Robot fruit pickers to put migrant agricultural laborers out of work

Some of the biggest fruit orchards in the U.S. may soon use robots in harvesting fruits, as two robotics firms are currently developing machines that could accelerate fruit picking. Mechanical harvesting has become a staple practice in many farms for crops such as wheat, corn, green beans, tomatoes and others. However, the harvesting of fragile, easily-perishable crops — such as apples, berries, table grapes and lettuce — are still done through manual labor. Fruit orchards in Washington state alone require thousands of farm workers to do the harvesting.

Israel-based FFRobotics noted that human pickers are getting scarce, with many young people shying away from farm work. The firm also stressed that elderly pickers are slowly retiring. In line with this, the company is currently working on a machine with three-fingered grips designed to grab fruit and twist or clip it from a branch. According to company co-founder Gad Kober, the machine will feature between four and 12 robotic arms, and can harvest as many as 10,000 apples an hour. The machine would also be able to harvest 85 to 90 percent of the crop off trees. The remaining crops could then be manually harvested by workers, Kober noted. On the other hand, California-based Abundant Robotics is developing a machine that makes use of suction technology to vacuum apples off trees. Plans for machine production were discussed in February at an international convention of fruit growers. The company aims to launch the robotic harvesters in the market before 2019.

The two robotics companies are likely to achieve their production targets, with both prototypes projected to be released this fall, according to Karen Lewis. Lewis is a Washington State University cooperative extension agent who assessed the use of robotics in fruit orchards. Lewis also noted that while the machines will serve as game changers in harvesting, fruit orchards across the country may be required to cultivate fruits in new trellis systems to allow the machines to see and harvest the crops.

Experts raise flags on potential losses in migrant laborers

Despite the agricultural advances, the announcement did not sit well with many agricultural experts. According to experts, robot pickers will negatively impact the livelihood of farm workers especially the migrant labor sector, many of whom have been illegally working in the U.S. An analysis by the Pew Research Center revealed that unauthorized immigrant workers accounted for 17 percent of the workforce in the U.S. agriculture industry in 2014.

Washington has long suffered from human power shortages, and has greatly depended on immigrant workers from Mexico to harvest many crops. According to Erik Nicholson, an official with the United Farm Workers union, the eventual loss of jobs among human pickers will have huge implications. Nicholson estimated that about half of Washington’s farm workers are illegal immigrants. However, he stressed that many of them have settled in the state and were productive members of the society. “They are scared of losing their jobs to mechanisation [sic]. A robot is not going to rent a house, buy clothing for their kids, buy food in a grocery and reinvest that money in the local economy,” Nicholson was quoted in DailyMail.co.uk.

President Donald trump’s hard-hitting policies against illegal migrant workers have had farms and orchards scrambling for alternative harvesting methods. Some farms have purchased new equipment in order to cut back on human resources. Other farms have even lobbied with federal officials for deals that would limit the negative effects of recent policies on their livelihoods. Jim McFerson, head of the Washington State Tree Fruit Research Centre, stressed that the recent immigration conundrum is now a matter of survival for many farmers.

Sources include: 

DailyMail.co.uk

Like
Like Love Haha Wow Sad Angry
1

Robots Podcast #230: bots_alive, with Bradley Knox

In this episode, Audrow Nash interviews Bradley Knox, founder of bots_alive. Knox speaks about an add-on to a Hexbug, a six-legged robotic toy, that makes the bot behave more like a character. They discuss the novel way Knox uses machine learning to create a sense character. They also discuss the limitation of technology to emulate living creatures, and how the bots_alive robot was built within these limitations.

 

Brad Knox


Dr. Bradley Knox is the founder of bots_alive. He researched human-robot interaction, interactive machine learning, and artificial intelligence at the MIT Media Lab and at UT Austin. At MIT, he designed and taught Interactive Machine Learning. He has won two best paper awards at major robotics and AI conferences, was awarded best dissertation from UT Austin’s Computer Science Department, and was named to IEEE’s AI’s 10 to Watch in 2013.

