MIT engineers have designed an ingestible, Jell-O-like pill that, upon reaching the stomach, quickly swells to the size of a soft, squishy ping-pong ball big enough to stay in the stomach for an extended period of time.
Living in extreme conditions requires creative adaptations. For certain species of bacteria that exist in oxygen-deprived environments, this means finding a way to breathe that doesn’t involve oxygen. These hardy microbes, which can be found deep within mines, at the bottom of lakes, and even in the human gut, have evolved a unique form of breathing that involves excreting and pumping out electrons. In other words, these microbes can actually produce electricity.
Scientists and engineers are exploring ways to harness these microbial power plants to run fuel cells and purify sewage water, among other uses. But pinning down a microbe’s electrical properties has been a challenge: The cells are much smaller than mammalian cells and extremely difficult to grow in laboratory conditions.
Now MIT engineers have developed a microfluidic technique that can quickly process small samples of bacteria and gauge a specific property that’s highly correlated with bacteria’s ability to produce electricity. They say that this property, known as polarizability, can be used to assess a bacteria’s electrochemical activity in a safer, more efficient manner compared to current techniques.
“The vision is to pick out those strongest candidates to do the desirable tasks that humans want the cells to do,” says Qianru Wang, a postdoc in MIT’s Department of Mechanical Engineering.
“There is recent work suggesting there might be a much broader range of bacteria that have [electricity-producing] properties,” adds Cullen Buie, associate professor of mechanical engineering at MIT. “Thus, a tool that allows you to probe those organisms could be much more important than we thought. It’s not just a small handful of microbes that can do this.”
Buie and Wang have published their results today in Science Advances.
Just between frogs
Bacteria that produce electricity do so by generating electrons within their cells, then transferring those electrons across their cell membranes via tiny channels formed by surface proteins, in a process known as extracellular electron transfer, or EET.
Existing techniques for probing bacteria’s electrochemical activity involve growing large batches of cells and measuring the activity of EET proteins — a meticulous, time-consuming process. Other techniques require rupturing a cell in order to purify and probe the proteins. Buie looked for a faster, less destructive method to assess bacteria’s electrical function.
For the past 10 years, his group has been building microfluidic chips etched with small channels, through which they flow microliter-samples of bacteria. Each channel is pinched in the middle to form an hourglass configuration. When a voltage is applied across a channel, the pinched section — about 100 times smaller than the rest of the channel — puts a squeeze on the electric field, making it 100 times stronger than the surrounding field. The gradient of the electric field creates a phenomenon known as dielectrophoresis, or a force that pushes the cell against its motion induced by the electric field. As a result, dielectrophoresis can repel a particle or stop it in its tracks at different applied voltages, depending on that particle’s surface properties.
Researchers including Buie have used dielectrophoresis to quickly sort bacteria according to general properties, such as size and species. This time around, Buie wondered whether the technique could suss out bacteria’s electrochemical activity — a far more subtle property.
“Basically, people were using dielectrophoresis to separate bacteria that were as different as, say, a frog from a bird, whereas we’re trying to distinguish between frog siblings — tinier differences,” Wang says.
An electric correlation
In their new study, the researchers used their microfluidic setup to compare various strains of bacteria, each with a different, known electrochemical activity. The strains included a “wild-type” or natural strain of bacteria that actively produces electricity in microbial fuel cells, and several strains that the researchers had genetically engineered. In general, the team aimed to see whether there was a correlation between a bacteria’s electrical ability and how it behaves in a microfluidic device under a dielectrophoretic force.
The team flowed very small, microliter samples of each bacterial strain through the hourglass-shaped microfluidic channel and slowly amped up the voltage across the channel, one volt per second, from 0 to 80 volts. Through an imaging technique known as particle image velocimetry, they observed that the resulting electric field propelled bacterial cells through the channel until they approached the pinched section, where the much stronger field acted to push back on the bacteria via dielectrophoresis and trap them in place.
Some bacteria were trapped at lower applied voltages, and others at higher voltages. Wang took note of the “trapping voltage” for each bacterial cell, measured their cell sizes, and then used a computer simulation to calculate a cell’s polarizability — how easy it is for a cell to form electric dipoles in response to an external electric field.
From her calculations, Wang discovered that bacteria that were more electrochemically active tended to have a higher polarizability. She observed this correlation across all species of bacteria that the group tested.
“We have the necessary evidence to see that there’s a strong correlation between polarizability and electrochemical activity,” Wang says. “In fact, polarizability might be something we could use as a proxy to select microorganisms with high electrochemical activity.”
