An integrated process that guides the estimation of size, volume, and yield, combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponics cycle agriculture.

Abstract

A system that guides the robotic automation of vertical farming, comprising artificial intelligence optimization software for estimating the size, volume, and yield of vertical farming; the artificial intelligence optimization software is coupled to a robot; the robot utilizes computer vision within the vertical farm to estimate the height, growth, and volume of plants; the robot has a robotic arm for sowing seeds within the vertical farm; once the seeds have grown past the seedling stage, the robot moves the seedlings to a hydroponic greenhouse; within the hydroponic greenhouse, the robot uses computer vision to estimate the height, growth, and volume of plants; and the artificial intelligence optimization software provides guidance and feedback on when and where the robot should make changes to the plants in the hydroponic greenhouse. The system also has sensors throughout the vertical farm and greenhouse that transmit data to the software.

Description

Technical Field

[0001] The present invention relates to an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence (“AI”) and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture.

Background Art

[0002] The description of the background art includes information that may be useful in understanding the present invention. It is not admitted that any of the information provided herein is prior art, or is related to the invention claimed in the claims, or that any of the published documents specifically or implicitly referenced is prior art.

[0003] All published documents identified herein are incorporated by reference to the extent that each respective publication or patent application is as if specifically and individually indicated to be incorporated by reference. If the definition or use of a term in the incorporated reference is not consistent with or is contrary to the definition of that term provided herein, then the definition of that term provided herein applies and the definition of that term in the reference does not apply. The following description includes information that may be useful in understanding the present invention. It is not admitted that any of the information provided herein is prior art, or is related to the invention claimed in the claims, or that any of the published documents specifically or implicitly referenced is prior art.

[0004] In some embodiments, it is to be understood that numbers representing characteristics such as amounts, concentrations, etc. of components, reaction conditions, etc., used to describe and claim particular embodiments of the present invention are, in some instances, modified by the term “about”.

[0005] Therefore, in some embodiments, the numerical parameters described in the specification and appended claims are approximations that may vary depending on the desired characteristics to be obtained by a particular embodiment.

[0006] In some embodiments, numerical parameters are preferably interpreted in light of the number of significant figures reported and by applying standard rounding methods. Although the numerical ranges and parameters describing a broad range of some embodiments of the present invention are approximations, the numerical values ​​described in the specific examples are reported as accurately as possible for practical purposes.

[0007] The numerical values ​​shown in some embodiments of the present invention may include certain errors that inevitably arise from the standard deviation observed in each test measurement.

[0008] Unless the context indicates otherwise, all ranges described herein should preferably be interpreted as including their endpoints, and non-limiting ranges should preferably be interpreted as including only commercially useful values. Similarly, all listed values ​​should preferably be considered to include intermediate values ​​unless the context indicates otherwise.

[0009] As used in this specification and throughout the attached claims, the meanings of “a,” “an,” and “the” include plural references unless otherwise explicitly stated by the context. Furthermore, as used in this specification, the meaning of “in” includes both “in” and “on” unless otherwise explicitly stated by the context.

[0010] The enumeration of value ranges in this specification is intended solely as a shorthand notation for individually referring to the individual values ​​that fall within those ranges. Unless otherwise indicated herein, each individual value is incorporated herein as if it were individually enumerated. All methods described herein may be performed in any preferred order unless otherwise indicated herein or unless it would be clearly inconsistent with the context. The use of any examples or exemplary language provided herein in relation to a particular embodiment (e.g., "such as") is intended solely to further illustrate the invention and not to limit the scope of the invention as otherwise claimed.

[0011] It is preferable that nothing in this specification be construed as indicating an unclaimed component that is essential to the implementation of the present invention.

[0012] The grouping of alternative components or embodiments of the Invention disclosed herein shall not be construed as limiting. Each member of a group may be claimed by reference individually or in combination with other members of the group or other components found herein. One or more members of a group may be included in or removed from a group for convenience and / or patentability reasons. In the event of any such inclusion or removal, this Specified herein shall be deemed to include the modified group and shall satisfy all descriptions of the Markush group used in the appended claims.

[0013] Energy is the most expensive expense on any farm with vertical lighting. Today, farms use more energy than is necessary to grow crops optimally. In some cases, energy can account for up to 31% of a farm's operating costs.

[0014] While outdoor farming is less expensive than vertical farming, the outdoor spaces used for these farms are typically located far from major metropolitan areas that consume the majority of the produce from those farms. In fact, fruits and vegetables can sometimes be transported thousands of miles, resulting in further pollution and exacerbation of climate change.

[0015] Climate change is also increasing heat all over the globe and reducing the availability of freshwater, both of which are detrimental to farming. [Overview of the Initiative] [Means for solving the problem]

[0016] This invention solves these problems because it produces crops with the lowest energy use using optimal photosynthetic yields both indoors and outdoors.