Like
Like Love Haha Wow Sad Angry
1

World’s First Robot Farm

Japanese sustainable vegetable producer, Spread, is creating the world’s first farm manned entirely by robots at its new facility in Kyoto, set to open in 2017.  Instead of relying on a crew of human farmers, the indoor Vegetable Factory will employ robots that can harvest 30,000 heads of lettuce every day. The move comes in response to rising concerns in Japan that an aging population will result in a labor shortage. To circumvent this disaster, government and tech industries are furthering the development of robotics to replace human farm laborers.

According to J.J. Price, a spokesperson for Spread, “Our mission is to help create a sustainable society where future generations will not have to worry about food security and food safety.” He says, “This means that we will have to make it affordable for everyone and begin to grow staple crops and plant protein to make a real difference.”

Price speaks for many experts. There’s a global concern that the current global food production paradigm is unsustainable. The U.N. estimates that by 2050 we’ll need to sustainably produce 70 percent more food by calories than we do now in order to keep up with population growth. The problem is that there will be less land for farming as the planet’s population grows. Another factor is that farmers are aging globally as younger generations migrate to cities, largely because a productivity boom over the last century has kept food prices low, making farming unattractive economically.

The Vegetable Factory is part of the growing agricultural trend of vertical farming, where farmers grow crops indoors without natural sunlight. Instead, they rely on LED light and grow crops on racks that stack on top of each other. This arrangement can reduce labor costs by 50%, cut energy use by 30%, and recycle 98% of water needed to grow the crops.

The majority of the farm bots will be articulated arms that work around a conveyer belt running throughout the 4,400 square meter farm, with floor-to-ceiling shelves growing pesticide-free lettuce. The robotic arms will transfer and replant seedlings and perform all harvesting. The smart farm will automatically optimize temperature, humidity, and CO2 levels. The new farm will be an upgrade to Spread’s existing plant in Kameoke, Japan. That farm produces 21,000 head of lettuce per day with a small staff of human employees.

Automated farms are the future of farming. Tech giants including Panasonic, Toshiba, and Sharp are currently experimenting with their own robotic farming solutions.

Like
Like Love Haha Wow Sad Angry

Drones to Land themselves on moving targets

The buzzword in drone research is autonomous — having the unmanned aerial vehicle do most or all of its own flying.

It’s the only realistic way that drones will have commercially viable uses such as delivering that roll of toilet paper to customers, said Manish Kumar, associate professor of mechanical engineering at the University of Cincinnati’s College of Engineering and Applied Science.

Kumar and his co-authors, Nicklas Stockton, a UC researcher, and Kelly Cohen, aerospace engineering professor, considered the difficulty drones have in navigating their ever-changing airspace in a study presented at the American Institute of Aeronautics and Astronautics SciTech 2017 Conference in January.

This problem is compounded when the drone tries to land on a moving platform such as a delivery van or even a U.S. Navy warship pitching in high seas.

To address this challenge, UC researchers applied a concept called fuzzy logic, the kind of reasoning people employ subconsciously every day.

While scientists are concerned with precision and accuracy in all they do, most people get through their day by making inferences and generalities, or by using fuzzy logic. Instead of seeing the world in black and white, fuzzy logic allows for nuance or degrees of truth.

Fuzzy logic helps the drone make good navigational decisions amid a sea of statistical noise, he said. It’s called “genetic-fuzzy” because the system evolves over time and continuously discards the lesser solutions.

Stockton, Kumar, and Cohen successfully employed fuzzy logic in a simulation to show it is an ideal system for navigating under dynamic conditions. Stockton, an engineering master’s student who was the lead author on the paper, is putting fuzzy logic to the test in experiments to land quadcopters on robots mounted with landing pads at UC’s UAV Multi-Agent System Research (MASTER) Lab.

Stockton is just the latest UC student mentored by Cohen who was offered a job, at least in part, for his experience in fuzzy logic. The U.S. Air Force offered Stockton a federal position to continue his engineering research at Wright-Patterson Air Force Base when he graduates this summer.

