Precision agriculture is rapidly attracting research to efficiently introduce automation and robotics solutions to support agricultural activities. Robotic navigation in vineyards and orchards offers competitive advantages in autonomously monitoring and easily accessing crops for harvesting, spraying and performing time-consuming necessary tasks. Nowadays, autonomous navigation algorithms exploit expensive sensors which also require heavy computational cost for data processing. Nonetheless, vineyard rows represent a challenging outdoor scenario where GPS and Visual Odometry techniques often struggle to provide reliable positioning information. In this work, we combine Edge AI with Deep Reinforcement Learning to propose a cutting-edge lightweight solution to tackle the problem of autonomous vineyard navigation with-out exploiting precise localization data and overcoming task-tailored algorithms with a flexible learning-based approach. We train an end-to-end sensorimotor agent which directly maps noisy depth images and position-agnostic robot state information to velocity commands and guides the robot to the end of a row, continuously adjusting its heading for a collision-free central trajectory. Our extensive experimentation in realistic simulated vineyards demonstrates the effectiveness of our solution and the generalization capabilities of our agent.

Position-agnostic autonomous navigation in vineyards with Deep Reinforcement Learning / Martini, Mauro; Cerrato, Simone; Salvetti, Francesco; Angarano, Simone; Chiaberge, Marcello. - ELETTRONICO. - 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE):(2022), pp. 477-484. ((Intervento presentato al convegno 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) tenutosi a Mexico City (Mexico) nel August 20-24, 2022 [10.1109/CASE49997.2022.9926582].

Position-agnostic autonomous navigation in vineyards with Deep Reinforcement Learning

Mauro Martini;Simone Cerrato;Francesco Salvetti;Simone Angarano;Marcello Chiaberge
2022

Abstract

Precision agriculture is rapidly attracting research to efficiently introduce automation and robotics solutions to support agricultural activities. Robotic navigation in vineyards and orchards offers competitive advantages in autonomously monitoring and easily accessing crops for harvesting, spraying and performing time-consuming necessary tasks. Nowadays, autonomous navigation algorithms exploit expensive sensors which also require heavy computational cost for data processing. Nonetheless, vineyard rows represent a challenging outdoor scenario where GPS and Visual Odometry techniques often struggle to provide reliable positioning information. In this work, we combine Edge AI with Deep Reinforcement Learning to propose a cutting-edge lightweight solution to tackle the problem of autonomous vineyard navigation with-out exploiting precise localization data and overcoming task-tailored algorithms with a flexible learning-based approach. We train an end-to-end sensorimotor agent which directly maps noisy depth images and position-agnostic robot state information to velocity commands and guides the robot to the end of a row, continuously adjusting its heading for a collision-free central trajectory. Our extensive experimentation in realistic simulated vineyards demonstrates the effectiveness of our solution and the generalization capabilities of our agent.
File in questo prodotto:
File Dimensione Formato  
Position-Agnostic_Autonomous_Navigation_in_Vineyards_with_Deep_Reinforcement_Learning.pdf

non disponibili

Descrizione: Post print
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.63 MB
Formato Adobe PDF
1.63 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
2206.14155.pdf

accesso aperto

Descrizione: Accepted manuscript
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 3.97 MB
Formato Adobe PDF
3.97 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2972745