[0017] No vertical farm exists that uses 100% renewable energy. Nor does a vertical farm that optimally utilizes sunlight. This invention uses 100% renewable energy and optimizes the use of sunlight for solar power.

[0018] Vertical farms in containers can be easily installed in major metropolitan areas. In alternative embodiments, seedbeds are used instead of vertical farms. Hydroponic greenhouses can similarly be installed on rooftops or even in individual residences.

[0019] Both vertical farming and solar power can be costly, therefore, there is a need to optimize the use of energy from solar power and maximize the yield of crops that can be grown.

[0020] This invention represents the most cost-effective use of hydroponics, combining indoor farming with a hydroponic greenhouse that draws power from solar energy. In places like the Middle East and California, where climate change is causing rising heat levels and water scarcity, this invention could potentially utilize large amounts of solar energy to produce crops locally, in contrast to importing crops thousands of miles away.

[0021] Furthermore, the present invention utilizes computer vision to estimate the height, growth, and volume of plants. This includes a camera and computer vision software that analyzes images to estimate the height, growth, and volume of plants. In addition, a robotic arm sows seeds in a vertical farm. Once the plants have grown beyond seedlings into mature plants, they are moved to a hydroponic greenhouse. Inside the hydroponic greenhouse, computer vision continues to estimate the height, growth, and volume of the plants. The robotic arm continues to operate based on the data from the computer vision.

[0022] Today, there is nothing on the market that uses computer vision software in combination with robotics to optimize vertical farms and hydroponic greenhouses.

[0023] Many aspects of this disclosure can be better understood with reference to the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but rather to emphasize the clear illustration of the principles of the disclosure. Furthermore, similar reference numerals in the drawings point to corresponding parts across multiple figures. [Brief explanation of the drawing]

[0024] [Figure 1] Figure 1 is a diagram illustrating an integrated process that guides the estimation of size, volume, and yield by combined artificial intelligence and robotics, as well as robotic automation for vertical farming and greenhouse hydroponics cycle agriculture, according to various embodiments of the present disclosure. [Figure 2]Figure 2 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 3] Figure 3 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 4] Figure 4 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 5] Figure 5 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 6] Figure 6 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 7] Figure 7 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 8] Figure 8 is a diagram of an integrated process that provides guidance for sizing, quantifying, and estimating yields in combined artificial intelligence and robotics, as well as robotic automation in vertical farming and greenhouse hydroponic cycle agriculture, according to various embodiments of the present disclosure. [Figure 9]Figure 9 is a diagram illustrating an integrated process that guides the estimation of size, volume, and yield by combined artificial intelligence and robotics, as well as robotic automation for vertical farming and greenhouse hydroponics cycle agriculture, according to various embodiments of the present disclosure. [Figure 10] Figure 10 is a diagram illustrating an integrated process that guides the estimation of size, volume, and yield by combined artificial intelligence and robotics, as well as robotic automation for vertical farming and greenhouse hydroponics cycle agriculture, according to various embodiments of the present disclosure. [Figure 11] Figure 11 is a diagram illustrating an integrated process that guides the estimation of size, volume, and yield by combined artificial intelligence and robotics, as well as robotic automation for vertical farming and greenhouse hydroponics cycle agriculture, according to various embodiments of the present disclosure. [Figure 12] Figure 12 is a diagram illustrating an integrated process that guides the estimation of size, volume, and yield by combined artificial intelligence and robotics, as well as robotic automation for vertical farming and greenhouse hydroponics cycle agriculture, according to various embodiments of the present disclosure. [Modes for carrying out the invention]

[0025] Various embodiments of this disclosure relate to providing.

[0026] The facility includes a vertical farm and a hydroponic greenhouse, both equipped with sensors and control systems throughout, which are used in combination. Both the vertical farm and the hydroponic greenhouse transmit data to artificial intelligence energy optimization software.

[0027] Artificial intelligence is the intelligence exhibited by machines, particularly computers. It includes software that enables machines to perceive their environment and uses learning and intelligence to maximize the likelihood of achieving defined goals. One form of AI is machine learning, which involves statistical algorithms that can learn from data and generalize to unseen data, thereby enabling them to perform tasks without explicit instructions. Training data is provided from time to time to ensure that AI software based on machine learning learns the correct lessons. Another form of AI is a neural network, which is a model inspired by the structure of the brain. AI based on neural networks includes nodes called artificial neurons, which are modeled after neurons in the brain. These are connected by edges that model synapses in the brain. Each artificial neuron receives signals from connected neurons, processes those signals, and transmits them to other connected neurons. These "signals" are real numbers, and the output of each neuron is calculated by some nonlinear function of the sum of the inputs to that neuron, which is called the activation function. The strength of the signal at each connection is determined by weights, which are adjusted during the learning process. Typically, neurons are aggregated into layers. Different layers can perform different transformations on the inputs they receive. Signals travel from the first layer (input layer) to the last layer (output layer), sometimes passing through multiple hidden layers. When a network has at least two hidden layers, it is typically called a deep neural network. Machine learning that uses deep neural networks is called deep learning.

