Contact SLAM: An Active Tactile Exploration Policy Based on Physical Reasoning Utilized in Robotic Fine Blind Manipulation Tasks

TL;DR

This paper introduces Contact SLAM, a tactile-based environment estimation method for robotic blind manipulation, combining physical reasoning with active exploration to improve accuracy in contact-rich tasks without visual feedback.

Contribution

It presents a novel physically-driven contact cognition approach and an active exploration policy for tactile-based environment estimation in blind manipulation tasks.

Findings

Effective in socket assembly and block-pushing tasks

Reduces uncertainty in environment state estimation

Demonstrates high accuracy and robustness

Abstract

Contact-rich manipulation is difficult for robots to execute and requires accurate perception of the environment. In some scenarios, vision is occluded. The robot can then no longer obtain real-time scene state information through visual feedback. This is called ``blind manipulation". In this manuscript, a novel physically-driven contact cognition method, called ``Contact SLAM", is proposed. It estimates the state of the environment and achieves manipulation using only tactile sensing and prior knowledge of the scene. To maximize exploration efficiency, this manuscript also designs an active exploration policy. The policy gradually reduces uncertainties in the manipulation scene. The experimental results demonstrated the effectiveness and accuracy of the proposed method in several contact-rich tasks, including the difficult and delicate socket assembly task and block-pushing task.