Wang says that, at least for the strains they measured, researchers can gauge their electricity production by measuring their polarizability — something that the group can easily, efficiently, and nondestructively track using their microfluidic technique.
Collaborators on the team are currently using the method to test new strains of bacteria that have recently been identified as potential electricity producers.
“If the same trend of correlation stands for those newer strains, then this technique can have a broader application, in clean energy generation, bioremediation, and biofuels production,” Wang says.
This research was supported in part by the National Science Foundation, and the Institute for Collaborative Biotechnologies, through a grant from the U.S. Army.
MIT researchers have developed a new cryptocurrency that drastically reduces the data users need to join the network and verify transactions — by up to 99 percent compared to today’s popular cryptocurrencies. This means a much more scalable network.
Cryptocurrencies, such as the popular Bitcoin, are networks built on the blockchain, a financial ledger formatted in a sequence of individual blocks, each containing transaction data. These networks are decentralized, meaning there are no banks or organizations to manage funds and balances, so users join forces to store and verify the transactions.
But decentralization leads to a scalability problem. To join a cryptocurrency, new users must download and store all transaction data from hundreds of thousands of individual blocks. They must also store these data to use the service and help verify transactions. This makes the process slow or computationally impractical for some.
In a paper being presented at the Network and Distributed System Security Symposium next month, the MIT researchers introduce Vault, a cryptocurrency that lets users join the network by downloading only a fraction of the total transaction data. It also incorporates techniques that delete empty accounts that take up space, and enables verifications using only the most recent transaction data that are divided and shared across the network, minimizing an individual user’s data storage and processing requirements.
In experiments, Vault reduced the bandwidth for joining its network by 99 percent compared to Bitcoin and 90 percent compared to Ethereum, which is considered one of today’s most efficient cryptocurrencies. Importantly, Vault still ensures that all nodes validate all transactions, providing tight security equal to its existing counterparts.
“Currently there are a lot of cryptocurrencies, but they’re hitting bottlenecks related to joining the system as a new user and to storage. The broad goal here is to enable cryptocurrencies to scale well for more and more users,” says co-author Derek Leung, a graduate student in the Computer Science and Artificial Intelligence Laboratory (CSAIL).
Joining Leung on the paper are CSAIL researchers Yossi Gilad and Nickolai Zeldovich, who is also a professor in the Department of Electrical Engineering and Computer Science (EECS); and recent alumnus Adam Suhl ’18.
Vaulting over blocks
Each block in a cryptocurrency network contains a timestamp, its location in the blockchain, and fixed-length string of numbers and letters, called a “hash,” that’s basically the block’s identification. Each new block contains the hash of the previous block in the blockchain. Blocks in Vault also contain up to 10,000 transactions — or 10 megabytes of data — that must all be verified by users. The structure of the blockchain and, in particular, the chain of hashes, ensures that an adversary cannot hack the blocks without detection.
New users join cryptocurrency networks, or “bootstrap,” by downloading all past transaction data to ensure they’re secure and up to date. To join Bitcoin last year, for instance, a user would download 500,000 blocks totaling about 150 gigabytes. Users must also store all account balances to help verify new users and ensure users have enough funds to complete transactions. Storage requirements are becoming substantial, as Bitcoin expands beyond 22 million accounts.
The researchers built their system on top of a new cryptocurrency network called Algorand — invented by Silvio Micali, the Ford Professor of Engineering at MIT — that’s secure, decentralized, and more scalable than other cryptocurrencies.
With traditional cryptocurrencies, users compete to solve equations that validate blocks, with the first to solve the equations receiving funds. As the network scales, this slows down transaction processing times. Algorand uses a “proof-of-stake” concept to more efficiently verify blocks and better enable new users join. For every block, a representative verification “committee” is selected. Users with more money — or stake — in the network have higher probability of being selected. To join the network, users verify each certificate, not every transaction.
But each block holds some key information to validate the certificate immediately ahead of it, meaning new users must start with the first block in the chain, along with its certificate, and sequentially validate each one in order, which can be time-consuming. To speed things up, the researchers give each new certificate verification information based on a block a few hundred or 1,000 blocks behind it — called a “breadcrumb.” When a new user joins, they match the breadcrumb of an early block to a breadcrumb 1,000 blocks ahead. That breadcrumb can be matched to another breadcrumb 1,000 blocks ahead, and so on.
