We consider the problem of autonomously estimating position and orientation of an object from tactile data. When initial uncertainty is high, estimation of all six parameters precisely is computationally expensive. We propose an efﬁcient Bayesian approach that is able to estimate all six parameters in both unimodal and multimodal scenarios. The approach is termed Scaling Series sampling as it estimates the solution region by samples. It performs the search using a series of successive reﬁnements, gradually scaling the precision from low to high. Our approach can be applied to a wide range of manipulation tasks. We demonstrate its portability on two applications: (1) manipulating a box and (2) grasping a door handle.