This report is no longer available. Click here to view our current reports or contact us to discuss a custom report.
If you have previously purchased this report then please use the download links on the right to download the files.
ARCHIVEAgricultural Robots, Drones, and AI: 2020-2040: Technologies, Markets, and Players
The future of farming; ultra precision farming; autonomous farming; artificial intelligence; machine vision; mobile robots; autonomous tractors.
Show All
Description
Contents, Table & Figures List
FAQs
Pricing
Related Content
The developments in agricultural robotics, machine vision, and AI will drive a deep and far-reaching transformation of the way farming is carried out. Yes, today the fleet sizes and the total area covered by new robots are still vanishingly small compared to the global agricultural industry. Yet, this should not lull the players into a false sense of security because the ground is slowly but surely shifting. Robotics and AI are enabling a revolution in affordable ultraprecision, which will eventually upend familiar norms in agrochemical supply, in agricultural machine design, and in farming practices.
This development frontier has the wind in its sails, pushed by rapidly advancing and sustainable hardware and software technology trends, and pulled by structural and growing challenges and needs. In our assessment, these technology developments can no longer be dismissed as gimmicks or too futuristic. They are here to stay and will only grow in significance. Indeed, all players in the agricultural value chain will need to develop a strategy today to benefit from, or at least to safeguard against, this transformative trend.
This report provides the following:
1. Application assessment and market forecasts: this report analyses all the emerging product types. It offers short- and long-term market forecasts, considering the addressable market size in area or tons and value, penetration rates, annual robot sales, accumulated fleet sizes, total RaaS (robot as a service) revenue projections and so on. Note that we built a twenty-year model because our technology roadmap suggests that these changes will take place over long timescales.
The forecasts cover 15 robot types and farming sectors. More specifically, these include the following: autonomous ultra-precision robots, intelligent vision-enabled robotic implements, simple robotic implements, fresh fruit and citrus harvesting robots, fresh berry harvesting robots, highly automated and autonomous tractors and high-power farm vehicles (levels 3, 4 and 5), imaging and spraying drones, automatic milking, mobile robots in dairy farming and others.
A detailed application assessment covering dairy farms, fresh fruit harvesting, organic farming, crop protection, data mapping, seeding, vertical farming, and so on. For each application/sector, a detailed overview of the existing industry is given, the needs for and the challenges facing the robotic technology are analysed, the addressable market size is estimated, and granular ten-year market projections are given.
2. Technology assessment and roadmap: Agriculture is still largely non-automated and non-digitized. This has been mainly because the technological deficiencies have so far held back automation. This is, however, changing, largely (but not exclusively) thanks to leaps in four core technologies: (1) CNN-based machine vison and AI, (2) autonomous mobility, (3) electric drive and powertrains; and (4) affordable and robust robotic arms.
This report provides a detailed technology assessment covering all the key robotic/drone projects, prototypes, and commercial products relevant to the agricultural sector. The report details the increasing role that deep learning-based image recognition plays in enabling an affordable ultraprecision revolution. Furthermore, the report also outlines the state-of-the-art in the use of AI in agriculture beyond image recognition in applications such as localization, yield prediction, and disease detection.
The report also considers the trend towards autonomous mobility in small and large as well as ground and aerial machines. It examines perception and sensor technologies such as RTK-GPS, camera and Lidars needed in achieving autonomy in various environments. On this hardware aspect, the report considers long-term price and performance trends in transistors, memory, energy storage, electric motors, GPS, cameras, and MEMS technology. The key role of innovative end effectors, precision actuators, and robotic arms in fresh fruit harvesting, precision weeding, and automatic dairy farming is analysed. The report also highlights the role that power train electrification is playing, especially in enabling drones and novel small- and mid-sized autonomous robots.
3. Company profiles analysis: All key companies and research entities are overviewed. The readiness level of firms and their products are benchmarked. The business models, target markets, product details, development roadmaps, etc are discussed. The report provides a complete view of the competitive landscape.
Agricultural robots: a cost-effective ultraprecision revolution?
These are often small or mid-sized robots which are designed to autonomously navigate and to automatically take some precise plant-specific action (see examples below).
Machine vision technology is a core competency, enabling the robots to see, identify, localise, and to take some intelligent site-specific action on individual plants. The machine vision increasingly uses deep learning algorithms often trained on expert-annotated image datasets, allowing the technology to far exceed the performance of conventional algorithms and even at times expert agronomists. Crucially, this approach enables a long-term technology roadmap, which can be extended to recognize all types of crops and to analyse their associated conditions, e.g., water-stress, disease, etc.
Many versions of this emerging robotic class are autonomous. The autonomy challenge is incomparably simpler than a car. The legislation is today a hinderance, including in places such as California, but will become more accommodative relatively soon.
