Integration of 3D Object Recognition and Planning for Robotic Manipulation: A Preliminary Report

TL;DR

This paper explores integrating 3D object recognition with planning in robotic manipulation, demonstrating that close integration enhances plan quality and reduces computation times in a tabletop domain.

Contribution

It presents preliminary experimental results showing the benefits of integrating perception and planning for robotic manipulation tasks.

Findings

Improved plan quality with integrated perception and planning

Reduced computation times for feasible plans

Preliminary evidence supporting integrated approaches

Abstract

We investigate different approaches to integrating object recognition and planning in a tabletop manipulation domain with the set of objects used in the 2012 RoboCup@Work competition. Results of our preliminary experiments show that, with some approaches, close integration of perception and planning improves the quality of plans, as well as the computation times of feasible plans.