UC doctoral graduate Nick Ernest, another student of Cohen’s, started an artificial intelligence company called Psibernetix, Inc., that demonstrated the power of fuzzy logic last year when a fuzzy-logic-based artificial intelligence, dubbed ALPHA, bested a human fighter pilot in simulated dogfights.

 

Like
Like Love Haha Wow Sad Angry
41

Driverless-vehicle options now include scooters

Driverless-vehicle options now include scooters

At MIT’s 2016 Open House last spring, more than 100 visitors took rides on an autonomous mobility scooter in a trial of software designed by researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), the National University of Singapore, and the Singapore-MIT Alliance for Research and Technology (SMART).

The researchers had previously used the same sensor configuration and software in trials of autonomous cars and golf carts, so the new trial completes the demonstration of a comprehensive autonomous mobility system. A mobility-impaired user could, in principle, use a scooter to get down the hall and through the lobby of an apartment building, take a golf cart across the building’s parking lot, and pick up an autonomous car on the public roads.

The new trial establishes that the researchers’ control algorithms work indoors as well as out. “We were testing them in tighter spaces,” says Scott Pendleton, a graduate student in mechanical engineering at the National University of Singapore (NUS) and a research fellow at SMART. “One of the spaces that we tested in was the Infinite Corridor of MIT, which is a very difficult localization problem, being a long corridor without very many distinctive features. You can lose your place along the corridor. But our algorithms proved to work very well in this new environment.”

The researchers’ system includes several layers of software: low-level control algorithms that enable a vehicle to respond immediately to changes in its environment, such as a pedestrian darting across its path; route-planning algorithms; localization algorithms that the vehicle uses to determine its location on a map; map-building algorithms that it uses to construct the map in the first place; a scheduling algorithm that allocates fleet resources; and an online booking system that allows users to schedule rides.

Uniformity

Using the same control algorithms for all types of vehicles — scooters, golf carts, and city cars — has several advantages. One is that it becomes much more practical to perform reliable analyses of the system’s overall performance.

“If you have a uniform system where all the algorithms are the same, the complexity is much lower than if you have a heterogeneous system where each vehicle does something different,” says Daniela Rus, the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT and one of the project’s leaders. “That’s useful for verifying that this multilayer complexity is correct.”

Furthermore, with software uniformity, information that one vehicle acquires can easily be transferred to another. Before the scooter was shipped to MIT, for instance, it was tested in Singapore, where it used maps that had been created by the autonomous golf cart.

Similarly, says Marcelo Ang, an associate professor of mechanical engineering at NUS who co-leads the project with Rus, in ongoing work the researchers are equipping their vehicles with machine-learning systems, so that interactions with the environment will improve the performance of their navigation and control algorithms. “Once you have a better driver, you can easily transplant that to another vehicle,” says Ang. “That’s the same across different platforms.”

Finally, software uniformity means that the scheduling algorithm has more flexibility in its allocation of system resources. If an autonomous golf cart isn’t available to take a user across a public park, a scooter could fill in; if a city car isn’t available for a short trip on back roads, a golf cart might be.

“I can see its usefulness in large indoor shopping malls and amusement parks to take [mobility-impaired] people from one spot to another,” says Dan Ding, an associate professor of rehabilitation science and technology at the University of Pittsburgh, about the system.

Changing perceptions

The scooter trial at MIT also demonstrated the ease with which the researchers could deploy their modular hardware and software system in a new context. “It’s extraordinary to me, because it’s a project that the team conducted in about two months,” Rus says. MIT’s Open House was at the end of April, and “the scooter didn’t exist on February 1st,” Rus says.

The researchers described the design of the scooter system and the results of the trial in a paper they presented last week at the IEEE International Conference on Intelligent Transportation Systems. Joining Rus, Pendleton, and Ang on the paper are You Hong Eng, who leads the SMART autonomous-vehicle project, and four other researchers from both NUS and SMART.

