Advances on Affordable Hardware Platforms for Human Demonstration Acquisition in Agricultural Applications

TL;DR

This paper introduces an improved low-cost hand-held gripper system for agricultural robot learning from demonstration, enhancing sample acquisition efficiency and reliability through innovative data extraction and sensor fusion techniques.

Contribution

The paper presents novel methods for extracting task samples from continuous demonstrations and combining inertial and visual data using EKF, tailored for agricultural applications.

Findings

Outperforms default pipeline in fruit harvesting tasks

Reduces user cognitive load and idle times

Enhances sample reliability with sensor fusion

Abstract

This paper presents advances on the Universal Manipulation Interface (UMI), a low-cost hand-held gripper for robot Learning from Demonstration (LfD), for complex in-the-wild scenarios found in agricultural settings. The focus is on improving the acquisition of suitable samples with minimal additional setup. Firstly, idle times and user's cognitive load are reduced through the extraction of individual samples from a continuous demonstration considering task events. Secondly, reliability on the generation of task sample's trajectories is increased through the combination on-board inertial measurements and external visual marker localization usage using Extended Kalman Filtering (EKF). Results are presented for a fruit harvesting task, outperforming the default pipeline.