DeepWay: A Deep Learning waypoint estimator for global path generation

Mazzia, Vittorio; Salvetti, Francesco; Aghi, Diego; Chiaberge, Marcello

doi:10.1016/j.compag.2021.106091

Cited by 22 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a suitable path generator is crucial for obtaining a complete autonomous navigation performance and its absence prevents the control of the platform on the field. For that reason, in [1], moving from the clustering solution proposed in [37] to detect the rows of the vineyards, DeepWay, a robust datadriven approach for global path generation, was presented. Besides being more robust and easier to adopt, DeepWay is a highly general approach that can be extended to every kind of row-based crops.…”

Section: A Related Workmentioning

confidence: 99%

“…Agriculture 3.0 and 4.0 have gradually introduced autonomous machines and interconnected sensors into several agricultural processes [1], trying to introduce robust and costeffective novel solutions into the overall production chain. For instance, precision agriculture has progressively innovated tools for automatic harvesting [2], vegetative assessment [3], crops yield estimation [4], smart and sustainable pesticide spraying robotic system [5] and many others [6], [7].…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

“…Global path planning [1], mapping [11], localization [12] and decision-making [13] are only some of the required tools that each year undergo heavy research from the scientific community to achieve the necessary requirements for full automation. Among all requirements, a low financial impact constitutes a fundamental goal in order to provide genuinely large-scale competitive solutions [14].…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

“…The overall proposed methodology guarantees to autonomously navigate throughout row-based crops without expensive sensors and with every seasonal variation. All the algorithmic pipeline has been developed ROS-compatible in order to make easier the communication among different software modules and to be easily deployed on our developing platform, the Jackal Unmanned Ground Vehicle (UGV) by Clearpath Robotics 1 . Extensive experimentation and simulations against computer-generated environments and diverse real-world crops demonstrated the robustness and intrinsic generalizability of our solution.…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

See 3 more Smart Citations

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Cerrato¹,

Mazzia²,

Salvetti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Expensive sensors and inefficient algorithmic pipelines significantly affect the overall cost of autonomous machines. However, affordable robotic solutions are essential to practical usage, and their financial impact constitutes a fundamental requirement to employ service robotics in most fields of application. Among all, researchers in the precision agriculture domain strive to devise robust and cost-effective autonomous platforms in order to provide genuinely large-scale competitive solutions. In this article, we present a complete algorithmic pipeline for row-based crops autonomous navigation, specifically designed to cope with low-range sensors and seasonal variations. Firstly, we build on a robust data-driven methodology to generate a viable path for the autonomous machine, covering the full extension of the crop with only the occupancy grid map information of the field. Moreover, our solution leverages on latest advancement of deep learning optimization techniques and synthetic generation of data to provide an affordable solution that efficiently tackles the well-known Global Navigation Satellite System unreliability and degradation due to vegetation growing inside rows. Extensive experimentation and simulations against computer-generated environments and real-world crops demonstrated the robustness and intrinsic generalizability of our methodology that opens the possibility of highly affordable and fully autonomous machines.

show abstract

Section: A Related Workmentioning

confidence: 99%

Section: Introduction and State Of The Artmentioning

confidence: 99%

Section: Introduction and State Of The Artmentioning

confidence: 99%

Section: Introduction and State Of The Artmentioning

confidence: 99%

See 2 more Smart Citations

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Cerrato¹,

Mazzia²,

Salvetti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed high-level controller for autonomous navigation in the vineyard rows is part of a broader project of our research group that aims at developing an affordable self-driving system for vineyard parcels. Given a global path made of georeferenced waypoints [28], we exploit a dual local planner to overcome the lack of accuracy of the GPSbased localization filter inside the vine rows. Indeed, the signals provided by the satellites are very sensitive to obstacles encountered during the satellite-receiver path (e.g.…”

Section: B the Broader Projectmentioning

confidence: 99%

Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows

Aghi,

Cerrato,

Mazzia

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Precision agriculture is a fast-growing field that aims at introducing affordable and effective automation into agricultural processes. Nowadays, algorithmic solutions for navigation in vineyards require expensive sensors and high computational workloads that preclude large-scale applicability of autonomous robotic platforms in real business case scenarios. From this perspective, our novel proposed control leverages the latest advancement in machine perception and edge AI techniques to achieve highly affordable and reliable navigation inside vineyard rows with low computational and power consumption. Indeed, using a custom-trained segmentation network and a low-range RGB-D camera, we are able to take advantage of the semantic information of the environment to produce smooth trajectories and stable control in different vineyards scenarios. Moreover, the segmentation maps generated by the control algorithm itself could be directly exploited as filters for a vegetative assessment of the crop status. Extensive experimentations and evaluations against real-world data and simulated environments demonstrated the effectiveness and intrinsic robustness of our methodology.

show abstract

Waypoint Generation in Row-Based Crops with Deep Learning and Contrastive Clustering

Salvetti

Angarano

Martini

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

DeepWay: A Deep Learning waypoint estimator for global path generation

Cited by 22 publications

References 18 publications

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows

Waypoint Generation in Row-Based Crops with Deep Learning and Contrastive Clustering

Contact Info

Product

Resources

About