A Bayesian Framework for Active Tactile Object Recognition, Pose Estimation and Shape Transfer Learning

TL;DR

This paper presents a Bayesian framework combining particle filters and Gaussian process implicit surfaces for active tactile object recognition, pose estimation, and shape transfer learning, enabling robots to learn and recognize objects through touch.

Contribution

It introduces a unified Bayesian approach that integrates shape reconstruction, object recognition, and transfer learning for tactile perception in robots.

Findings

Effective in estimating object class and pose in simulation

Able to learn and recognize novel shapes reliably

Guides active data acquisition for efficient exploration

Abstract

As humans can explore and understand the world through active touch, similar capability is desired for robots. In this paper, we address the problem of active tactile object recognition, pose estimation and shape transfer learning, where a customized particle filter (PF) and Gaussian process implicit surface (GPIS) is combined in a unified Bayesian framework. Upon new tactile input, the customized PF updates the joint distribution of the object class and object pose while tracking the novelty of the object. Once a novel object is identified, its shape will be reconstructed using GPIS. By grounding the prior of the GPIS with the maximum-a-posteriori (MAP) estimation from the PF, the knowledge about known shapes can be transferred to learn novel shapes. An exploration procedure based on global shape estimation is proposed to guide active data acquisition and terminate the exploration upon sufficient information. Through experiments in simulation, the proposed framework demonstrated its effectiveness and efficiency in estimating object class and pose for known objects and learning novel shapes. Furthermore, it can recognize previously learned shapes reliably.