[0028] Distribution Center

[0029] Solar power is absorbed through the solar grid of solar panels. The solar grid measures solar power generation data. There are solar cells that store some of the energy absorbed by the solar grid.

[0030] The plants begin as seedlings and plugs, in which case, plugs in horticulture are small seedlings that are grown without soil, as is the case with hydroponics. In one embodiment of the present invention, the seedlings and plugs begin in larger containers similar to or identical to standard shipping containers. In another embodiment of the present invention, the vertical farm can be incorporated into a greenhouse without containers. They are placed close together and spaced apart. Once the plants have grown beyond the seedling stage into plants, they are moved into the greenhouse and placed in a planting medium.

[0031] The planting medium may be deep hydroponics or nutrient film technique ("NFT"), or ebb & flow, or rockwool slab, or Dutch bucket. Plants are transferred from indoor vertical hydroponics for germination to seedlings and planted in a greenhouse hydroponic system. In one embodiment of the present invention, plants are spaced more sparsely than in containers to allow time for the plants to grow to full size. In another embodiment of the present invention, the vertical farm can be maintained without transplanting.

[0032] Solar energy is used to power the containers and greenhouses. Power usage includes heating, cooling, and pumping. Light is provided through sunlight within the greenhouse. If sunlight is insufficient, for example during a storm or in the middle of winter far from the equator, artificial light may be used to supplement the lighting. The solar grid charges the solar cells. The batteries last longest when maintained at 60-80% charge. Power goes directly from the solar grid to the heating, cooling, and pumps, balancing the load with the solar cell charge, while artificial intelligence energy optimization software balances the load. The solar cells transmit battery percentage data to the artificial intelligence energy optimization software.

[0033] The optimal range for extending battery life is between 20% and 60% charge.

[0034] Fertilizer is added as needed, both at the seedling stage and later. Either chemical or organic fertilizers can be used, depending on what is best for each type of plant.

[0035] Heating and cooling are controlled according to the type of plant and its stage of growth. Some plant seedlings require a specific temperature, while other stages of growth require different temperatures; different plants require different temperatures at each stage. Typically, plants can exhibit greater heat tolerance as they grow towards maturity.

[0036] There are combined cycle sensors, instrumentation, and control systems. There are also outdoor light measurement sensors and instrumentation. Data from both the vertical farm and the hydroponic greenhouse are fed to the combined cycle sensors and instrumentation. Data from the outdoor light measurement sensors and instrumentation are fed to artificial intelligence energy optimization software. The outdoor light measurement sensors and instrumentation measure the estimated photosynthetic yield and solar power generation. The outdoor light measurement sensors and instrumentation also measure the amount of photosynthetically active radiation ("PAR") and the total amount of radiation flow. The data from the outdoor light measurement sensors and instrumentation allows the artificial intelligence energy optimization software to determine how much light is needed for the various plants in the hydroponic greenhouse. The outdoor light measurement sensors and instrumentation also measure and estimate the solar power conditions within the solar grid.

[0037] Photosynthetically active radiation tells artificial intelligence energy optimization software how much light from the sun is available for plants to grow. Then, if more lighting needs to be turned on to maximize the yield of a particular crop, the artificial intelligence energy optimization software will turn on more lighting until the amount of light reaching that crop results in the maximum yield of that crop. Alternatively, if more lighting needs to be turned off to maximize the yield of a particular crop, the artificial intelligence energy optimization software will turn off more lighting until the amount of light reaching that crop results in the maximum yield of that crop. In another embodiment of the present invention, controllable awnings reduce the amount of sunlight entering the greenhouse by opening and closing, which is done based on the results of the artificial intelligence energy optimization software determining what will result in the maximum crop yield, taking into account the sunlight coming through those controllable awnings.

[0038] The combined cycle sensor, instrumentation, and control system measures ambient temperature, water temperature, lighting on or off time, flow rate, carbon dioxide levels, humidity, nutrient solution levels, electrical conductivity, and pH.

[0039] The combined cycle sensor, instrumentation, and control system transmit data to artificial intelligence energy optimization software.

[0040] The artificial intelligence energy optimization software transmits data to the combined cycle sensor, instrumentation, and control system, informing them of what to do.

[0041] There is a non-networked artificial intelligence architecture that integrates solar grid data with real-time data, solar cells with real-time data, and outdoor light measurement sensors and instrumentation with real-time data.

[0042] Artificial intelligence energy optimization software analyzes inputs from vertical farms, hydroponic greenhouses, solar grids, and solar panels to optimize conditions in vertical farms and hydroponic greenhouses to maximize crop yields. The software performs this optimization by modifying heating, cooling, flow rates, lighting, carbon dioxide levels, humidity, nutrient solutions, electrical conductivity, and pH. It makes these changes based on what is optimal for the yield of each plant at each stage of its life cycle. The software attempts to minimize overall energy consumption per crop.

