Contact force estimation from flexible tactile sensor values considering hysteresis by Gaussian process

摘要: Flexible tactile sensors are important elements for facilitating the physical interaction between robots and uncertain environments. For instance, information is used by robot to grasp objects interact with humans. A model-based approach one technique building a relationship sensor values task-relevant such as force, slip, temperature. However, it difficult create models of flexible converting signals beforehand due nonlinear relation contact deformations form caused its hysteresis [1]. In contrast, machine learning techniques can be adopted represent these relationships. example, Tada et al. [2] proposed model acquire slip vibration using neural network.