Tactile information is valuable in determining properties of objects that are inaccessible from visual perception. A new type of tangential friction and normal contact force magnetostrictive tactile sensor was developed based on the inverse magnetostrictive effect, and the force output model has been established. It can measure the exerted force in the range of 0–4 N, and it has a good response to the dynamic force in cycles of 0.25–0.5 s. We present a tactile perception strategy that a manipulator with tactile sensors in its grippers manipulates an object to measure a set of tactile features. It shows that tactile sensing system can use these features and the extreme learning machine algorithm to recognize household objects—purely from tactile sensing—from a small training set. The complex matrixes show the recognition rate is up to 83%.

中文翻译：

---

用于物体识别的检测摩擦力和法向力的磁致伸缩触觉传感器

触觉信息在确定视觉感知无法访问的对象的属性方面很有价值。基于逆磁致伸缩效应研制了一种新型的切向摩擦法向接触力磁致伸缩触觉传感器，并建立了力输出模型。它可以测量0-4 N范围内的作用力，对0.25-0.5 s周期的动态力有很好的响应。我们提出了一种触觉感知策略，即在其抓手中带有触觉传感器的机械手操纵一个物体来测量一组触觉特征。它表明触觉感知系统可以使用这些特征和极限学习机算法从一个小的训练集中识别家庭物体——完全通过触觉感知。复杂矩阵显示识别率高达83%。