Going In Blind: Object Motion Classification using Distributed Tactile Sensing for Safe Reaching in Clutter

TL;DR

This paper introduces a tactile sensing method for classifying object motion during incidental contacts, enabling safe and efficient manipulation in cluttered environments without explicit object identification.

Contribution

It presents a novel tactile-based classification approach that determines object movability and contact safety with high accuracy, bypassing the need for object recognition.

Findings

Achieves over 90% accuracy in classifying object movability.

Effectively distinguishes between safe and unsafe contacts.

Demonstrates practical application in cluttered manipulation tasks.

Abstract

Robotic manipulators navigating cluttered shelves or cabinets may find it challenging to avoid contact with obstacles. Indeed, rearranging obstacles may be necessary to access a target. Rather than planning explicit motions that place obstacles into a desired pose, we suggest allowing incidental contacts to rearrange obstacles while monitoring contacts for safety. Bypassing object identification, we present a method for categorizing object motions from tactile data collected from incidental contacts with a capacitive tactile skin on an Allegro Hand. We formalize tactile cues associated with categories of object motion, demonstrating that they can determine with $>90$% accuracy whether an object is movable and whether a contact is causing the object to slide stably (safe contact) or tip (unsafe).