2023
1.
Aseem Saxena; Paola Pesantez-Cabrera; Rohan Ballapragada; Markus Keller; Alan Fern
Multi-Task Learning for Budbreak Prediction Workshop
2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS), arXiv, 2023, (arXiv:2301.01815 [cs]).
Abstract | Links | BibTeX | Tags: Computer Science - Machine Learning
@workshop{saxena_multi-task_2023,
title = {Multi-Task Learning for Budbreak Prediction},
author = {Aseem Saxena and Paola Pesantez-Cabrera and Rohan Ballapragada and Markus Keller and Alan Fern},
url = {http://arxiv.org/abs/2301.01815},
doi = {10.48550/arXiv.2301.01815},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS)},
publisher = {arXiv},
abstract = {Grapevine budbreak is a key phenological stage of seasonal development, which serves as a signal for the onset of active growth. This is also when grape plants are most vulnerable to damage from freezing temperatures. Hence, it is important for winegrowers to anticipate the day of budbreak occurrence to protect their vineyards from late spring frost events. This work investigates deep learning for budbreak prediction using data collected for multiple grape cultivars. While some cultivars have over 30 seasons of data others have as little as 4 seasons, which can adversely impact prediction accuracy. To address this issue, we investigate multi-task learning, which combines data across all cultivars to make predictions for individual cultivars. Our main result shows that several variants of multi-task learning are all able to significantly improve prediction accuracy compared to learning for each cultivar independently.},
note = {arXiv:2301.01815 [cs]},
keywords = {Computer Science - Machine Learning},
pubstate = {published},
tppubtype = {workshop}
}
Grapevine budbreak is a key phenological stage of seasonal development, which serves as a signal for the onset of active growth. This is also when grape plants are most vulnerable to damage from freezing temperatures. Hence, it is important for winegrowers to anticipate the day of budbreak occurrence to protect their vineyards from late spring frost events. This work investigates deep learning for budbreak prediction using data collected for multiple grape cultivars. While some cultivars have over 30 seasons of data others have as little as 4 seasons, which can adversely impact prediction accuracy. To address this issue, we investigate multi-task learning, which combines data across all cultivars to make predictions for individual cultivars. Our main result shows that several variants of multi-task learning are all able to significantly improve prediction accuracy compared to learning for each cultivar independently.
2.
Welankar Sejal; Paola Pesantez-Cabrera; Bala Krishnamoorthy; Ananth Kalyanaraman
Persistent Homology to Study Cold Hardiness of Grape Cultivars Workshop
2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS), arXiv, 2023.
Links | BibTeX | Tags: Computer Science - Machine Learning
@workshop{welankar_grape_2023,
title = {Persistent Homology to Study Cold Hardiness of Grape Cultivars},
author = {Welankar Sejal and Paola Pesantez-Cabrera and Bala Krishnamoorthy and Ananth Kalyanaraman},
url = {https://doi.org/10.48550/arXiv.2302.05600},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS)},
publisher = {arXiv},
keywords = {Computer Science - Machine Learning},
pubstate = {published},
tppubtype = {workshop}
}
3.
Aseem Saxena; Paola Pesantez-Cabrera; Rohan Ballapragada; Kin-Ho Lam; Markus Keller; Alan Fern
Grape Cold Hardiness Prediction via Multi-Task Learning Conference
Association for the Advancement of Artificial Intelligence (AAAI) 2023, arXiv, 2023.
