Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Chung Hee, Silwal, Abhisesh, Kantor, George
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909391020621824
author Kim, Chung Hee
Silwal, Abhisesh
Kantor, George
author_facet Kim, Chung Hee
Silwal, Abhisesh
Kantor, George
contents Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system for autonomous pepper harvesting designed to operate in these unprotected, complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the feasibility and effectiveness of leveraging imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09929
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments
Kim, Chung Hee
Silwal, Abhisesh
Kantor, George
Robotics
Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system for autonomous pepper harvesting designed to operate in these unprotected, complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the feasibility and effectiveness of leveraging imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings.
title Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments
topic Robotics
url https://arxiv.org/abs/2411.09929