“The paper title is a pun,” Leung says. “A vault is a place where you can store money, but the blockchain also lets you ‘vault’ over blocks when joining a network. When I’m bootstrapping, I only need a block from way in the past to verify a block way in the future. I can skip over all blocks in between, which saves us a lot of bandwidth.”
Divide and discard
To reduce data storage requirements, the researchers designed Vault with a novel “sharding” scheme. The technique divides transaction data into smaller portions — or shards — that it shares across the network, so individual users only have to process small amounts of data to verify transactions.
To implement sharing in a secure way, Vault uses a well-known data structure called a binary Merkle tree. In binary trees, a single top node branches off into two “children” nodes, and those two nodes each break into two children nodes, and so on.
In Merkle trees, the top node contains a single hash, called a root hash. But the tree is constructed from the bottom, up. The tree combines each pair of children hashes along the bottom to form their parent hash. It repeats that process up the tree, assigning a parent node from each pair of children nodes, until it combines everything into the root hash. In cryptocurrencies, the top node contains a hash of a single block. Each bottom node contains a hash that signifies the balance information about one account involved in one transaction in the block. The balance hash and block hash are tied together.
To verify any one transaction, the network combines the two children nodes to get the parent node hash. It repeats that process working up the tree. If the final combined hash matches the root hash of the block, the transaction can be verified. But with traditional cryptocurrencies, users must store the entire tree structure.
With Vault, the researchers divide the Merkle tree into separate shards assigned to separate groups of users. Each user account only ever stores the balances of the accounts in its assigned shard, as well as root hashes. The trick is having all users store one layer of nodes that cuts across the entire Merkle tree. When a user needs to verify a transaction from outside of their shard, they trace a path to that common layer. From that common layer, they can determine the balance of the account outside their shard, and continue validation normally.
“Each shard of the network is responsible for storing a smaller slice of a big data structure, but this small slice allows users to verify transactions from all other parts of network,” Leung says.
Additionally, the researchers designed a novel scheme that recognizes and discards from a user’s assigned shard accounts that have had zero balances for a certain length of time. Other cryptocurrencies keep all empty accounts, which increase data storage requirements while serving no real purpose, as they don’t need verification. When users store account data in Vault, they ignore those old, empty accounts.
Imagine a world where smartphones, laptops, wearables, and other electronics are powered without batteries. Researchers from MIT and elsewhere have taken a step in that direction, with the first fully flexible device that can convert energy from Wi-Fi signals into electricity that could power electronics.
Devices that convert AC electromagnetic waves into DC electricity are known as “rectennas.” The researchers demonstrate a new kind of rectenna, described in a study appearing inNature today, that uses a flexible radio-frequency (RF) antenna that captures electromagnetic waves — including those carrying Wi-Fi — as AC waveforms.
The antenna is then connected to a novel device made out of a two-dimensional semiconductor just a few atoms thick. The AC signal travels into the semiconductor, which converts it into a DC voltage that could be used to power electronic circuits or recharge batteries.
In this way, the battery-free device passively captures and transforms ubiquitous Wi-Fi signals into useful DC power. Moreover, the device is flexible and can be fabricated in a roll-to-roll process to cover very large areas.
“What if we could develop electronic systems that we wrap around a bridge or cover an entire highway, or the walls of our office and bring electronic intelligence to everything around us? How do you provide energy for those electronics?” says paper co-author Tomás Palacios, a professor in the Department of Electrical Engineering and Computer Science and director of the MIT/MTL Center for Graphene Devices and 2D Systems in the Microsystems Technology Laboratories. “We have come up with a new way to power the electronics systems of the future — by harvesting Wi-Fi energy in a way that’s easily integrated in large areas — to bring intelligence to every object around us.”
Promising early applications for the proposed rectenna include powering flexible and wearable electronics, medical devices, and sensors for the “internet of things.” Flexible smartphones, for instance, are a hot new market for major tech firms. In experiments, the researchers’ device can produce about 40 microwatts of power when exposed to the typical power levels of Wi-Fi signals (around 150 microwatts). That’s more than enough power to light up an LED or drive silicon chips.
Another possible application is powering the data communications of implantable medical devices, says co-author Jesús Grajal, a researcher at the Technical University of Madrid. For example, researchers are beginning to develop pills that can be swallowed by patients and stream health data back to a computer for diagnostics.