Abstract | Links | BibTeX | Tags: FOS: Computer and information sciences, Machine Learning (cs.LG)
@conference{saxena_aaai2023,
title = {Grape Cold Hardiness Prediction via Multi-Task Learning},
author = {Aseem Saxena and Paola Pesantez-Cabrera and Rohan Ballapragada and Kin-Ho Lam and Markus Keller and Alan Fern},
url = {https://arxiv.org/abs/2209.10585},
doi = {10.48550/ARXIV.2209.10585},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Association for the Advancement of Artificial Intelligence (AAAI) 2023},
publisher = {arXiv},
abstract = {Cold temperatures during fall and spring have the potential to cause frost damage to grapevines and other fruit plants, which can significantly decrease harvest yields. To help prevent these losses, farmers deploy expensive frost mitigation measures such as sprinklers, heaters, and wind machines when they judge that damage may occur. This judgment, however, is challenging because the cold hardiness of plants changes throughout the dormancy period and it is difficult to directly measure. This has led scientists to develop cold hardiness prediction models that can be tuned to different grape cultivars based on laborious field measurement data. In this paper, we study whether deep-learning models can improve cold hardiness prediction for grapes based on data that has been collected over a 30-year time period. A key challenge is that the amount of data per cultivar is highly variable, with some cultivars having only a small amount. For this purpose, we investigate the use of multi-task learning to leverage data across cultivars in order to improve prediction performance for individual cultivars. We evaluate a number of multi-task learning
approaches and show that the highest-performing approach is able to significantly improve overlearning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.},
keywords = {FOS: Computer and information sciences, Machine Learning (cs.LG)},
pubstate = {published},
tppubtype = {conference}
}
Cold temperatures during fall and spring have the potential to cause frost damage to grapevines and other fruit plants, which can significantly decrease harvest yields. To help prevent these losses, farmers deploy expensive frost mitigation measures such as sprinklers, heaters, and wind machines when they judge that damage may occur. This judgment, however, is challenging because the cold hardiness of plants changes throughout the dormancy period and it is difficult to directly measure. This has led scientists to develop cold hardiness prediction models that can be tuned to different grape cultivars based on laborious field measurement data. In this paper, we study whether deep-learning models can improve cold hardiness prediction for grapes based on data that has been collected over a 30-year time period. A key challenge is that the amount of data per cultivar is highly variable, with some cultivars having only a small amount. For this purpose, we investigate the use of multi-task learning to leverage data across cultivars in order to improve prediction performance for individual cultivars. We evaluate a number of multi-task learning
approaches and show that the highest-performing approach is able to significantly improve overlearning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.
approaches and show that the highest-performing approach is able to significantly improve overlearning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.
2022
4.
Aseem Saxena; Paola Pesantez-Cabrera; Rohan Ballapragada; Kin-Ho Lam; Markus Keller; Alan Fern
Grape Cold Hardiness Prediction via Multi-Task Learning Workshop
Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022), 2022.
Abstract | BibTeX | Tags: AI, Farm Ops
@workshop{saxena_grape_2022,
title = {Grape Cold Hardiness Prediction via Multi-Task Learning},
author = {Aseem Saxena and Paola Pesantez-Cabrera and Rohan Ballapragada and Kin-Ho Lam and Markus Keller and Alan Fern},
year = {2022},
date = {2022-09-01},
urldate = {2022-09-01},
journal = {Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022)},
publisher = {Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022)},
abstract = {Cold temperatures during fall and spring have the potential to cause frost damage to grapevines and other fruit plants, which can significantly decrease harvest yields. To help prevent these losses, farmers deploy expensive frost mitigation measures, such as, sprinklers, heaters, and wind machines, when they judge that damage may occur. This judgment, however, is challenging because the cold hardiness of plants changes throughout the dormancy period and it is difficult to directly measure. This has led scientists to develop cold hardiness prediction models that can be tuned to different grape cultivars based on laborious field measurement data. In this paper, we study whether deep-learning models can improve cold hardiness prediction for grapes based on data that has been collected over a 30-year time period. A key challenge is that the amount of data per cultivar is highly variable, with some cultivars having only a small amount. For this purpose, we investigate the use of multi-task learning to leverage data across cultivars in order to improve prediction performance for individual cultivars. We evaluate a number of multi-task learning approaches and show that the highest performing approach is able to significantly improve over learning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.},
keywords = {AI, Farm Ops},
pubstate = {published},
tppubtype = {workshop}
}
Cold temperatures during fall and spring have the potential to cause frost damage to grapevines and other fruit plants, which can significantly decrease harvest yields. To help prevent these losses, farmers deploy expensive frost mitigation measures, such as, sprinklers, heaters, and wind machines, when they judge that damage may occur. This judgment, however, is challenging because the cold hardiness of plants changes throughout the dormancy period and it is difficult to directly measure. This has led scientists to develop cold hardiness prediction models that can be tuned to different grape cultivars based on laborious field measurement data. In this paper, we study whether deep-learning models can improve cold hardiness prediction for grapes based on data that has been collected over a 30-year time period. A key challenge is that the amount of data per cultivar is highly variable, with some cultivars having only a small amount. For this purpose, we investigate the use of multi-task learning to leverage data across cultivars in order to improve prediction performance for individual cultivars. We evaluate a number of multi-task learning approaches and show that the highest performing approach is able to significantly improve over learning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.
5.
Sejal Welankar; Paola Pesantez-Cabrera; Ananth Kalyanaraman
Extracting patterns in cold hardiness behavior using topological data analysis Workshop
arXiv, 2022.
