Elliot Sadler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Elliot Sadler has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Bingbing Li
Autonomy Research Center for STEAHM (ARCS) California State University Northridge Northridge California United States
2 shared publications - Andreas George
Marilyn Magaram Center for Food Science, Nutrition, and Dietetics, California State University Northridge, USA
1 shared publication - Andrew Wang
Portola High School, USA
1 shared publication - Andrew Wang
Institute for Imaging, Data and Communications, School of Engineering, University of Edinburgh
1 shared publication - Annette Besnilian
Department of Family and Consumer Sciences, Marilyn Magaram Center for Food Science, Nutrition, and Dietetics, California State University, Northridge
1 shared publication - Anthony Manuel Morales-Badajoz
Autonomy Research Center for STEAHM (ARCS), California State University Northridge, USA
1 shared publication
Latest Publications
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 385-390
Astro Cultivators: Autonomous Growth System for Space Farming based on Machine Vision and Multi-Sensor Fusion
The autonomous space farming system could be used to grow self-pollinating crops in space exploration missions that require no human intervention. Our goal is to utilize hyper spectral imaging and traditional imaging to allow for machine learning models to be used and retrained for not only our crops, but others as well. Temperature, humidity, and pressure sensors coupled with a robotic arm will care and tend to the crops at every stage of development. This system can decrease crew members’ input needed to operate the plant growth systems in deep space by providing autonomous monitoring, real-time data reporting, ambient environment management, automatic harvesting, and cleaning. Crops with high nutrient content, high acceptability ratings, dwarf growth habits, and short harvest cycles (Sugar Ann Snap Peas and Red Robin Tomato) will initially be grown in this modular system which has the potential to be scale up or down, depending on the mission. A variety of “pick and eat” crops can be grown to provide palatable, safe, nutritious foods that are familiar foods for crews to consume. To reduce resupply from Earth, the seeds from these crops have the potential to be saved and used to grow continuous generations of crops.
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 385-390
Open AccessAstro Cultivators: Autonomous Growth System for Space Farming based on Machine Vision and Multi-Sensor Fusion
The autonomous space farming system could be used to grow self-pollinating crops in space exploration missions that require no human intervention. Our goal is to utilize hyper spectral imaging and traditional imaging to allow for machine learning models to be used and retrained for not only our crops, but others as well. Temperature, humidity, and pressure sensors coupled with a robotic arm will care and tend to the crops at every stage of development. This system can decrease crew members’ input needed to operate the plant growth systems in deep space by providing autonomous monitoring, real-time data reporting, ambient environment management, automatic harvesting, and cleaning. Crops with high nutrient content, high acceptability ratings, dwarf growth habits, and short harvest cycles (Sugar Ann Snap Peas and Red Robin Tomato) will initially be grown in this modular system which has the potential to be scale up or down, depending on the mission. A variety of “pick and eat” crops can be grown to provide palatable, safe, nutritious foods that are familiar foods for crews to consume. To reduce resupply from Earth, the seeds from these crops have the potential to be saved and used to grow continuous generations of crops.
- Open Access
Material Prediction for Design Automation Using Graph Representation Learning
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality designs by selecting the most appropriate materials through performance, manufacturability, and sustainability evaluation. Intelligent tools can help designers with varying expertise by providing recommendations learned from prior designs. To enable this, we introduce a graph representation learning framework that supports the material prediction of bodies in assemblies. We formulate the material selection task as a node-level prediction task over the assembly graph representation of CAD models and tackle it using Graph Neural Networks (GNNs). Evaluations over three experimental protocols performed on the Fusion 360 Gallery dataset indicate the feasibility of our approach, achieving a 0.75 top-3 micro-f1 score. The proposed framework can scale to large datasets and incorporate designers' knowledge into the learning process. These capabilities allow the framework to serve as a recommendation system for design automation and a baseline for future work, narrowing the gap between human designers and intelligent design agents.
Open AccessMaterial Prediction for Design Automation Using Graph Representation Learning
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality designs by selecting the most appropriate materials through performance, manufacturability, and sustainability evaluation. Intelligent tools can help designers with varying expertise by providing recommendations learned from prior designs. To enable this, we introduce a graph representation learning framework that supports the material prediction of bodies in assemblies. We formulate the material selection task as a node-level prediction task over the assembly graph representation of CAD models and tackle it using Graph Neural Networks (GNNs). Evaluations over three experimental protocols performed on the Fusion 360 Gallery dataset indicate the feasibility of our approach, achieving a 0.75 top-3 micro-f1 score. The proposed framework can scale to large datasets and incorporate designers' knowledge into the learning process. These capabilities allow the framework to serve as a recommendation system for design automation and a baseline for future work, narrowing the gap between human designers and intelligent design agents.