Soft Tracking Using Contacts for Cluttered Objects to Perform Blind Object Retrieval

TL;DR

This paper introduces STUCCO, a particle filter-based method for tracking objects in cluttered spaces using contact feedback alone, enabling blind object retrieval despite noisy sensing and ambiguous object associations.

Contribution

The paper presents a novel contact-based tracking method that revises object associations over time, improving retrieval success in cluttered environments with limited sensing.

Findings

Achieves at least 65% grasp success in simulations

Outperforms baselines which achieve under 5% success

Effective on real robot with noisy contact sensing

Abstract

Retrieving an object from cluttered spaces suchas cupboards, refrigerators, or bins requires tracking objects with limited or no visual sensing. In these scenarios, contact feedback is necessary to estimate the pose of the objects, yet the objects are movable while their shapes and number may be unknown, making the association of contacts with objects extremely difficult. While previous work has focused on multi-target tracking, the assumptions therein prohibit using prior methods given only the contact-sensing modality. Instead, this paper proposes the method Soft Tracking Using Contacts for Cluttered Objects (STUCCO) that tracks the belief over contact point locations and implicit object associations using a particle filter. This method allows ambiguous object associations of past contacts to be revised as new information becomes available. We apply STUCCO to the Blind Object Retrieval problem, where a target object of known shape but unknown pose must be retrieved from clutter. Our results suggest that our method outperforms baselines in four simulation environments, and on a real robot, where contact sensing is noisy. In simulation, we achieve grasp success of at least 65% on all environments while no baselines achieve over 5%.