[0043] The vertical farm and hydroponic greenhouses operate year-round using artificial intelligence energy optimization software. This software constantly attempts to maximize crop yields within the vertical farm.

[0044] Increasing carbon dioxide levels improves plant growth. If sensors detect that there is too little carbon dioxide for a particular plant, the artificial intelligence energy optimization software will pump carbon dioxide to increase the level until the sensors signal that the optimal amount of carbon dioxide for that plant has been achieved.

[0045] If the sensor detects that the humidity is too high for a particular plant, the artificial intelligence energy optimization software will either turn on a fan near the plant, turn on a dehumidifier near the plant, or place a cooling pad near the plant to reduce the humidity until the sensor signals that the optimal humidity level for that plant has been achieved. Alternatively, if the sensor detects that the humidity is too high for a particular plant and that the outdoor environment is not humid, the artificial intelligence energy optimization software will open vents to facilitate humidity reduction until the sensor signals that the optimal humidity level for that plant has been achieved.

[0046] If the sensor detects that the air is too hot for a particular plant, the artificial intelligence energy optimization software will either turn on the air conditioning near that plant, or if the sensor detects that the outdoor air is not hotter than the indoor air, the artificial intelligence energy optimization software will open vents to facilitate a temperature reduction, and will continue this until the sensor signals that the optimal temperature for that particular plant has been achieved.

[0047] If the sensor detects that the air is too cold for a particular plant, the artificial intelligence energy optimization software will turn on a water heater near that plant, or if the sensor detects that the outdoor air is not colder than the indoor air, the artificial intelligence energy optimization software will open vents to promote a temperature increase, and will continue this until the sensor signals that the optimal temperature for that particular plant has been achieved.

[0048] If the sensor detects that the water is too hot for a particular plant, the artificial intelligence energy optimization software will turn on the water chiller supplying the plant until the sensor signals that the optimal temperature for the water going to that plant has been achieved.

[0049] If the sensor detects that the water is too cold for a particular plant, the artificial intelligence energy optimization software will turn on the water heater supplying that plant until the sensor signals that the water has reached the optimal temperature.

[0050] If the sensor detects that a certain component of the nutrient solution is deficient for a particular plant, the artificial intelligence energy optimization software will instruct the machine to add those components to the nutrient solution going to that plant until the sensor signals that the optimal level of those components has been achieved.

[0051] If the sensor detects that the amount of a certain component in the nutrient solution is too high for a particular plant, the artificial intelligence energy optimization software will instruct the machine to remove those components from the nutrient solution going to the plant until the sensor signals that the optimal level of those components has been achieved for the nutrient solution going to that plant.

[0052] If the sensor detects that the electrical conductivity in Siemens per meter is too low for a particular plant, the artificial intelligence energy optimization software will instruct the machine to increase the Siemens per meter of electrical conductivity going to that plant until the sensor signals that the Siemens per meter of electrical conductivity going to that plant has reached an optimal level.

[0053] If the sensor detects that the electrical conductivity is too high in Siemens per meter for a particular plant, the artificial intelligence energy optimization software will instruct the machine to reduce the Siemens per meter of electrical conductivity going to that plant until the sensor signals that the Siemens per meter of electrical conductivity going to that plant has reached an optimal level.

[0054] If the sensor detects that the pH of a particular plant is too low, the artificial intelligence energy optimization software will instruct the machine to add a basic liquid to that plant to increase its pH until the sensor signals that the plant's pH has reached the optimal level.

[0055] If the sensor detects that the pH is too high in a particular plant, the artificial intelligence energy optimization software will instruct the machine to add an acidic liquid to that plant to lower its pH until the sensor signals that the plant's pH has reached an optimal level.

[0056] Artificial intelligence energy optimization software utilizes different types of artificial intelligence depending on the situation. It can employ machine learning, deep learning, neural networks, or any other useful neural network architecture.

[0057] Solar panels may never reach 100% charge. If a solar panel reaches 1%, the artificial intelligence energy optimization software may stop directing energy from the solar grid to the vertical farm and hydroponic greenhouse and instead focus on charging the solar panel. Alternatively, if a solar panel is above 80%, the artificial intelligence energy optimization software may direct all energy from the solar grid to the vertical farm and hydroponic greenhouse and not charge the solar panel until it drops to 60%. If a solar panel is charged beyond 100%, it can cause battery damage, battery degradation, and potentially fire. Therefore, if a solar panel has already reached 99% charge, energy from the solar grid will stop charging the solar panel and instead focus on powering the vertical farm and hydroponic greenhouse.

[0058] Outdoor light measurement sensors and instrumentation also measure all the energy available for solar conversion. The outdoor light measurement sensors transmit this data to artificial intelligence energy optimization software, which estimates the power generation of the solar grid. This data is available in real time. One unit for measuring energy from the solar grid is the kilowatt-hour.