The rise of autonomous robots, provided they require little remote supervision, can alter the economics of machine design, enabling the rise of smaller and slower machines. Indeed, this elimination of the driver overhead per vehicle is the basis of the swarm concept. There is clearly a large productivity gap today between current large and high-power vehicles and those composed of fleets of slow, small robots. This productivity gap, however, can only narrow as the latter has substantial room for improvement even without a breakthrough or radical innovation.
The first major target market is in weeding. The ROI benefits here are driven by labour savings, chemical savings, boosted yields, and less soil compaction. Precision action (spraying, mechanical, or electrical) reduces consumption of agrochemicals, e.g., by 90%, and boosts yield by cutting herbicide-induced collateral damage, e.g., by 5-10%. This technology can further enable farmers to tackle herbicide-resistant weeds and leave behind no unusable compacted soil.
These robots are evolving. Many robots have already grown in size and capability since the earlier days, today offering faster speeds, higher frame-per-seconds, more ruggedized designs, higher on-board energy for longer operation time and a heavier load, and etc. This hardware and machine vision evolution will inevitably continue, just as with all other agricultural tools and vehicles. We are still at the beginning. The deployed fleet sizes worldwide are small, but this is about to dramatically change.
Examples of past and present autonomous agricultural robots. The image panel is not intended to be a comprehensive representation of all prototypes and products.
Intelligent robotic implements: the inevitable next generation of agricultural tools
Simple robotic implements utilising basic row-following vision technology are already mature and not uncommon in organic farms. Advances in vision technology are transforming tractor-pulled implements though, upgrading them into intelligent computerized tools able to take plant-specific precise action.
The core technology here is also the machine vision, which enables the identification and the localization of specific plants. The algorithms already surpass the capabilities of agronomists in specific cases, e.g., weed amongst cotton. Crucially, the systems are becoming ever more productive, closing the productivity gap with established technology. A leading product is a 40ft wide implement which is pulled at 12mph and covers 12 rows of crops. This system achieves 2-inch resolution and 20 fps imaging, deploying 30 cameras and 25 on-board GPUs.
This approach does not focus on autonomy, although the tractor itself can readily be made autonomous to render the entire system automatic if needed. This system is designed to become competitive in large farms, which demand high productivity, which in turn is linked to technology parameters such as fps (frame per second), false positives, sprayer controller speed, and so on. In the future, the system costs will likely fall, particularly if lighter versions of the algorithms on the inference side become available to render GPU processors unessential without a major performance sacrifice.
This image is the evolution of Blue River's (now John Deere) machine over the years, showing how the implement has evolved from a prototype to become rugged and productive.
Autonomous tractors and high-power vehicles: fewer but more autonomous systems will be the future?
Autonomous navigation is not new to tractors. Thanks to RTK-GPS, tractors have long been benefiting from tractor guidance and autosteer. The latter is in fact level-4 autonomy since the tractor can autonomously drive outdoors along pre-determined GPS coordinates without human intervention. The cost of implementation as well as the adoption of such technologies has increased. In short, the technical challenge does not hinder deployment.
Level-5 or fully autonomous tractors have also been demonstrated for some years. The technical barrier here is low. The determining factors here are farmer perception and added value. The additional cost incurred in going from level-4 to level-5 will not justify the additional benefits until level-5 can enable many new possibilities. This means that more tasks, and not just movement, should become automated.
The rise of autonomous mobility is also giving rise to novel designs. Some examples are shown in the panel below. In particular, the weight distribution can be altered without scarifying the horsepower, helping alleviate soil compaction issues. In the longer term, though, other agricultural robots will eat into the tasks that tractors perform today, potentially denting overall demand.
Robotic fresh fruit picking: is it technically and commercially viable?
Fresh fruit picking is still largely manual as deficient technical ability had thus far held automation back. As such, farms are faced with high harvesting costs and are, more importantly, grappling with the growing challenge of assembling sufficiently large armies of seasonal pickers. Is this about to change?
Today machine vision technology can identify and localize different visible fruits against complex and varying backgrounds with a high success rate. The rise of deep learning-based image recognition technologies has caused a leap in performance. Crucially, a clear pathway exists for algorithm development for new fruit-environment combinations, enabling the applicability of machine detection and localization to be extended to many fruits. The robotic path planning, picking strategy and the motion control of the robotic arm are also challenges. Here, too, there are algorithmic improvements. More importantly, companies are developing novel end-effectors which can accelerate gentle fresh fruit picking whilst lightening the computational load.
Humans today are still faster- e.g., 2-3s per picked strawberry vs 8-10s for the robot. This speed gap will almost certainly narrow in the future, lowering the comparative advantage of humans. In addition, robots can have many arms, compensating for the slowness of each arm (both articulated and delta arms are deployed). The key to commercial success lies in the development of robust robotic and associated AI platforms which can be utilized across the harvesting season of different crops.
