Self-Assessment of Grasp Affordance Transfer

TL;DR

This paper introduces a novel pipeline for grasp affordance transfer that leverages prior experiences and simulation to improve grasp success rates in robotic manipulation tasks.

Contribution

It presents a SAGAT pipeline that uses experience-based simulation and ranking to enhance grasp affordance detection and transfer for robots.

Findings

Achieves up to 11.7% performance improvement over state-of-the-art methods.

Demonstrates high reliability on a PR2 robotic platform.

Effectively transfers grasp affordances to new objects using a learned experience library.

Abstract

Reasoning about object grasp affordances allows an autonomous agent to estimate the most suitable grasp to execute a task. While current approaches for estimating grasp affordances are effective, their prediction is driven by hypotheses on visual features rather than an indicator of a proposal's suitability for an affordance task. Consequently, these works cannot guarantee any level of performance when executing a task and, in fact, not even ensure successful task completion. In this work, we present a pipeline for SAGAT based on prior experiences. We visually detect a grasp affordance region to extract multiple grasp affordance configuration candidates. Using these candidates, we forward simulate the outcome of executing the affordance task to analyse the relation between task outcome and grasp candidates. The relations are ranked by performance success with a heuristic confidence function and used to build a library of affordance task experiences. The library is later queried to perform one-shot transfer estimation of the best grasp configuration on new objects. Experimental evaluation shows that our method exhibits a significant performance improvement up to 11.7% against current state-of-the-art methods on grasp affordance detection. Experiments on a PR2 robotic platform demonstrate our method's highly reliable deployability to deal with real-world task affordance problems.