[0059] Different crops that can be grown using this invention include lettuce, tomatoes, leafy vegetables, and climbing crops. Many other fruits, vegetables, lentils, and other plants can also be grown using this invention.

[0060] In one embodiment of the present invention, artificial intelligence energy optimization software balances energy generation from the solar grid, energy storage in solar cells, and energy consumption in the vertical farm and hydroponic greenhouse to maximize the yield of crops grown in the vertical farm and hydroponic greenhouse.

[0061] In one embodiment of the present invention, the solar cells have a backup energy source. In environments with less sunlight, increasing the solar grid can compensate for the reduced amount of sunlight, still providing enough energy to power vertical farms, hydroponic greenhouses, and artificial intelligence energy optimization software. In an alternative embodiment, a nursery is used instead of a vertical farm.

[0062] In another embodiment of the present invention, a robotic arm sows seeds in a vertical farm.

[0063] In another embodiment of the present invention, after the plants have reached the seedling stage, a conveyor belt carries the plants from the vertical farm to a hydroponic greenhouse. Both the vertical farm and the hydroponic greenhouse have cameras that feed data to computer vision software. The computer vision software can identify whether the plants have reached the seedling stage and can then transmit that data to artificial intelligence energy optimization software. The artificial intelligence energy optimization software then instructs a robotic arm to place the seedlings on a conveyor belt, which carries the seedlings to the hydroponic greenhouse. Another robotic arm inside the hydroponic greenhouse then places the seedlings in the optimal location for maximum growth.

[0064] Inside the hydroponic greenhouse, computer vision continuously estimates the height, growth, and volume of the plants. This includes cameras and computer vision software that analyzes images to estimate the height, growth, and volume of the plants. The robotic arm continues to operate based on the data from the computer vision. The computer vision analyzes whether the plants are ready for harvest, and if it determines that the plants are ready for harvest, it sends that data to artificial intelligence energy optimization software. If the artificial intelligence energy optimization software agrees that the plants are ready for harvest, it instructs the robotic arm to harvest the plants. The robotic arm then harvests the plants.

[0065] A separate robot will be used to package the plants. They can be placed in plastic or, as an alternative, biodegradable packaging materials. Some harvested plants will be individually wrapped in a plastic outer shell. Other harvested plants will be placed in boxes. Different packaging techniques will be applied based on the type of plant and the requirements of the customer intending to purchase that type of plant. Some packaging will also contain adhesive at the top to keep the packaging attached to the harvested plant.

[0066] This order can differ for different plants. In the case of lettuce, the order is as described above, with no robotic activity between placing the seedlings in the hydroponic greenhouse and harvesting the plants. However, for cucumbers, tomatoes, and peppers, there will be a separate robot with a sub-computer vision module that knows the location of each vegetable and any vines. This separate robot will cut one inch above where the vines are. This allows the unharvested portion of the plant to continue growing and be harvested again at a later date. This maximizes the productivity of each plant. Depending on the plant species, type of vegetable, and type of fruit, there will be different decisions regarding the optimal time to harvest each plant. Some plants may be harvested once a year, some three times a year, and some may even be harvested year-round.

[0067] In another embodiment of the present invention, having multiple cameras throughout both the vertical farm and the hydroponic greenhouse provides computer vision software with many different angles from which to begin image analysis.

[0068] In another embodiment of the present invention, the robot and robotic arm will utilize a Robot Operating System ("ROS"), which is an operating system.

[0069] In another embodiment of the present invention, the computer vision software utilizes artificial intelligence, which can be machine learning, deep learning, neural networks, or any useful neural network architecture. This artificial intelligence helps the computer vision software estimate the height, growth, and quantity of each plant and transmit the analysis results to the artificial intelligence energy optimization software. The artificial intelligence energy optimization software can then determine whether to harvest the plant or take some other action with respect to the plant. Once that decision has been made, the artificial intelligence energy optimization software can inform the robot or robotic arm of what action it should take.

[0070] Computer vision software collects data on the time to seed maturity, the variability of seed maturity, and the percentage of seeds that fail to mature. This data can be sent to the seed providers to provide quality feedback and suggestions on which seeds are performing well. Robots can also take actions to maximize yield based on all of this data. One example of an action a robot might take is if the computer vision software in a vertical farm determines that seedlings have not grown to the appropriate height by a certain point. The computer vision software would then send this data to artificial intelligence energy optimization software, which would determine that the seedlings should not be moved to a hydroponic greenhouse. Instead, the artificial intelligence energy optimization software would instruct the robot to discard the seedlings.

[0071] In another example of the actions the robot might take, it would sow approximately 10% more seeds of each plant to allow for the disposal of plants that do not grow at an optimal rate, without reducing the final yield of the harvested plants. The percentage of oversowing may vary depending on the plant, based on how often those plants fail to grow at their maximum rate.