The total deployed number of units is small, thus the robotically harvested amount of fresh fruit is still vanishingly small compared to the addressable market. However, the technical viability is long proved. The emphasis is now in bridging the productivity gap to offer a reliable solution with reasonable ROI compared with the incumbent human picking. Importantly, there is still ample room to boost productivity and applicability by making constant incremental gains. As such, no breakthrough is required, making it more a question when and not if.
Examples of robots automatically harvesting apples, strawberries, etc.
Drones
Drones are an increasingly common tool. Currently remote-controlled consumer or prosumer drones are utilized for aerial image acquisition. They have helped reduce the acquisition cost and the resolution of aerial farm images, making the technology accessible to all manner of farmers. Indeed, the hardware platform is now widely available. Note that the business landscape on the platform side has gone through a brutal consolidation phase, establishing the winning supplier and design.
Attention has been increasingly shifting to software and service. Indeed, many firms are in parallel offering the data analytics, starting from simple indexes such as NDVI and progressing to more complex analytics. Aerial drone-based sprayers have also been launched. These however remain currently niche.
Note that the use of unmanned aerial technology is not just limited to drones. Indeed, unmanned remote-controlled helicopters have already been spraying rice fields in Japan since early 1990s. This is a maturing technology/sector with overall sales in Japan having plateaued. This market may however benefit from a new injection of life as suppliers diversify into new territories
Dairy farming
Automated milking has been in the making for 25 years. The technology is already proven with high and growing installations worldwide. Indeed, this multi-billion market is showing high annual growth rates. An important enabling innovation was the development of (1) a robust robotic arm that could survive when, for example, crushed by the animal, and (b) a teat localization mechanism (often based on measuring the change in a projected pattern). In parallel to fixing automatic milking assets, heavy mobile robots acting as automatic feed pushers are also gaining further popularity.
Analyst access from IDTechEx
All report purchases include up to 30 minutes telephone time with an expert analyst who will help you link key findings in the report to the business issues you're addressing. This needs to be used within three months of purchasing the report.
Further information
If you have any questions about this report, please do not hesitate to contact our report team at research@IDTechEx.com or call one of our sales managers:
ASIA: +82 10 3896 6219
| 1. | EXECUTIVE SUMMARY |
| 1.1.1. | What is this report about? |
| 1.1.2. | Growing population and growing demand for food |
| 1.1.3. | Major crop yields are plateauing |
| 1.1.4. | Employment in agriculture |
| 1.1.5. | Global evolution of employment in agriculture |
| 1.1.6. | Aging farmer population |
| 1.1.7. | Trends in minimum wages globally |
| 1.1.8. | Towards ultra precision agriculture via the variable rate technology route |
| 1.1.9. | Towards better disease prevention, yield prediction, and quality management |
| 1.1.10. | Key enabling technologies of the future |
| 1.1.11. | Ultra Precision farming will cause upheaval in the farming value chain |
| 1.1.12. | Agricultural robotics and ultra precision agriculture will cause upheaval in agriculture's value chain |
| 1.1.13. | Agriculture is one of the last major industries to digitize: a look at investment in data analytics/management firms in agricultural and dairy farming |
| 1.1.14. | The battle of business models between RaaS and equipment sales |
| 1.1.15. | Transition towards swarms of small, slow, cheap and unmanned robots |
| 1.1.16. | Robots and drones: market and technology readiness by agricultural activity |
| 1.1.17. | Robotic product classes used in our forecasts and analysis |
| 1.1.18. | Technology readiness level of different companies |
| 1.1.19. | Technology progression towards driverless autonomous large-sized tractors |
| 1.1.20. | Technology progression towards autonomous, ultra precision de-weeding |
| 1.1.21. | Technology and progress roadmap for robotic fresh fruit harvesting |
| 1.1.22. | Different areas in agriculture into which machine learning penetrates |