“Ideally you don’t want to use batteries to power these systems, because if they leak lithium, the patient could die,” Grajal says. “It is much better to harvest energy from the environment to power up these small labs inside the body and communicate data to external computers.”
All rectennas rely on a component known as a “rectifier,” which converts the AC input signal into DC power. Traditional rectennas use either silicon or gallium arsenide for the rectifier. These materials can cover the Wi-Fi band, but they are rigid. And, although using these materials to fabricate small devices is relatively inexpensive, using them to cover vast areas, such as the surfaces of buildings and walls, would be cost-prohibitive. Researchers have been trying to fix these problems for a long time. But the few flexible rectennas reported so far operate at low frequencies and can’t capture and convert signals in gigahertz frequencies, where most of the relevant cell phone and Wi-Fi signals are.
To build their rectifier, the researchers used a novel 2-D material called molybdenum disulfide (MoS2), which at three atoms thick is one of the thinnest semiconductors in the world. In doing so, the team leveraged a singular behavior of MoS2: When exposed to certain chemicals, the material’s atoms rearrange in a way that acts like a switch, forcing a phase transition from a semiconductor to a metallic material. The resulting structure is known as a Schottky diode, which is the junction of a semiconductor with a metal.
“By engineering MoS2 into a 2-D semiconducting-metallic phase junction, we built an atomically thin, ultrafast Schottky diode that simultaneously minimizes the series resistance and parasitic capacitance,” says first author and EECS postdoc Xu Zhang, who will soon join Carnegie Mellon University as an assistant professor.
Parasitic capacitance is an unavoidable situation in electronics where certain materials store a little electrical charge, which slows down the circuit. Lower capacitance, therefore, means increased rectifier speeds and higher operating frequencies. The parasitic capacitance of the researchers’ Schottky diode is an order of magnitude smaller than today’s state-of-the-art flexible rectifiers, so it is much faster at signal conversion and allows it to capture and convert up to 10 gigahertz of wireless signals.
“Such a design has allowed a fully flexible device that is fast enough to cover most of the radio-frequency bands used by our daily electronics, including Wi-Fi, Bluetooth, cellular LTE, and many others,” Zhang says.
The reported work provides blueprints for other flexible Wi-Fi-to-electricity devices with substantial output and efficiency. The maximum output efficiency for the current device stands at 40 percent, depending on the input power of the Wi-Fi input. At the typical Wi-Fi power level, the power efficiency of the MoS2 rectifier is about 30 percent. For reference, today’s rectennas made from rigid, more expensive silicon or gallium arsenide achieve around 50 to 60 percent.
“This very nice teamwork from MIT demonstrates the first real application [of] atomically thin semiconductors for a flexible rectenna for energy harvesting,” says Philip Kim, a professor of physics and applied physics at Harvard University whose research focuses on 2-D materials. “I am amazed by the innovate approach that the team has set up to utilize the waste energy from RF power around us.”
There are 15 other paper co-authors from MIT, Technical University of Madrid, the Army Research Laboratory, Charles III University of Madrid, Boston University, and the University of Southern California.
The team is now planning to build more complex systems and improve efficiency. The work was made possible, in part, by a collaboration with the Technical University of Madrid through the MIT International Science and Technology Initiatives (MISTI). It was also partially supported by the Institute for Soldier Nanotechnologies, the Army Research Laboratory, the National Science Foundation’s Center for Integrated Quantum Materials, and the Air Force Office of Scientific Research.
Machine-learning approach could help robots assemble cellphones and other small parts in a manufacturing line.
In the basement of MIT’s Building 3, a robot is carefully contemplating its next move. It gently pokes at a tower of blocks, looking for the best block to extract without toppling the tower, in a solitary, slow-moving, yet surprisingly agile game of Jenga.
The robot, developed by MIT engineers, is equipped with a soft-pronged gripper, a force-sensing wrist cuff, and an external camera, all of which it uses to see and feel the tower and its individual blocks.
As the robot carefully pushes against a block, a computer takes in visual and tactile feedback from its camera and cuff, and compares these measurements to moves that the robot previously made. It also considers the outcomes of those moves — specifically, whether a block, in a certain configuration and pushed with a certain amount of force, was successfully extracted or not. In real-time, the robot then “learns” whether to keep pushing or move to a new block, in order to keep the tower from falling.
Details of the Jenga-playing robot are published today in the journal Science Robotics. Alberto Rodriguez, the Walter Henry Gale Career Development Assistant Professor in the Department of Mechanical Engineering at MIT, says the robot demonstrates something that’s been tricky to attain in previous systems: the ability to quickly learn the best way to carry out a task, not just from visual cues, as it is commonly studied today, but also from tactile, physical interactions.