The paper also reports the results of a short user survey that the researchers conducted during the trial. Before riding the scooter, users were asked how safe they considered autonomous vehicles to be, on a scale from one to five; after their rides, they were asked the same question again. Experience with the scooter brought the average safety score up, from 3.5 to 4.6.

Like
Like Love Haha Wow Sad Angry
73

Delivery by drone

In the near future, the package that you ordered online may be deposited at your doorstep by a drone: Last December, online retailer Amazon announced plans to explore drone-based delivery, suggesting that fleets of flying robots might serve as autonomous messengers that shuttle packages to customers within 30 minutes of an order.

To ensure safe, timely, and accurate delivery, drones would need to deal with a degree of uncertainty in responding to factors such as high winds, sensor measurement errors, or drops in fuel. But such “what-if” planning typically requires massive computation, which can be difficult to perform on the fly.

Now MIT researchers have come up with a two-pronged approach that significantly reduces the computation associated with lengthy delivery missions. The team first developed an algorithm that enables a drone to monitor aspects of its “health” in real time. With the algorithm, a drone can predict its fuel level and the condition of its propellers, cameras, and other sensors throughout a mission, and take proactive measures — for example, rerouting to a charging station — if needed.

The researchers also devised a method for a drone to efficiently compute its possible future locations offline, before it takes off. The method simplifies all potential routes a drone may take to reach a destination without colliding with obstacles.

In simulations involving multiple deliveries under various environmental conditions, the researchers found that their drones delivered as many packages as those that lacked health-monitoring algorithms — but with far fewer failures or breakdowns.

“With something like package delivery, which needs to be done persistently over hours, you need to take into account the health of the system,” says Ali-akbar Agha-mohammadi, a postdoc in MIT’s Department of Aeronautics and Astronautics. “Interestingly, in our simulations, we found that, even in harsh environments, out of 100 drones, we only had a few failures.”

Agha-mohammadi will present details of the group’s approach in September at the IEEE/RSJ International Conference on Intelligent Robots and Systems, in Chicago. His co-authors are MIT graduate student Kemal Ure; Jonathan How, the Richard Cockburn Maclaurin Professor of Aeronautics and Astronautics; and John Vian of Boeing.

Tree of possibilities

Planning an autonomous vehicle’s course often involves an approach called Markov Decision Process (MDP), a sequential decision-making framework that resembles a “tree” of possible actions. Each node along a tree can branch into several potential actions — each of which, if taken, may result in even more possibilities. As Agha-mohammadi explains it, MDP is “the process of reasoning about the future” to determine the best sequence of policies to minimize risk.

MDP, he says, works reasonably well in environments with perfect measurements, where the result of one action will be observed perfectly. But in real-life scenarios, where there is uncertainty in measurements, such sequential reasoning is less reliable. For example, even if a command is given to turn 90 degrees, a strong wind may prevent that command from being carried out.

Instead, the researchers chose to work with a more general framework of Partially Observable Markov Decision Processes (POMDP). This approach generates a similar tree of possibilities, although each node represents a probability distribution, or the likelihood of a given outcome. Planning a vehicle’s route over any length of time, therefore, can result in an exponential growth of probable outcomes, which can be a monumental task in computing.

Agha-mohammadi chose to simplify the problem by splitting the computation into two parts: vehicle-level planning, such as a vehicle’s location at any given time; and mission-level, or health planning, such as the condition of a vehicle’s propellers, cameras, and fuel levels.

For vehicle-level planning, he developed a computational approach to POMDP that essentially funnels multiple possible outcomes into a few most-likely outcomes.

“Imagine a huge tree of possibilities, and a large chunk of leaves collapses to one leaf, and you end up with maybe 10 leaves instead of a million leaves,” Agha-mohammadi says. “Then you can … let this run offline for say, half an hour, and map a large environment, and accurately predict the collision and failure probabilities on different routes.”

He says that planning out a vehicle’s possible positions ahead of time frees up a significant amount of computational energy, which can then be spent on mission-level planning in real time. In this regard, he and his colleagues used POMDP to generate a tree of possible health outcomes, including fuel levels and the status of sensors and propellers.