| 1.1.23. | Machine learning in agriculture: research state of the art |
| 1.1.24. | Definition of AI abbreviations |
| 1.1.25. | Various algorithm types: definitions |
| 1.1.26. | Data, model, and results are correlated |
| 1.1.27. | Evolution of model leads to the evolution of capability |
| 1.1.28. | Products are maturing |
| 1.1.29. | AI and robotics to enable ultra precision agriculture |
| 1.1.30. | Electric vs non-electric autonomous agricultural robots. |
| 1.1.31. | Categorising firms by location, type of robot, level of autonomy, power source, technology readiness level, and function |
| 1.1.32. | Categorising firms by location, type of robot, level of autonomy, power source, technology readiness level, and function |
| 1.1.33. | Summary of market forecasts |
| 1.1.34. | Autonomous small and mid-sized robots in data collection, precision weeding, precision pruning, etc: 2020 to 2040 market forecasts |
| 1.1.35. | Autonomous small and mid-sized robots: penetration rate into the addressable market |
| 1.1.36. | Autonomous small and mid-sized robots: accumulated fleet size and annual sales |
| 1.1.37. | Intelligent robotic implements: 2020 to 2040 market forecasts |
| 1.1.38. | Intelligent robotic implements: penetration rate into the addressable market |
| 1.1.39. | Intelligent robotic implements: accumulated fleet size and annual sales |
| 1.1.40. | Simple robotic implements: 2020 to 2040 market forecasts |
| 1.1.41. | Highly automated and autonomous tractors: 2020 to 2040 market forecasts |
| 1.1.42. | Robotic fresh fruit and citrus harvesting: 2020 to 2040 market forecasts |
| 1.1.43. | Addressable market for fresh fruit and citrus harvesting (apples, grapes, pears, lemons, grapefruit, tangerines, oranges) |
| 1.1.44. | Robotic fresh fruit and citrus harvesting |
| 1.1.45. | Robotic fresh fruit and citrus harvesting: productivity |
| 1.1.46. | Robotic fresh fruit and citrus harvesting: accumulated fleet size and annual sales |
| 1.1.47. | Robotic fresh berry and similar fruit harvesting: 2020 to 2040 market forecasts |
| 1.1.48. | Robotic fresh berry and similar fruit harvesting: accumulated fleet size and annual sales |
| 1.1.49. | Imaging and spraying drones in agriculture: 2020 to 2040 market forecasts |
| 1.1.50. | Robotic milking is already a major market: 2018:2038 market forecasts |
| 2. | AUTONOMOUS MOBILITY FOR LARGE TRACTORS |
| 2.1. | Number of tractors sold globally |
| 2.2. | Value of crop production and average farm sizes per region |
| 2.3. | Revenues of top agricultural equipment companies |
| 2.4. | Overview of top agricultural equipment companies |
| 2.5. | Tractor Guidance and Autosteer Technology for Large Tractors |
| 2.6. | Autosteer for large tractors |
| 2.7. | Ten-year forecasts for autosteer tractors |
| 2.8. | Master-slave or follow-me large autonomous tractors |
| 2.9. | Fully autonomous driverless large tractors |
| 2.10. | Fully autonomous unmanned tractors |
| 2.11. | New Holland Autonomous Tractor |
| 2.12. | Precision Makers |
| 2.13. | Agrointellli: developing autonomous high horse-power agricultural vehicles |
| 2.14. | Handsfree Hectar: fully autonomous human-free barley farming |
| 2.15. | Technology progression towards driverless autonomous large-sized tractors |
| 2.16. | Tractors evolving towards full autonomy: 2018-2038 market forecasts in unit numbers segmented by level of navigational autonomy |
| 2.17. | Tractors evolving towards full autonomy: 2018-2038 market forecasts in market value segmented by level of navigational autonomy |
| 2.18. | Tractors evolving towards full autonomy: 2018-2038 market forecasts segmented by level of navigational autonomy (value of automation only) |
| 3. | AUTONOMOUS ROBOTIC AGRICULTURAL PLATFORMS |
| 3.1.1. | Autonomous small-sized agricultural robots |
| 3.1.2. | FENDT (AGCO) launches swarms of autonomous agrobots |
| 3.1.3. | Autonomous agricultural robotic platforms |
| 3.1.4. | IdaBot: autonomous agricultural robotic platforms |
| 3.1.5. | Augen Robotics: autonomous vision-navigated mobile platform or transporter |
| 3.1.6. | Octinion: autonomous mobile platform and robotic strawberry picking |
| 3.2. | Artificial intelligence in crop yield prediction |
| 3.2.1. | Content outline |
| 3.2.2. | Artificial intelligence in crop yield prediction: summary and conclusions |
| 3.2.3. | Types of crop prediction |
| 3.2.4. | Yield prediction: summary of algorithms used and results obtained |
| 3.2.5. | Yield prediction: a shift from other methods to neural network-based method |
| 3.2.6. | Trends: (a) from large-data based to Image based methods and (b) from massive to site-specific crop yield prediction |