[0072] Figure 1 is a flowchart of one embodiment of the present invention, showing how the vertical farm and hydroponic greenhouse interact with the AI ​​software. Figure 2 is the same flowchart as Figure 1, except that the operations described in Figure 1 are shown numerically. There are vertical farm inputs 201 for seeds, fertilizer, heating, cooling, pumps, and lighting. There are hydroponic greenhouse inputs 202 for seedlings, fertilizer, heating, cooling, and pumps. There are composite cycle sensors / instruments and control devices 203 for air temperature (heating or cooling or ventilation), water temperature (on and off of water heater or chiller), lighting on and off, flow sensors, carbon dioxide on or vent opening, humidity (fan and pad cooling or dehumidifier or greenhouse window opening), nutrient solution electrical conductivity, and pH. There are outdoor light measurement sensors and instruments 204 that give estimated photosynthetic yield and photovoltaic power generation. There is AI energy optimization 205 that includes balancing energy generation, energy storage, and energy consumption. There is a solar grid 206 for solar panels that give photovoltaic power generation data. There is a solar cell 207 that stores energy from the solar panel and provides battery percentage data.

[0073] Figure 3 is a flowchart of the present invention. Figure 4 is the same flowchart as Figure 3, except that the operations described in Figure 3 are shown numerically. There is a vertical farm 401 with input labor for camera-based height / growth estimation, sowing seeds, and placing seeds within the vertical farm. There is a hydroponic greenhouse 402 with camera-based height / growth estimation, transplanting plants from the vertical hydroponic system to the horizontal hydroponic system via a conveyor belt and robotic arm, harvesting from the hydroponic system using a robotic arm, moving via a conveyor belt to packaging or harvest, and automatic packaging of the produce. There is a computer vision analysis method 403 with estimation of height, width, volume, and growth stage. There is yield, based on the minimum labor required per crop, i.e., the optimized production process.

[0074] Figure 5 shows sensors located throughout the greenhouse. These include a humidity sensor 301, a soil pH sensor 302, a temperature sensor 303, and a flow sensor 304. These sensors can be swapped and moved to different locations throughout the greenhouse and vertical farm.

[0075] Figure 6 shows the outdoor light measurement sensors of the PAR. Sensor 401 absorbs UV light across the entire color spectrum and analyzes it. Sensor 402 also absorbs UV light and analyzes it. Display 403 shows the analysis of the PAR based on sensors 401 and 402.

[0076] Figure 7 shows multiple solar cells and solar panels arranged in a grid configuration.

[0077] Figure 8 shows a sensor for measuring soil pH in either a greenhouse or a vertical farm.

[0078] Figures 9 through 12 are different images of vertical farms. These are different arrangements of vertical farms, and different sensors can be placed in various different locations within these vertical farms, depending on where those sensors will obtain accurate measurement results.

[0079] Each of the following further embodiments can be combined with any other in any combination. Furthermore, in each of the following embodiments, the vertical farm can be replaced with a seedling bed. Moreover, all of the embodiments described can be combined with one or more other embodiments in any combination.

[0080] In a further embodiment, there is a system for guiding robotic automation of vertical farming, comprising: artificial intelligence optimization software for estimating the size, volume, and yield of the vertical farm; the artificial intelligence optimization software is coupled to a robot; the robot utilizes computer vision to estimate the height, growth, and volume of plants in the vertical farm; the robot has a robotic arm for sowing seeds within the vertical farm; once the seeds have grown past seedlings into plants, the robot moves the plants to a hydroponic greenhouse; in the hydroponic greenhouse, the robot uses computer vision to estimate the height, growth, and volume of plants; and the artificial intelligence optimization software provides guidance and feedback on when and where the robot should make changes to the plants in the hydroponic greenhouse.

[0081] In a further embodiment, the system includes sensors throughout the vertical farm and sensors throughout the hydroponic greenhouse; the sensors throughout the vertical farm and sensors throughout the hydroponic greenhouse provide feedback to artificial intelligence optimization software;

[0082] In a further embodiment, the system analyzes data from sensors in a vertical farm and a hydroponic greenhouse working together using artificial intelligence optimization software.

[0083] In a further embodiment, the system includes a vertical farm and a hydroponic greenhouse that receive power through solar energy from a grid of solar panels; and artificial intelligence optimization software optimizes the distribution of power from the solar energy.

[0084] In a further embodiment, the system includes a solar cell that stores some of the power from the solar panel grid.

[0085] In a further embodiment, the system includes artificial intelligence optimization software that balances the electrical load by ensuring that power is supplied directly from the solar panel grid to heating, cooling, and pumping, and that this balances with the charging of the solar cells; the solar cells transmit battery percentage data to the artificial intelligence optimization software.

[0086] In a further embodiment, the system includes a plant medium for plants being grown in a hydroponic greenhouse, the plant medium being one of the following: deep hydroponics or thin-film hydroponics (nutrient film technique) ("NFT"), or ebb & flow, or rockwool slab, or Dutch bucket.