Abstract | Links | BibTeX | Tags: AI, Farm Ops
@workshop{welankar_grape_2022,
title = {Extracting patterns in cold hardiness behavior using topological data analysis},
author = {Sejal Welankar and Paola Pesantez-Cabrera and Ananth Kalyanaraman},
url = {https://drive.google.com/file/d/1Mv4rGB1OhnK5Q0W_9To8UkSoqmPkL2WZ/view?usp=share_link},
year = {2022},
date = {2022-09-01},
urldate = {2022-09-01},
journal = {Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022)},
publisher = {arXiv},
abstract = {Prevention of cold injury is essential to maximize throughput for perennial specialty crops such as apples, cherries, wine grapes, etc. To achieve this, it is primordial to study the effects of environmental factors and their variations across different cultivars. To fully analyze and understand the relationship between phenotypes, genotypes, and environmental variables we need high dimensional datasets containing information such as crop height, growth characteristics, photosynthetic activity, and temperature, humidity, soil temperature. However, these datasets usually are incomplete and noisy. Topological data analysis (TDA) provides a general framework to analyze such data, extracting the underlying shape of data. The two main approaches in TDA are the mapper algorithm and persistence homology.},
keywords = {AI, Farm Ops},
pubstate = {published},
tppubtype = {workshop}
}
Prevention of cold injury is essential to maximize throughput for perennial specialty crops such as apples, cherries, wine grapes, etc. To achieve this, it is primordial to study the effects of environmental factors and their variations across different cultivars. To fully analyze and understand the relationship between phenotypes, genotypes, and environmental variables we need high dimensional datasets containing information such as crop height, growth characteristics, photosynthetic activity, and temperature, humidity, soil temperature. However, these datasets usually are incomplete and noisy. Topological data analysis (TDA) provides a general framework to analyze such data, extracting the underlying shape of data. The two main approaches in TDA are the mapper algorithm and persistence homology.
6.
Donald Bertucci; Md Montaser Hamid; Yashwanthi Anand; Anita Ruangrotsakun; Delyar Tabatabai; Melissa Perez; Minsuk Kahng
DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps Miscellaneous
2022, (arXiv:2205.06935 [cs]).
Abstract | Links | BibTeX | Tags: AI, Human-Computer Interaction
@misc{bertucci_dendromap_2022,
title = {DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps},
author = { Donald Bertucci and Md Montaser Hamid and Yashwanthi Anand and Anita Ruangrotsakun and Delyar Tabatabai and Melissa Perez and Minsuk Kahng},
url = {http://arxiv.org/abs/2205.06935},
doi = {10.48550/arXiv.2205.06935},
year = {2022},
date = {2022-08-01},
urldate = {2022-08-01},
publisher = {arXiv},
abstract = {In this paper, we present DendroMap, a novel approach to interactively exploring large-scale image datasets for machine learning (ML). ML practitioners often explore image datasets by generating a grid of images or projecting high-dimensional representations of images into 2-D using dimensionality reduction techniques (e.g., t-SNE). However, neither approach effectively scales to large datasets because images are ineffectively organized and interactions are insufficiently supported. To address these challenges, we develop DendroMap by adapting Treemaps, a well-known visualization technique. DendroMap effectively organizes images by extracting hierarchical cluster structures from high-dimensional representations of images. It enables users to make sense of the overall distributions of datasets and interactively zoom into specific areas of interests at multiple levels of abstraction. Our case studies with widely-used image datasets for deep learning demonstrate that users can discover insights about datasets and trained models by examining the diversity of images, identifying underperforming subgroups, and analyzing classification errors. We conducted a user study that evaluates the effectiveness of DendroMap in grouping and searching tasks by comparing it with a gridified version of t-SNE and found that participants preferred DendroMap. DendroMap is available at https://div-lab.github.io/dendromap/.},
note = {arXiv:2205.06935 [cs]},
keywords = {AI, Human-Computer Interaction},
pubstate = {published},
tppubtype = {misc}
}
In this paper, we present DendroMap, a novel approach to interactively exploring large-scale image datasets for machine learning (ML). ML practitioners often explore image datasets by generating a grid of images or projecting high-dimensional representations of images into 2-D using dimensionality reduction techniques (e.g., t-SNE). However, neither approach effectively scales to large datasets because images are ineffectively organized and interactions are insufficiently supported. To address these challenges, we develop DendroMap by adapting Treemaps, a well-known visualization technique. DendroMap effectively organizes images by extracting hierarchical cluster structures from high-dimensional representations of images. It enables users to make sense of the overall distributions of datasets and interactively zoom into specific areas of interests at multiple levels of abstraction. Our case studies with widely-used image datasets for deep learning demonstrate that users can discover insights about datasets and trained models by examining the diversity of images, identifying underperforming subgroups, and analyzing classification errors. We conducted a user study that evaluates the effectiveness of DendroMap in grouping and searching tasks by comparing it with a gridified version of t-SNE and found that participants preferred DendroMap. DendroMap is available at https://div-lab.github.io/dendromap/.