| 3.3. | Artificial intelligence in crop yield prediction: review |
| 3.3.1. | Grassland biomass estimation using spectrography |
| 3.3.2. | Biomass estimation process |
| 3.3.3. | Biomass estimation results |
| 3.3.4. | What is MODIS? |
| 3.3.5. | Wheat yield prediction |
| 3.3.6. | Wheat yield prediction materials and method |
| 3.3.7. | General crop yield prediction based on ensemble learning |
| 3.3.8. | Ensemble learning results are best in prediction of general crop yield |
| 3.3.9. | Rice development stages prediction |
| 3.3.10. | What is included in rice development stage and yield prediction? |
| 3.3.11. | Cloud-Based Agricultural Framework for Soil Classification and Crop Yield Prediction as a Service |
| 3.3.12. | Rapid yield prediction in paddy fields based on 2D image modelling of rice panicles |
| 3.3.13. | Procedure and method |
| 3.3.14. | Crop yield prediction with deep convolutional neural networks |
| 3.3.15. | Network used and the procedure |
| 3.3.16. | Artificial Neural Network-Based Crop Yield Prediction Using NDVI, SPI, VCI Feature Vectors |
| 3.3.17. | Method and result |
| 3.3.18. | Soybean yield prediction from UAV using multimodal data fusion and deep learning |
| 3.3.19. | Hardware and network model |
| 4. | AUTONOMOUS ROBOTIC WEED KILLING |
| 4.1. | From manned, broadcast towards autonomous, ultra precision de-weeding |
| 4.2. | Crop protection chemical sales per top suppliers globally |
| 4.3. | Sales of top global and Chinese herbicide suppliers |
| 4.4. | Global herbicide consumption data |
| 4.5. | Glyphosate consumption and market globally |
| 4.6. | Regulations will impact the market for robotic weed killers? |
| 4.7. | Glyphosate banning state in the world now |
| 4.8. | Penetration of herbicides in different field crops |
| 4.9. | Growing challenge of herbicide-resistant weeds |
| 4.10. | Glyphosate is no longer as effective as it was |
| 4.11. | In almost all major crops, weeds are showing resistance |
| 4.12. | Autonomous weed killing robots |
| 4.13. | Autonomous robotic weed killers |
| 4.14. | EcoRobotix: energy-independent autonomous precision weeder |
| 4.15. | EcoRobotix: precision positioning and spraying |
| 4.16. | EcoRobotix: deep learning for crop and weed recognition |
| 4.17. | EcoRobotix: target markets |
| 4.18. | EcoRobotix: autonomous mobility |
| 4.19. | EcoRobotix: next generation of products |
| 4.20. | Adigio: autonomous weeding machine with precision sprayer and DNN-based week detection |
| 4.21. | Small Robot Company: supporting the rise of small autonomous agricultural robots |
| 4.22. | Small Robot Company: going from robotic data acquisition and mapping to precision weeding and planning |
| 4.23. | Earthsense: from autonomous data analytics robots to precision weeders |
| 4.24. | Naio Technologies: autonomous large-sized mechanical weeding robot |
| 4.25. | Agerris: autonomous robot with an AI suite |
| 4.26. | Farmwise: autonomous precision weeding (robot and AI) |
| 4.27. | DeepField Robotics: a Bosch start-up |
| 4.28. | Deepfield Robotics: cloud-based data management |
| 4.29. | Deepfield Robotics: machine vision technology |
| 4.30. | Deepfield Robotics: autonomous non-chemical precision weeding |
| 4.31. | Organic farming |
| 4.32. | Organic farming and market potential for robotic weed killing |
| 4.33. | Carre: autonomous mechanical in-row weeding |
| 4.34. | Robotic in-row mechanical weeding implements for organic farming |
| 4.35. | Robotic mechanical weeding for organic farming |
| 4.36. | Technology progression towards autonomous, ultra precision de-weeding |
| 5. | ROBOTIC IMPLEMENTS: WEEDING, VEGETABLE THINNING, AND HARVESTING |
| 5.1.1. | Autonomous lettuce thinning robots |
| 5.1.2. | Blue River Tech ( now John Deere): see and spray |
| 5.1.3. | Blue River Tech (now John Deere): machine vision and machine learning |
| 5.1.4. | Blue River Tech (now John Deere): evolution of the machinery |
| 5.1.5. | Blue River Tech (now John Deere): business model |
| 5.1.6. | Blue River Tech (now John Deere): long-term vision |
| 5.1.7. | Why asparagus harvesting should be automated |
| 5.1.8. | Automatic asparagus harvesting |
| 5.1.9. | Robotic/Automatic asparagus harvesting |
| 5.1.10. | Robotic/Automatic asparagus harvesting |
| 5.2. | Artificial intelligence in weed (and other object) detection |
| 5.2.1. | Content outline |
| 5.3. | Artificial intelligence in weed (and other object) detection: summary and conclusion |