[0087] In a further embodiment, the system includes artificial intelligence optimization software that balances the electrical load by ensuring that power is supplied directly from the solar panel grid to heating, cooling, and pumps, and that this is balanced with the charging of the solar cells, the solar cells transmit battery percentage data to the artificial intelligence optimization software; and the artificial intelligence optimization software manages heating and cooling according to the type of plant and stage of growth.

[0088] In a further embodiment, the system includes a combined cycle sensor, instrumentation, and control unit; also an outdoor light measuring sensor and instrumentation; data from both the vertical farm and the hydroponic greenhouse is fed to the combined cycle sensor, instrumentation, and control unit; data from the outdoor light measuring sensor and instrumentation is fed to artificial intelligence optimization software; the outdoor light measuring sensor and instrumentation measures the estimated photosynthetic yield and solar power generation; the outdoor light measuring sensor and instrumentation measures photosynthetically active radiation ("PAR") and the overall radiation flow; data from the outdoor light measuring sensor and instrumentation enables the artificial intelligence energy optimization software to determine how much light is needed for the various plants in the vertical farm and the hydroponic greenhouse; and the outdoor light measuring sensor and instrumentation also measure and estimate the solar power conditions in the solar grid.

[0089] In a further embodiment, the system includes artificial intelligence optimization software that utilizes machine learning.

[0090] In a further embodiment, the system includes artificial intelligence optimization software that utilizes deep learning.

[0091] In a further embodiment, the system includes artificial intelligence optimization software that utilizes a neural network.

[0092] From the above, it will be understood that specific embodiments of the present invention have been described herein for illustrative purposes, but that various modifications may be made without departing from the spirit and scope of the invention. Accordingly, the present invention is not limited to the appended claims.

Claims

1. This system provides guidance for robotic automation in vertical farming. AI optimization software is integrated into the robot; The robot uses computer vision to estimate the height, growth, and quantity of plants in the vertical farm; The robot has a robotic arm for sowing seeds in a vertical farm; Once the seeds have grown beyond seedlings into plants, the robot moves the plants to a hydroponic greenhouse; Within the hydroponic greenhouse, the robot uses computer vision to estimate the height, growth, and quantity of plants; The artificial intelligence optimization software provides guidance and feedback on when and where the robot should make changes to the plants in the hydroponic greenhouse. system.

2. Furthermore, there are sensors throughout the aforementioned vertical farm; Sensors are placed throughout the aforementioned hydroponic greenhouse; Sensors throughout the vertical farm and sensors throughout the hydroponic greenhouse provide feedback to the artificial intelligence optimization software. The system according to claim 1.

3. moreover, The system according to claim 2, wherein data from the vertical farm sensor and the hydroponic greenhouse sensor, which work in coordination, are analyzed together by artificial intelligence optimization software.

4. moreover, The aforementioned vertical farm and hydroponic greenhouse receive power through solar energy from a grid of solar panels; The system according to claim 1, wherein the artificial intelligence optimization software optimizes the distribution of power from the solar power.

5. moreover, The system according to claim 4, wherein there is a solar cell that stores a portion of the electricity from the grid of the solar panels.

6. moreover, The artificial intelligence optimization software balances the electrical load by supplying power directly from the grid of the solar panels to the heating, cooling, and pumps, and balancing this with the charging of the solar cells; The system according to claim 5, wherein the solar cell transmits battery percentage data to the artificial intelligence optimization software.

7. moreover, The plant growing medium in the aforementioned hydroponic greenhouse is as follows: The system according to claim 1, which may be deep hydroponics or thin-film hydroponics ("NFT"), or ebb and flow, or rockwool slab, or Dutch bucket.

8. moreover, The artificial intelligence optimization software balances the electrical load by directing power from the solar panel grid to the heating, cooling, and pumps, and balancing it with the charging of the solar cells; The solar cell transmits the battery percentage data to artificial intelligence optimization software; The system according to claim 1, wherein the artificial intelligence optimization software manages heating and cooling according to the type of plant and stage of growth.

9. moreover, It includes a combined cycle sensor, instrumentation, and control system; Outdoor light measurement sensors and instrumentation are also available; Data from both the vertical farm and the hydroponic greenhouse are fed to the combined cycle sensor, instrumentation, and control unit; The data from the outdoor light measuring sensor and instrumentation is supplied to the artificial intelligence optimization software; The aforementioned outdoor light measuring sensor and instrumentation measure the estimated photosynthetic yield and solar power generation; The aforementioned outdoor light measuring sensor and instrumentation also measure photosynthetically active radiation ("PAR") and the overall flow of radiation; Data from outdoor light measurement sensors and instrumentation enables the artificial intelligence energy optimization software to determine how much light each plant in the hydroponic greenhouse requires; The aforementioned vertical farm and hydroponic greenhouse receive power through solar energy from a grid of solar panels; The artificial intelligence optimization software optimizes the distribution of power from the solar power; There is a solar cell that stores some of the electricity from the aforementioned solar panel grid; The aforementioned outdoor light measurement sensor and instrumentation will also measure and estimate the conditions of solar power within the solar grid. The system according to claim 1.

