Optimization-Based Mechanical Perception for Peduncle Localization During Robotic Fruit Harvest

TL;DR

This paper introduces a mechanical perception method using force/torque sensors and physical modeling to localize peduncles during robotic fruit harvesting, providing an alternative to visual methods in cluttered environments.

Contribution

It presents a novel mechanical perception approach that estimates peduncle location through force measurements and physical modeling, improving localization robustness.

Findings

Median peduncle localization error of 3.8 cm

Median orientation error of 16.8 degrees

Effective in cluttered orchard environments

Abstract

Rising global food demand and harsh working conditions make fruit harvest an important domain to automate. Peduncle localization is an important step for any automated fruit harvesting system, since fruit separation techniques are highly sensitive to peduncle location. Most work on peduncle localization has focused on computer vision, but peduncles can be difficult to visually access due to the cluttered nature of agricultural environments. Our work proposes an alternative method which relies on mechanical -- rather than visual -- perception to localize the peduncle. To estimate the location of this important plant feature, we fit wrench measurements from a wrist force/torque sensor to a physical model of the fruit-plant system, treating the fruit's attachment point as a parameter to be tuned. This method is performed inline as part of the fruit picking procedure. Using our orchard proxy for evaluation, we demonstrate that the technique is able to localize the peduncle within a median distance of 3.8 cm and median orientation error of 16.8 degrees.