“Unlike in more purely cognitive tasks or games such as chess or Go, playing the game of Jenga also requires mastery of physical skills such as probing, pushing, pulling, placing, and aligning pieces. It requires interactive perception and manipulation, where you have to go and touch the tower to learn how and when to move blocks,” Rodriguez says. “This is very difficult to simulate, so the robot has to learn in the real world, by interacting with the real Jenga tower. The key challenge is to learn from a relatively small number of experiments by exploiting common sense about objects and physics.”
He says the tactile learning system the researchers have developed can be used in applications beyond Jenga, especially in tasks that need careful physical interaction, including separating recyclable objects from landfill trash and assembling consumer products.
“In a cellphone assembly line, in almost every single step, the feeling of a snap-fit, or a threaded screw, is coming from force and touch rather than vision,” Rodriguez says. “Learning models for those actions is prime real-estate for this kind of technology.”
The paper’s lead author is MIT graduate student Nima Fazeli. The team also includes Miquel Oller, Jiajun Wu, Zheng Wu, and Joshua Tenenbaum, professor of brain and cognitive sciences at MIT. Push and pull
In the game of Jenga — Swahili for “build” — 54 rectangular blocks are stacked in 18 layers of three blocks each, with the blocks in each layer oriented perpendicular to the blocks below. The aim of the game is to carefully extract a block and place it at the top of the tower, thus building a new level, without toppling the entire structure.
To program a robot to play Jenga, traditional machine-learning schemes might require capturing everything that could possibly happen between a block, the robot, and the tower — an expensive computational task requiring data from thousands if not tens of thousands of block-extraction attempts.
Instead, Rodriguez and his colleagues looked for a more data-efficient way for a robot to learn to play Jenga, inspired by human cognition and the way we ourselves might approach the game.
The team customized an industry-standard ABB IRB 120 robotic arm, then set up a Jenga tower within the robot’s reach, and began a training period in which the robot first chose a random block and a location on the block against which to push. It then exerted a small amount of force in an attempt to push the block out of the tower.
For each block attempt, a computer recorded the associated visual and force measurements, and labeled whether each attempt was a success.
Rather than carry out tens of thousands of such attempts (which would involve reconstructing the tower almost as many times), the robot trained on just about 300, with attempts of similar measurements and outcomes grouped in clusters representing certain block behaviors. For instance, one cluster of data might represent attempts on a block that was hard to move, versus one that was easier to move, or that toppled the tower when moved. For each data cluster, the robot developed a simple model to predict a block’s behavior given its current visual and tactile measurements.
Fazeli says this clustering technique dramatically increases the efficiency with which the robot can learn to play the game, and is inspired by the natural way in which humans cluster similar behavior: “The robot builds clusters and then learns models for each of these clusters, instead of learning a model that captures absolutely everything that could happen.”
The researchers tested their approach against other state-of-the-art machine learning algorithms, in a computer simulation of the game using the simulator MuJoCo. The lessons learned in the simulator informed the researchers of the way the robot would learn in the real world.
“We provide to these algorithms the same information our system gets, to see how they learn to play Jenga at a similar level,” Oller says. “Compared with our approach, these algorithms need to explore orders of magnitude more towers to learn the game.”
Curious as to how their machine-learning approach stacks up against actual human players, the team carried out a few informal trials with several volunteers.
“We saw how many blocks a human was able to extract before the tower fell, and the difference was not that much,” Oller says.
But there is still a way to go if the researchers want to competitively pit their robot against a human player. In addition to physical interactions, Jenga requires strategy, such as extracting just the right block that will make it difficult for an opponent to pull out the next block without toppling the tower.
For now, the team is less interested in developing a robotic Jenga champion, and more focused on applying the robot’s new skills to other application domains.
“There are many tasks that we do with our hands where the feeling of doing it ‘the right way’ comes in the language of forces and tactile cues,” Rodriguez says. “For tasks like these, a similar approach to ours could figure it out.”
This research was supported, in part, by the National Science Foundation through the National Robotics Initiative.
MIT spinoff Raptor Maps uses machine-learning software to improve the maintenance of solar panels.
As the solar industry has grown, so have some of its inefficiencies. Smart entrepreneurs see those inefficiencies as business opportunities and try to create solutions around them. Such is the nature of a maturing industry.