Proactive delivery

The researchers combined the two computational approaches, and ran simulations in which drones were tasked with delivering multiple packages to different addresses under various wind conditions and with limited fuel. They found that drones operating under the two-pronged approach were more proactive in preserving their health, rerouting to a recharge station midmission to keep from running out of fuel. Even with these interruptions, the team found that these drones were able to deliver just as many packages as those that were programmed to simply make deliveries without considering health.

Going forward, the team plans to test the route-planning approach in actual experiments. The researchers have attached electromagnets to small drones, or quadrotors, enabling them to pick up and drop off small parcels. The team has also programmed the drones to land on custom-engineered recharge stations.

We believe in the near future, in a lab setting, we can show what we’re gaining with this framework by delivering as many packages as we can while preserving health,” Agha-mohammadi says. “Not only the drone, but the package might be important, and if you fail, it could be a big loss.”

Like
Like Love Haha Wow Sad Angry
5

Cancer-Fighting Army? Magnetic Robot Swarms Could Combat Disease

The Lego bot can move each limb independently of the other thanks to its magnetically controlled screws placed in a unique layered magnetic field.

Magnetically controlled swarms of microscopic robots might one day help fight cancer inside the body, new research suggests.

Over the past decade, scientists have shown they can manipulate magnetic forces to guide medical devices within the human body, as these fields can apply forces to remotely control objects. For instance, prior work used magnetic fields to maneuver a catheter inside the heart and steer video capsules in the gut.

Previous research also used magnetic fields to simultaneously control swarms of tiny magnets. In principle, these objects could work together on large problems such as fighting cancers. However, individually guiding members of a team of microscopic devices so that each moves in its own direction and at its own speed remains a challenge. This is because identical magnetic items under the control of the same magnetic field usually behave identically to each other. [The 6 Strangest Robots Ever Created]

Now, scientists have developed a way to magnetically control each member of a swarm of magnetic devices to perform specific, unique tasks, researchers in the new study said.

“Our method may enable complex manipulations inside the human body,” said study lead author Jürgen Rahmer, a physicist at Philips Innovative Technologies in Hamburg, Germany.

First, the scientists created a number of tiny identical magnetic screws. The researchers next used a strong, uniform magnetic field to freeze groups of these magnetic screws in place. In small, weak spots within this powerful magnetic field, the microscopic screws are free to move. Superimposing a relatively weak rotating magnetic field could make these free screws spin, the researchers said.

In experiments, the researchers could make several magnetic screws whirl in different directions at the same time with pinpoint accuracy. In principle, the scientists noted, they could manipulate hundreds of microscopic robots at once.First, the scientists created a number of tiny identical magnetic screws. The researchers next used a strong, uniform magnetic field to freeze groups of these magnetic screws in place. In small, weak spots within this powerful magnetic field, the microscopic screws are free to move. Superimposing a relatively weak rotating magnetic field could make these free screws spin, the researchers said.

“One could think of screw-driven mechanisms that perform tasks inside the human body without the need for batteries or motors,” Rahmer told Live Science.

One application for these magnetic swarms could involve magnetic screws embedded within injectable microscopic pills. Doctors could use magnetic fields to make certain screws spin to open the pills, the researchers said. This could help doctors make sure that cancer-killing radioactive “seeds” within the pills target and damage only tumors rather than healthy tissues, cutting down on harmful side effects, the researchers said. Once the pills deliver a therapeutic dose of radiation, physicians could then use magnets to essentially switch the pills off. (The pills would be made of metallic material that would otherwise keep radiation from leaking out.)

Another potential application could be medical implants that change over time, the researchers said. For instance, as people heal, magnetic fields could help alter the shape of implants to better adjust to the bodies of patients, Rahmer said.

In the future, researchers could develop compact and magnetic field applicators to control tiny magnetic robots, and use imaging technologies such as X-ray machines or ultrasound scanners to show where those devices are located in the body, Rahmer suggested.

The scientists detailed their findings online Feb. 15 in the journal Science Robotics.

 

Like
Like Love Haha Wow Sad Angry
431