10. moreover, The system according to claim 1, wherein the artificial intelligence optimization software utilizes machine learning.

11. moreover, The system according to claim 1, wherein the artificial intelligence optimization software utilizes deep learning.

12. moreover, The system according to claim 1, wherein the artificial intelligence optimization software utilizes a neural network.

13. A method that provides guidance for robotic automation in vertical farming; The system includes artificial intelligence optimization software for estimating the size, quantity, and yield of the aforementioned vertical farming method; The aforementioned artificial intelligence optimization software is coupled to a robot; The robot uses computer vision to estimate the height, growth, and quantity of plants in the vertical farm; The robot has a robotic arm for sowing seeds in the vertical farm; Once the seeds have grown beyond seedlings into plants, the robot moves the plants to a hydroponic greenhouse; Within the hydroponic greenhouse, the robot uses computer vision to estimate the height, growth, and quantity of plants; The artificial intelligence optimization software provides guidance and feedback on when and where the robot should make changes to the plants in the hydroponic greenhouse; Sensors are placed throughout the aforementioned vertical farm; A method comprising: sensors placed throughout the hydroponic greenhouse; and sensors placed throughout the vertical farm and sensors placed throughout the hydroponic greenhouse providing feedback to the artificial intelligence optimization software.

14. moreover, The method according to claim 13, wherein data from sensors in the vertical farm and sensors in the hydroponic greenhouse, which work in coordination, are analyzed together by the artificial intelligence optimization software.

15. moreover, The aforementioned vertical farm and hydroponic greenhouse receive power through solar energy from a grid of solar panels; The artificial intelligence optimization software optimizes the distribution of power from the solar power; The method according to claim 13, wherein there is a solar cell that stores a portion of the electricity from the grid of the solar panel.

16. moreover, The artificial intelligence optimization software balances the electrical load by supplying power directly from the grid of the solar panels to the heating, cooling, and pumps, and balancing this with the charging of the solar cells; The solar cell transmits battery percentage data to the artificial intelligence optimization software. The system according to claim 15.

17. moreover, The plant growing medium for plants grown in the aforementioned hydroponic greenhouse is as follows: The system according to claim 1, which may be deep hydroponics or thin-film hydroponics ("NFT"), or ebb and flow, or rockwool slab, or Dutch bucket.

18. moreover, The artificial intelligence optimization software balances the electrical load by directing power from the solar panel grid to the heating, cooling, and pumps, and balancing this with the charging of the solar cells; The solar cell transmits the battery percentage data to the artificial intelligence optimization software; The system according to claim 1, wherein the artificial intelligence optimization software manages heating and cooling according to the type of plant and stage of growth.

19. moreover, It includes a combined cycle sensor, instrumentation, and control system; Outdoor light measurement sensors and instrumentation are also available; Data from both the vertical farm and the hydroponic greenhouse are fed to the combined cycle sensor, instrumentation, and control device; The data from the outdoor light measuring sensor and instrumentation is supplied to the artificial intelligence optimization software; The aforementioned outdoor light measuring sensor and instrumentation measure the estimated photosynthetic yield and solar power generation; The aforementioned outdoor light measuring sensor and instrumentation also measure photosynthetically active radiation ("PAR") and the overall flow of radiation; The data from the outdoor light measurement sensor and instrumentation enables the artificial intelligence energy optimization software to determine how much light each plant in the hydroponic greenhouse needs; The aforementioned vertical farm and hydroponic greenhouse receive power through solar energy from a grid of solar panels; The artificial intelligence optimization software optimizes the distribution of power from the solar power; There is a solar cell that stores some of the electricity from the aforementioned solar panel grid; The aforementioned outdoor light measurement sensor and instrumentation will also measure and estimate the conditions of solar power within the solar grid. The system according to claim 1.

20. A method that provides guidance for robotic automation in vertical farming: The system includes artificial intelligence optimization software for estimating the size, quantity, and yield of the aforementioned vertical farming method; The aforementioned artificial intelligence optimization software is coupled to a robot; The robot uses computer vision to estimate the height, growth, and quantity of plants in the vertical farm; The robot has a robotic arm for sowing seeds in the vertical farm; Once the seeds have grown beyond seedlings into plants, the robot moves the plants to a hydroponic greenhouse; Within the hydroponic greenhouse, the robot uses computer vision to estimate the height, growth, and quantity of plants; The artificial intelligence optimization software provides guidance and feedback on when and where the robot should make changes to the plants in the hydroponic greenhouse; Sensors are placed throughout the aforementioned vertical farm; Sensors are placed throughout the aforementioned hydroponic greenhouse; Sensors throughout the vertical farm and sensors throughout the hydroponic greenhouse provide feedback to the artificial intelligence optimization software; A method by which the artificial intelligence optimization software utilizes either machine learning, deep learning, or a neural network.

Images