One of the biggest complications emerging from the industry’s breakneck growth is the maintenance of solar farms. Historically, technicians have run electrical tests on random sections of solar cells in order to identify problems. In recent years, the use of drones equipped with thermal cameras has improved the speed of data collection, but now technicians are being asked to interpret a never-ending flow of unstructured data.
That’s where Raptor Maps comes in. The company’s software analyzes imagery from drones and diagnoses problems down to the level of individual cells. The system can also estimate the costs associated with each problem it finds, allowing technicians to prioritize their work and owners to decide what’s worth fixing.
“We can enable technicians to cover 10 times the territory and pinpoint the most optimal use of their skill set on any given day,” Raptor Maps co-founder and CEO Nikhil Vadhavkar says. “We came in and said, ‘If solar is going to become the number one source of energy in the world, this process needs to be standardized and scalable.’ That’s what it takes, and our customers appreciate that approach.”
Raptor Maps processed the data of 1 percent of the world’s solar energy in 2018, amounting to the energy generated by millions of panels around the world. And as the industry continues its upward trajectory, with solar farms expanding in size and complexity, the company’s business proposition only becomes more attractive to the people driving that growth.
Picking a path
Raptor Maps was founded by Eddie Obropta ’13 SM ’15, Forrest Meyen SM ’13 PhD ’17, and Vadhavkar, who was a PhD candidate at MIT between 2011 and 2016. The former classmates had worked together in the Human Systems Laboratory of the Department of Aeronautics and Astronautics when Vadhavkar came to them with the idea of starting a drone company in 2015.
The founders were initially focused on the agriculture industry. The plan was to build drones equipped with high-definition thermal cameras to gather data, then create a machine-learning system to gain insights on crops as they grew. While the founders began the arduous process of collecting training data, they received guidance from MIT’s Venture Mentoring Service and the Martin Trust Center. In the spring of 2015, Raptor Maps won the MIT $100K Launch competition.
But even as the company began working with the owners of two large farms, Obropta and Vadhavkar were unsure of their path to scaling the company. (Meyen left the company in 2016.) Then, in 2017, they made their software publicly available and something interesting happened.
They found that most of the people who used the system were applying it to thermal images of solar farms instead of real farms. It was a message the founders took to heart.
“Solar is similar to farming: It’s out in the open, 2-D, and it’s spread over a large area,” Obropta says. “And when you see [an anomaly] in thermal images on solar, it usually means an electrical issue or a mechanical issue — you don’t have to guess as much as in agriculture. So we decided the best use case was solar. And with a big push for clean energy and renewables, that aligned really well with what we wanted to do as a team.”
Obropta and Vadhavkar also found themselves on the right side of several long-term trends as a result of the pivot. The International Energy Agency has proposed that solar power could be the world’s largest source of electricity by 2050. But as demand grows, investors, owners, and operators of solar farms are dealing with an increasingly acute shortage of technicians to keep the panels running near peak efficiency.
Since deciding to focus on solar exclusively around the beginning of 2018, Raptor Maps has found success in the industry by releasing its standards for data collection and letting customers — or the many drone operators the company partners with — use off-the-shelf hardware to gather the data themselves. After the data is submitted to the company, the system creates a detailed map of each solar farm and pinpoints any problems it finds.
“We run analytics so we can tell you, ‘This is how many solar panels have this type of issue; this is how much the power is being affected,’” Vadhavkar says. “And we can put an estimate on how many dollars each issue costs.”
The model allows Raptor Maps to stay lean while its software does the heavy lifting. In fact, the company’s current operations involve more servers than people.
The tiny operation belies a company that’s carved out a formidable space for itself in the solar industry. Last year, Raptor Maps processed four gigawatts worth of data from customers on six different continents. That’s enough energy to power nearly 3 million homes.
Vadhavkar says the company’s goal is to grow at least fivefold in 2019 as several large customers move to make the software a core part of their operations. The team is also working on getting its software to generate insights in real time using graphical processing units on the drone itself as part of a project with the multinational energy company Enel Green Power.
Ultimately, the data Raptor Maps collect are taking the uncertainty out of the solar industry, making it a more attractive space for investors, operators, and everyone in between.
“The growth of the industry is what drives us,” Vadhavkar says. “We’re directly seeing that what we’re doing is impacting the ability of the industry to grow faster. That’s huge. Growing the industry — but also, from the entrepreneurial side, building a profitable business while doing it — that’s always been a huge dream.”