| 5.3.1. | Trend: a shift from SVM to SOM and to CNN and then to special CNNs in weed and other image object detection tasks |
| 5.3.2. | The evolution from binary classification to cloud based applications |
| 5.4. | Artificial intelligence in weed (and other object) detection: review |
| 5.4.1. | Rumex and Urtica detection in grassland with different machine learning algorithms |
| 5.4.2. | Which algorithm performs better in Rumex and Urtica detection |
| 5.4.3. | Results of different scenarios for Rumex and Urtica detection |
| 5.4.4. | UAS based imaging for Silybum marianum detection by self organizing maps |
| 5.4.5. | Data specs and procedure |
| 5.4.6. | S. Marianum recognition accuracy by self organizing maps |
| 5.4.7. | Self organizing map with active learning to detect 11 different weed types from each other and plant |
| 5.4.8. | Sensors, features, and procedure for weed type detection |
| 5.4.9. | Results of different active-learned one-class classifier on classifying weed types |
| 5.4.10. | Weed location and recognition based on UAV imaging and deep learning |
| 5.4.11. | What kind of Deep network is YOLO |
| 5.4.12. | Vegetation detection and discrimination within vegetable plasticulture row-middles using a convolutional neural network |
| 5.4.13. | Deep localization model for intra-row crop detection in paddy field |
| 5.4.14. | Proposed architecture in use |
| 5.4.15. | Deep convolutional neural networks for image based Convolvulus sepium detection in sugar beet fields |
| 5.4.16. | The structure of network and results |
| 5.4.17. | Transfer learning between crop types for semantic segmentation of crops versus weeds in precision agriculture |
| 5.4.18. | Network structure and results |
| 5.5. | Artificial intelligence in crop disease detection |
| 5.5.1. | Artificial intelligence in crop disease detection: summary and conclusions |
| 5.5.2. | Technology trend: from a single disease detection to nutrient or water stress detection to 58 plant-disease combinations detection |
| 5.5.3. | Trend: from hyperspectral images to RGB only images and from SVM to SOM to deep learning and convolutional deep learning |
| 5.5.4. | Content outline |
| 5.6. | Artificial intelligence in crop disease detection: literature review |
| 5.6.1. | More than 99% accuracy in detecting yellow rust infected wheat |
| 5.6.2. | Process and model for yellow rust infected wheat detection |
| 5.6.3. | Fluorescence and spectral imaging for yellow rust detection by Kohonen maps |
| 5.6.4. | Kohonen performs much better |
| 5.6.5. | Optical discrimination between healthy and water stressed wheat canopies |
| 5.6.6. | Fused spectral reflectance and fluorescence features are better for both binary and multiclass classification |
| 5.6.7. | Detecting Microbotryum Silybum infected plants by hierarchical self organizing maps |
| 5.6.8. | Contaminated rice seed detection |
| 5.6.9. | Feature selection and training method |
| 5.6.10. | Good features are selected for S. marianum health state recognition |
| 5.6.11. | Vision-based pest detection based on SVM |
| 5.6.12. | Pest detection classification method |
| 5.6.13. | Wheat crop biotic and abiotic stress detection |
| 5.6.14. | 95% accurate detection of stresses in wheat plant by self organizing map based classifiers |
| 5.6.15. | General plant healthy and diseased state detection with deep convolutional neural network |
| 5.6.16. | 58 classes of [plant, disease] to be detected by deep learning |
| 5.6.17. | Seasonal Crops Disease Prediction and Classification Using Deep Convolutional Encoder Network |
| 5.6.18. | Network architecture and results |
| 5.6.19. | Machine vision-based automatic disease symptom detection of onion downy mildew |
| 5.6.20. | Network structure and method and results |
| 5.6.21. | Mathematical and Visual Understanding of a Deep Learning Model Towards m Agriculture for Disease Diagnosis |
| 5.6.22. | The models compared and model selection strategy |
| 5.7. | Robotic spraying |
| 5.7.1. | Guss: autonomous robotic sprayers for permanent crops |
| 5.7.2. | Guss: key drivers of adoption |
| 5.7.3. | Guss: navigation technology |
| 5.7.4. | Guss: market, price, unit sales, etc. |
| 5.7.5. | Guss: future roadmap |
| 5.7.6. | Autonomous weed killing robots |
| 5.7.7. | Swarm Farm Robotics: moving platform into orchard spraying |
| 5.7.8. | Jacto: autonomous spray vehicles |
| 6. | ROBOTIC FRESH FRUIT PICKING |
| 6.1.1. | Field crop and non-fresh fruit harvesting is largely mechanized |
| 6.1.2. | Fresh fruit picking remains largely manual |
| 6.1.3. | Machining aiding humans in fresh fruit harvesting have not evolved in the past 50 years |
