| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | June 29, 2018 |
| Latest Amendment Date: | June 29, 2018 |
| Award Number: | 1820332 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Anna Brady-Estevez
TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | July 1, 2018 |
| End Date: | June 30, 2019 (Estimated) |
| Total Intended Award Amount: | $225,000.00 |
| Total Awarded Amount to Date: | $225,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1800 S OAK ST STE 111 CHAMPAIGN IL US 61820-6974 (217)402-4767 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
60 Hazelwood Drive Champaign IL US 61820-7460 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | SBIR Phase I |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.084 |
ABSTRACT
Broader Impacts: The broader impact of this Small Business Innovation Research (SBIR) project include improving food security, while at the same time enhancing the economic viability and environmental sustainability of large-scale production agriculture. In order to improve crop varieties, agricultural production, and sustainability of farming, there is an urgent need for better technologies to acquire under-canopy plant trait and health data. Examples of high-value under-canopy data include emergence, stem width, corn ear height, plant life-cycle events like flowering and fruiting, and symptoms of pathogens, diseases, and nutrient deficiency. Because these data cannot be obtained by aerial imaging, under-canopy data collection has dramatically greater actionability and value compared to aerial data. However no cost-effective, scalable ways of collecting this data are currently available. In fact, the state of the art is manual data collection by crop scientists (and their students or interns), agronomists, crop-scouts or farmers - an extremely labor intensive, and therefore expensive way of collecting this highly valuable data. Our work will greatly enhance the availability of under-canopy data from field crops. The commercial value of the field data for crop breeding is in excess of $50 Million/year for breeding major row-crops in the US.
Intellectual Merits: This SBIR Phase I project will demonstrate the technical feasibility of autonomously collecting under-canopy data from field crops using TerraSentia, our low-cost ground robot. In preliminary work, we have built the robot hardware, demonstrated its ability to collect high-value plant data from row-crop fields, and analyze it to generate plant-trait information. In the proposed work, we will enable and demonstrate the ability of TerraSentia to collect data autonomously throughout the season. We will demonstrate the technical feasibility of fusing information from low-cost LIDAR, GPS, and vision. We will also demonstrate the feasibility using real-time control algorithms to adapt camera perspective and robot path in order to obtain the highest quality information from the complex and dynamic under- canopy field environments. These high-risk innovations will together enable long-term deployment of TerraSentia for effective data collection and phenotyping, benefiting crop scientists and agricultural product development professionals.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
With SBIR Phase I funding, EarthSense has demonstrated the technical feasibility of the TerraSentia robotics and analytics platform to deliver large scale, under canopy, quantitative plant trait data for crop breeding and agricultural product research and development. Major corporations and public sector institutions currently spend over $250 Million per year on equipment, software, sensors, and most of all, manual labor on collecting field data. However, this data is incomplete, low-volume, and low-reliability.
This lack of data is called the "field phenotyping bottleneck". The inability to get large scale quantitative plant trait information from R&D fields is preventing us from significantly improving the yield and sustainability of agriculture. Yields of major crops -corn, soybean, wheat, rice, etc. - must double by 2050 in order to feed the global population. Unfortunately, we are on track to increase yields only by around 50%. This catastrophic shortfall is despite major seed companies spending over $6.5 Billion every year on product R&D, out of which over $250 Million is spent on field data collection. In large part, the current glacial rate of crop performance improvement is due to the field phenotyping bottleneck.
With SBIR Phase I support, EarthSense has successfully demonstrated the technical feasibility of using the TerraSentia platform to break through the field phenotyping bottleneck. Outcomes of the SBIR Phase I work include:
- Robust ultracompact TerraSentia robot that travels in row-crop fields
- Lidar or GPS based autonomous navigation in these fields
- Rapid collection of under-canopy, high volume, quantitative data with low-cost RGB cameras and 2D Lidars
- Analysis of these data on our cloud-hosted machine-learning algorithms
- Delivery of quantitative plant trait information to crop breeders
The unique datasets generated by TerraSentia at scale will enable development of new high yielding varieties of crops that require less water, chemicals, and other inputs; even as climate conditions become steadily unfavorable.
While our first target market is crop breeding, the unique data gathered by TerraSentia robots will also improve agricultural sustainability and productivity by enabling precision agriculture based on real-time, high-resolution, clearly actionable data. With clear, actionable insights derived from unique, under-canopy data collected by TerraSentia, farmers would detect diseases, nutrient deficiency, water stress etc. earlier and treat them far more efficiently.
To accelerate the path to market of the TerraSentia platform, EarthSense has marshaled other resources to supplement the SBIR Phase I support. These resources include sweat equity, revenues from pilot tests, and venture investment. These supplementary resources are being used for low-risk aspects of product development like web and tablet app development, industrial design, and manufacturing.
Ultimately, the mission at EarthSense is to enable sustainable abundance through intelligent machines. This SBIR Phase I funding has enabled us to lay the groundwork for long-term technical and product development that will enable large-scale adoption of environmentally and socially beneficial agricultural ecosystems enabled by robotics and machine learning products specifically designed for agriculture.
Last Modified: 08/19/2019
Modified by: Chinmay Soman
-
TerraSentia collects high-value, under canopy data with simple sensors. This data is used for accelerating the breeding of high-yeilding crops that require fewer fertilizers and chemicals and can thrive in stressful weather and degraded soils.EarthSense, Inc.Chinmay SomanTerraSentia - Field Phenotyping Robot
-
EarthSense has developed a suite of machine-learning and machine-vision algorithms that enable quantification of critical under-canopy traits of plants, including stem width, true leaf area index, corn ear height, soybean node count, flower count and others.EarthSense, Inc.Chinmay SomanStem Width Measurement
-
EarthSense has developed algorithms to reconstruct the 3D structure of crop canopies using data from low-cost 2D Lidars.EarthSense, Inc.Chinmay Soman3D Lidar Map
Please report errors in award information by writing to: awardsearch@nsf.gov.