7.
Harsha Kokel; Nikhilesh Prabhakar; Balaraman Ravindran; Erik Blasch; Prasad Tadepalli; Sriraam Natarajan
Hybrid Deep RePReL: Integrating Relational Planning and Reinforcement Learning for Information Fusion Inproceedings
In: 2022 25th International Conference on Information Fusion (FUSION), pp. 1–8, 2022, ISBN: 978-1-73774-972-1.
Abstract | Links | BibTeX | Tags: AI
@inproceedings{kokel_hybrid_2022,
title = {Hybrid Deep RePReL: Integrating Relational Planning and Reinforcement Learning for Information Fusion},
author = { Harsha Kokel and Nikhilesh Prabhakar and Balaraman Ravindran and Erik Blasch and Prasad Tadepalli and Sriraam Natarajan},
doi = {10.23919/FUSION49751.2022.9841246},
isbn = {978-1-73774-972-1},
year = {2022},
date = {2022-07-01},
urldate = {2022-07-01},
booktitle = {2022 25th International Conference on Information Fusion (FUSION)},
pages = {1--8},
abstract = {Fusion of high-level symbolic reasoning with lower level signal-based reasoning has attracted significant attention. We propose an architecture that integrates the high-level symbolic domain knowledge using a hierarchical planner with a lower level reinforcement learner that uses hybrid data (structured and unstructured). We introduce a novel neuro-symbolic system, Hybrid Deep RePReL that achieves the best of both worlds-the generalization ability of the planner with the effective learning ability of deep RL. Our results in two domains demonstrate the superiority of our approach in terms of sample efficiency as well as generalization to increased set of objects.},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
Fusion of high-level symbolic reasoning with lower level signal-based reasoning has attracted significant attention. We propose an architecture that integrates the high-level symbolic domain knowledge using a hierarchical planner with a lower level reinforcement learner that uses hybrid data (structured and unstructured). We introduce a novel neuro-symbolic system, Hybrid Deep RePReL that achieves the best of both worlds-the generalization ability of the planner with the effective learning ability of deep RL. Our results in two domains demonstrate the superiority of our approach in terms of sample efficiency as well as generalization to increased set of objects.
8.
Taha Belkhouja; Yan Yan; Janardhan Rao Doppa
Dynamic Time Warping based Adversarial Framework for Time-Series Domain Inproceedings
In: arXiv, 2022, (arXiv:2207.04308 [cs]).
Abstract | Links | BibTeX | Tags: AI
@inproceedings{belkhouja_dynamic_2022,
title = {Dynamic Time Warping based Adversarial Framework for Time-Series Domain},
author = { Taha Belkhouja and Yan Yan and Janardhan Rao Doppa},
url = {http://arxiv.org/abs/2207.04308},
doi = {10.48550/arXiv.2207.04308},
year = {2022},
date = {2022-07-01},
urldate = {2022-07-01},
publisher = {arXiv},
abstract = {Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as textbackslashem Dynamic Time Warping for Adversarial Robustness (DTW-AR) using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard Euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training. The source code of DTW-AR algorithms is available at https://github.com/tahabelkhouja/DTW-AR},
note = {arXiv:2207.04308 [cs]},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as textbackslashem Dynamic Time Warping for Adversarial Robustness (DTW-AR) using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard Euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training. The source code of DTW-AR algorithms is available at https://github.com/tahabelkhouja/DTW-AR
9.
Taha Belkhouja; Yan Yan; Janardhan Rao Doppa
Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach Inproceedings
In: arXiv, 2022, (arXiv:2207.04306 [cs]).