| 6.1.4. | Emerging robotic fresh fruit harvest assist technologies |
| 6.1.5. | Robot orchard data scouts and yield estimators |
| 6.1.6. | Emerging robotic fresh fruit harvest assist technologies |
| 6.1.7. | Robotic fresh apple harvesting |
| 6.1.8. | Robotic fresh citrus harvesting |
| 6.1.9. | Fresh fruit harvesting robots |
| 6.1.10. | Fresh Fruit Robotics: system evolution and current design |
| 6.1.11. | Fresh Fruit Robotics: business model and future product roadmap |
| 6.1.12. | Abundant Robotics: RaaS, at least for now |
| 6.1.13. | Technology and progress progression roadmap for robotic fresh fruit harvesting |
| 6.1.14. | Agrobot: Robotic fresh strawberry harvesting |
| 6.1.15. | Harvest Croo: Evolution of fresh strawberry harvesting robots |
| 6.1.16. | Octinion: autonomous mobile platform and robotic strawberry picking |
| 6.1.17. | Fully autonomous strawberry picking robots with soft grippers |
| 6.1.18. | Dogtooth: robotic arm on an autonomous platform to pick fresh, grade and pack fresh berries |
| 6.1.19. | Traptic: open field robotic strawberry pickers offered as RaaS |
| 6.1.20. | Advanced Farm Robotics: open field strawberry or similar picking |
| 6.2. | Artificial intelligence in crop detection, counting, and localization |
| 6.2.1. | Coffee fruit: counting and predicting ripeness state |
| 6.2.2. | Coffee fruit counting method |
| 6.2.3. | Green citrus identification using support vector machine |
| 6.2.4. | Citrus identification flowchart |
| 6.2.5. | Sweet cherry branch detection to automate shake-and-catch picking |
| 6.2.6. | How cherry branch is detected |
| 6.2.7. | Tomato detection via drone images and AI clustering |
| 6.2.8. | How tomato gets detected |
| 7. | VINE PRUNING ROBOTS |
| 7.1. | Autonomous robotic vineyard scouts and pruners |
| 7.2. | Vision Robotics Cop: Advanced vision systems in agricultural robotics |
| 7.3. | Fieldwork Robotics |
| 8. | GREENHOUSES AND NURSERIES |
| 8.1. | The problem with agriculture |
| 8.2. | Is vertical farming the answer? |
| 8.3. | Components of a vertical farm |
| 8.4. | Vertical farming vs other production methods |
| 8.5. | The argument against vertical farming |
| 8.6. | The argument for vertical farming |
| 8.7. | Investments in vertical farming |
| 8.8. | What crops do vertical farms grow? |
| 8.9. | Vertically farmed produce has a cost premium |
| 8.10. | Automation levels in vertical farming |
| 8.11. | Automation is not yet widespread in vertical farming |
| 8.12. | Technology adoption in vertical farming |
| 8.13. | Automation: environmental control |
| 8.14. | Autogrow |
| 8.15. | Priva |
| 8.16. | Automation: nutrient control |
| 8.17. | Imagination Garden |
| 8.18. | Automation: light recipes |
| 8.19. | Bowery Farming |
| 8.20. | Taking automation beyond level 2 |
| 8.21. | Logiqs |
| 8.22. | Is automation worth it? |
| 8.23. | Intelligent Growth Solutions |
| 8.24. | SananBio US |
| 8.25. | What could automation provide? |
| 8.26. | Autonomous robotics for greenhouses and nurseries |
| 9. | ROBOTIC SEEDERS |
| 9.1. | Variable rate technology for precision seed planting |
| 9.2. | Robotic seed planting |
| 10. | ROBOTIC DAIRY FARMING |
| 10.1. | Global trends and averages for diary farm sizes |
| 10.2. | Global number and distribution of dairy cows by territory |
| 10.3. | Robotic milking parlours |
| 10.4. | Overview of robotic milking parlours |
| 10.5. | Autonomous robotic feed pushers |
| 10.6. | Alternatives to autonomous robotic feed pushers |
| 10.7. | Autonomous robotic shepherds |
| 10.8. | Autonomous manure cleaning robots |
| 11. | AERIAL DATA COLLECTIONS AND DRONES |
| 11.1. | Drones: dominant designs begin to emerge |
| 11.2. | Drones: moving past the hype? |
| 11.3. | Drones: company formation slows down |
| 11.4. | Drones: global geographical spread of companies |
| 11.5. | Drones: platforms commoditize? |
| 11.6. | Drones: market forecasts |
| 11.7. | Drones: application pipeline |
| 11.8. | Satellite vs. plane vs drone mapping and scouting |
| 11.9. | Benefits of using aerial imaging in farming |
| 11.10. | Unmanned drones in rice field pest control in Japan |
| 11.11. | Unmanned drones and helicopters for field spraying |
| 11.12. | Unmanned agriculture drones on the market |
| 11.13. | Comparing different agricultural drones on the market |
| 11.14. | Regulation barriers coming down? |
| 11.15. | Agricultural drones: the emerging value chain |
| 11.16. | Core company information on key agricultural drone companies |
| 11.17. | Software opportunities: Vertical focused actionable analytics |
