on multimodal object recognition and proposes analytical and data-driven methodologies to fuse tactile- and kinesthetic-based classification results. The procedure is as follows: a three-finger actuated gripper with an integrated high-resolution tactile sensor performs squeeze-and-release Exploratory Procedures (EPs). The tactile images and kinesthetic information acquired using angular sensors on the finger joints constitute the time-series datasets of interest. Each temporal dataset is fed to a Long Short-term Memory (LSTM) Neural Network, which is trained to classify in-hand objects. The LSTMs provide an estimation of the posterior probability of each object given the corresponding measurements, which after fusion allows to estimate the object through Bayesian and Neural inference approaches. An experiment with 36-classes is carried out to evaluate and compare the performance of the fused, tactile, and kinesthetic perception systems. The results show that the Bayesian-based classifiers improves capabilities for object recognition and outperforms the Neural-based approach.

中文翻译：

---

基于触觉和动觉信息的基于 LSTM 的对象识别的贝叶斯和神经推理

智能机器人操纵领域的最新进展致力于为机器人手提供触摸灵敏度。触觉感知包括在触觉中遇到的感知方式（例如，触觉和动觉）。这封信侧重于多模态对象识别，并提出了分析和数据驱动的方法来融合基于触觉和动觉的分类结果。程序如下：带有集成高分辨率触觉传感器的三指驱动夹具执行挤压和释放探索程序 (EP)。使用手指关节上的角度传感器获取的触觉图像和动觉信息构成了感兴趣的时间序列数据集。每个时间数据集都被馈送到一个长短期记忆 (LSTM) 神经网络，它被训练来对手中的物体进行分类。LSTM 提供给定相应测量值的每个对象的后验概率估计，融合后允许通过贝叶斯和神经推理方法估计对象。进行了 36 个类别的实验，以评估和比较融合、触觉和动觉感知系统的性能。结果表明，基于贝叶斯的分类器提高了对象识别的能力，并且优于基于神经的方法。触觉和动觉感知系统。结果表明，基于贝叶斯的分类器提高了对象识别的能力，并且优于基于神经的方法。触觉和动觉感知系统。结果表明，基于贝叶斯的分类器提高了对象识别的能力，并且优于基于神经的方法。