Abstract | Links | BibTeX | Tags: AI
@inproceedings{belkhouja_out--distribution_2022,
title = {Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach},
author = { Taha Belkhouja and Yan Yan and Janardhan Rao Doppa},
url = {http://arxiv.org/abs/2207.04306},
doi = {10.48550/arXiv.2207.04306},
year = {2022},
date = {2022-07-01},
urldate = {2022-07-01},
publisher = {arXiv},
abstract = {Safe deployment of time-series classifiers for real-world applications relies on the ability to detect the data which is not generated from the same distribution as training data. This task is referred to as out-of-distribution (OOD) detection. We consider the novel problem of OOD detection for the time-series domain. We discuss the unique challenges posed by time-series data and explain why prior methods from the image domain will perform poorly. Motivated by these challenges, this paper proposes a novel textbackslashem Seasonal Ratio Scoring (SRS) approach. SRS consists of three key algorithmic steps. First, each input is decomposed into class-wise semantic component and remainder. Second, this decomposition is employed to estimate the class-wise conditional likelihoods of the input and remainder using deep generative models. The seasonal ratio score is computed from these estimates. Third, a threshold interval is identified from the in-distribution data to detect OOD examples. Experiments on diverse real-world benchmarks demonstrate that the SRS method is well-suited for time-series OOD detection when compared to baseline methods. Open-source code for SRS method is provided at https://github.com/tahabelkhouja/SRS},
note = {arXiv:2207.04306 [cs]},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
Safe deployment of time-series classifiers for real-world applications relies on the ability to detect the data which is not generated from the same distribution as training data. This task is referred to as out-of-distribution (OOD) detection. We consider the novel problem of OOD detection for the time-series domain. We discuss the unique challenges posed by time-series data and explain why prior methods from the image domain will perform poorly. Motivated by these challenges, this paper proposes a novel textbackslashem Seasonal Ratio Scoring (SRS) approach. SRS consists of three key algorithmic steps. First, each input is decomposed into class-wise semantic component and remainder. Second, this decomposition is employed to estimate the class-wise conditional likelihoods of the input and remainder using deep generative models. The seasonal ratio score is computed from these estimates. Third, a threshold interval is identified from the in-distribution data to detect OOD examples. Experiments on diverse real-world benchmarks demonstrate that the SRS method is well-suited for time-series OOD detection when compared to baseline methods. Open-source code for SRS method is provided at https://github.com/tahabelkhouja/SRS
10.
Alexander You; Nidhi Parayil; Josyula Gopala Krishna; Uddhav Bhattarai; Ranjan Sapkota; Dawood Ahmed; Matthew Whiting; Manoj Karkee; Cindy M. Grimm; Joseph R. Davidson
An autonomous robot for pruning modern, planar fruit trees Inproceedings
In: arXiv, 2022, (arXiv:2206.07201 [cs]).
Abstract | Links | BibTeX | Tags: Labor
@inproceedings{you_autonomous_2022,
title = {An autonomous robot for pruning modern, planar fruit trees},
author = { Alexander You and Nidhi Parayil and Josyula Gopala Krishna and Uddhav Bhattarai and Ranjan Sapkota and Dawood Ahmed and Matthew Whiting and Manoj Karkee and Cindy M. Grimm and Joseph R. Davidson},
url = {http://arxiv.org/abs/2206.07201},
doi = {10.48550/arXiv.2206.07201},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
publisher = {arXiv},
abstract = {Dormant pruning of fruit trees is an important task for maintaining tree health and ensuring high-quality fruit. Due to decreasing labor availability, pruning is a prime candidate for robotic automation. However, pruning also represents a uniquely difficult problem for robots, requiring robust systems for perception, pruning point determination, and manipulation that must operate under variable lighting conditions and in complex, highly unstructured environments. In this paper, we introduce a system for pruning sweet cherry trees (in a planar tree architecture called an upright fruiting offshoot configuration) that integrates various subsystems from our previous work on perception and manipulation. The resulting system is capable of operating completely autonomously and requires minimal control of the environment. We validate the performance of our system through field trials in a sweet cherry orchard, ultimately achieving a cutting success rate of 58%. Though not fully robust and requiring improvements in throughput, our system is the first to operate on fruit trees and represents a useful base platform to be improved in the future.},
note = {arXiv:2206.07201 [cs]},
keywords = {Labor},
pubstate = {published},
tppubtype = {inproceedings}
}
Dormant pruning of fruit trees is an important task for maintaining tree health and ensuring high-quality fruit. Due to decreasing labor availability, pruning is a prime candidate for robotic automation. However, pruning also represents a uniquely difficult problem for robots, requiring robust systems for perception, pruning point determination, and manipulation that must operate under variable lighting conditions and in complex, highly unstructured environments. In this paper, we introduce a system for pruning sweet cherry trees (in a planar tree architecture called an upright fruiting offshoot configuration) that integrates various subsystems from our previous work on perception and manipulation. The resulting system is capable of operating completely autonomously and requires minimal control of the environment. We validate the performance of our system through field trials in a sweet cherry orchard, ultimately achieving a cutting success rate of 58%. Though not fully robust and requiring improvements in throughput, our system is the first to operate on fruit trees and represents a useful base platform to be improved in the future.