| 11.18. | Drones: increasing autonomy |
| 12. | ENABLING TECHNOLOGIES: GRIPPER TECHNOLOGY |
| 12.1. | Suction-based end effector technologies for fresh fruit harvesting |
| 12.2. | Simple and effective robotic end effectors for fruit harvesting |
| 12.3. | Soft robotics based end effector technologies for fresh fruit handling |
| 12.4. | Pneumatic soft actuator: extensible layer + fiber |
| 12.5. | Soft actuator: self-contained McKibbern-type muscle |
| 12.6. | Shape Deposition Manufacturing (SDM) Compliant Joint |
| 12.7. | Fabrication processes for soft robotic actuators |
| 12.8. | Robotic end effector technologies for fresh fruit harvesting |
| 12.9. | Robotic end effector technologies for fresh fruit harvesting |
| 12.10. | Dexterous robotic hands for agricultural robotics |
| 12.11. | Examples of dexterous robotic hands |
| 13. | ENABLING TECHNOLOGIES: NAVIGATIONAL TECHNOLOGIES (RTK, LIDAR, LASERS AND OTHERS) |
| 13.1.1. | RTK systems: operation, performance and value chain |
| 13.1.2. | Lidar- basic operation principles |
| 13.1.3. | Review of LIDARs on the market or in development |
| 13.1.4. | Performance comparison of different LIDARs on the market or in development |
| 13.1.5. | Assessing suitability of different LIDAR for agricultural robotic applications |
| 13.1.6. | Hyperspectral image sensors |
| 13.1.7. | Hyperspectral imaging and precision agriculture |
| 13.1.8. | Hyperspectral imaging in other applications |
| 13.1.9. | Hyperspectral imaging sensors on the market |
| 13.1.10. | Common multi-spectral sensors used with agricultural drones |
| 13.1.11. | GeoVantage |
| 13.2. | Enabling technologies: long-term price and performance trends in key hardware components (transistors, memory, camera, MEMS, GPS, batteries, electric motors, etc.) |
| 13.2.1. | Why is new robotics becoming possible now? A hardware point of view |
| 13.2.2. | Why is new robotics possible now? |
| 13.2.3. | Transistors (computing): price evolution |
| 13.2.4. | Transistors (computing): performance evolution |
| 13.2.5. | Memory (RAM, hard driver and flash): price evolution in $/Mbit |
| 13.2.6. | Memory: performance evolution in Gbit/ sq inch |
| 13.2.7. | Sensors (Camera): price evolution |
| 13.2.8. | Sensors (MEMS): price evolution |
| 13.2.9. | Sensors (GPS): price and market adoption (in unit numbers) evolution of GPS sensors |
| 13.2.10. | Is Lidar on a similar path as other robotic sensor technologies? |
| 13.2.11. | Li ion battery: performance evolution in Wh/Kg and Wh/L |
| 13.2.12. | Energy storage technologies: price evolution in $/kWh by sector |
| 13.2.13. | Electric motors: evolution of size of a given output since 1910 |
| 13.3. | Enabling Technology: Software, deep learning and big data |
| 13.3.1. | Artificial intelligence: waves of development |
| 13.3.2. | Terminologies explained: AI, machine learning, artificial neural networks, deep neural networks |
| 13.3.3. | Rising interesting in deep learning |
| 13.3.4. | Algorithm training process in a single layer |
| 13.3.5. | Towards deep learning by deepening the neutral network |
| 13.3.6. | The main varieties of deep learning approaches explained |
| 13.3.7. | Evolution of deep learning |
| 13.3.8. | The rise of the big data quantified: fuel for deep learning applications |
| 13.3.9. | Examples of milestones in deep learning AI: word recognition supresses human level |
| 13.3.10. | Examples of milestones in deep learning AI: image recognition supresses human level |
| 13.3.11. | Deepening the neutral network to increase accuracy rate |
| 13.3.12. | GPUs: an enabling component for deep learning? |
| 13.3.13. | Examples of milestones in deep learning AI: translation approaching human level performance |
| 13.3.14. | Examples of milestones in deep learning AI: leap in progress in robotic grasping |
| 13.3.15. | What is 'good enough' accuracy in deep learning? |
| 13.3.16. | RoS and RoS-I: major open source movement slashing development costs and enticing OEMs to finally engage |
| 13.3.17. | Robotic Operating System (RoS): Examples of cutting edge projects |
| 14. | COMPANY INTERVIEWS AND PROFILES |
Report Statistics
| Slides | 401 |
|---|---|
| Forecasts to | 2040 |
Customer Testimonial
"The resources provided by IDTechEx, such as their insightful reports and analysis, engaging webinars, and knowledgeable analysts, serve as valuable tools and information sources... Their expertise allows us to make data-driven, strategic decisions and ensures we remain aligned with the latest trends and opportunities in the market."