Now that Root AI’s robot has mastered the art of picking oblong vegetables as well as oblate shaped berries, could this technology help enhance global food security?
In recent months, the coronavirus pandemic has highlighted frangibility in the global supply networks; particularly those involved in food security. Hallmarks of digital transformation, automation, and artificial intelligence, are being tapped to create a decentralized 21st century food chain.
On Thursday, the agricultural robotics and artificial intelligence company Root AI announced new capabilities to its AI-enhanced robotic harvester as well as investments totaling more than $7 million. Now that the AI-enhanced robotic harvester has demonstrated enhanced dexterity to tackle crops of various shapes and sizes, the technology could help shore up these vulnerabilities.
Ripe for the automated picking
In the past, Root AI has provided glimpses of its robo-harvester, known as Virgo, picking ripe tomatoes off the vine. In the latest video titled “Going Cross-Crop,” Virgo is shown picking cucumbers and strawberries in the field. In the accompanying press release, the company asserted that Virgo was the “world’s first robot ever to replicate a person’s ability to harvest multiple crops.”
In an indoor agriculture environment, Virgo can be situated on a track in between rows of various crops. As it navigates a greenhouse, the robot leverages a host of sensors as well as artificial intelligence to analyze crop positions and ripeness and then uses a specialized gripper to pick produce once it’s ready.
The machine sees its environment in 3D using intelligent motion sensing. This data allows Virgo to determine an optimal route, through vines, leaves, other unripe crops, to pluck its target. As Root AI CEO Josh Lessing explained, Virgo uses more than computer vision to see its environment and plan accordingly.
“We need to go beyond computer vision that finds fruit in three-dimensional space. We do that, but on top, we have a layer of computer perception that then plans how to go about grasping that fruit. How do I navigate through the environment and then land my fingers on that target to effectively pick it? To move with authority, the same way people look at an object that they want to pick, the mind needs to create a plan,” Lessing said.
The company is building solutions to enable its fleet of systems to learn on the job, so to speak, and then share these insights with other robotic harvesters in the field.
“We’re building artificial intelligence algorithms that understand how to do a task, but as it works, learns how to do it better, and then shares those learnings across a fleet of systems,” Lessing said.
Whether it’s an apple in a tree or a strawberry in a bush, these are both similar challenges from an identification, planning, and picking perspective, explained Lessing. The robotic gripper and software can be swapped for different crops, however, the underlying principles surrounding planning and picking will enable application across crops.
“It’s the same gripping concept, but for your human hand, when you grab a cucumber or, which is a cylinder, or you grab a tomato, which is an orb, you pose your fingers in different arrangements to grab them. Virgo is doing the same. So to go between different crops, you would swap the hand, which is a quick operation, and then use a different software package that is trained to go after the vegetable you’re interested in,” Lessing said.
Labor shortages and supply chain disruptions
In recent years, farmers have faced struggles with labor shortages throughout the agriculture industry. In California, more than half (56%) of participating farmers were “unable to hire all the employees they needed for production of their main crop at some point during the past five years,” according to a California Farm Bureau Federation report.
As a result, 56% of the farmers surveyed reported using labor-reducing technology. About half the farmers who incorporated mechanization solutions adopted these practices due to labor shortages.
“It’s also increasingly challenging to find master growers. Fewer and fewer people are training to become these virtuosos of crop care and yield optimization. This is the moment in human history to start transferring those learnings to artificial intelligence, so we have a sustainable infrastructure that guarantees we have enough to eat,” Lessing said.
In recent months, the coronavirus has shone a light on the vulnerabilities inherent within the global food supply chain. Due to market disruptions, farmers were forced to dump millions of gallons of milk, bury crops, and plow edible produce into fields. To assist, a number of organizations are looking to create regional supply chains.
“What we need is the capacity to grow any of a number of staple crops that are in our diets, close to the cities where they’re consumed and to be able to do that using sustainable agriculture practices. So that agriculture is no longer one of the largest polluters on the planet,” Lessing said.
The cost of many of the technologies integral to indoor agriculture has dropped substantially in recent years; especially the price of LED light arrays. This has set the stage for market competition in the industry. Similarly, Lessing explained that robotics has undergone a technological revolution of sorts over the last five years with technologies ranging from cloud-enabled model training to high-resolution depth sensors.
These advancements have reached a tipping point where organizations can start leveraging these solutions to create sustainable, decentralized food networks, despite human labor shortages. In tandem, these technologies could buttress the availability and security of human civilization’s central needs.
“The vision and the goal of the business is for food production to become automatic. People need healthcare, they need housing, they need food. At Root, we are focused on solving one of those problems: food. And if we can build the automated food infrastructure that the world needs, we will have forever solved one of humanity’s biggest challenges,” Lessing said.
Be in the know about smart cities, AI, Internet of Things, VR, AR, robotics, drones, autonomous driving, and more of the coolest tech innovations. Delivered Wednesdays and Fridays
A Human-Computer Duet System for Music Performance
Despite the popularity of virtual musicians, most of them cannot play together with human musicians following their tempo or create their own behaviors without the aid of human characters. The authors of a recent paper created a virtual violinist having these characteristics.
It can track music and adapt to the human pianist’s tempo varying with time and with performance, making the two voices harmonized. The virtual musician’s body movements are generated directly from the music. The motion generator is trained on a music video dataset of violin performance and a pose sequence synchronized with live performance is generated.
These features mean that the human musician can practice, rehearse, and perform music with the virtual musician like with a real human, by following the music content. The proposed system has successfully performed in a ticket-selling concert, where a movement from Beethoven’s Spring Sonata was played.
Virtual musicians have become a remarkable phenomenon in the contemporary multimedia arts. However, most of the virtual musicians nowadays have not been endowed with abilities to create their own behaviors, or to perform music with human musicians. In this paper, we firstly create a virtual violinist, who can collaborate with a human pianist to perform chamber music automatically without any intervention. The system incorporates the techniques from various fields, including real-time music tracking, pose estimation, and body movement generation. In our system, the virtual musician’s behavior is generated based on the given music audio alone, and such a system results in a low-cost, efficient and scalable way to produce human and virtual musicians’ co-performance. The proposed system has been validated in public concerts. Objective quality assessment approaches and possible ways to systematically improve the system are also discussed.
Xbox Series X, Series S India Pre-Order Time, Online Retailers Announced
India pre-orders for Xbox Series X and Series S will go live at 9am IST on Tuesday, September 22, Microsoft India has announced. Both Series X and Series S will be available on Amazon, Flipkart, and Reliance Digital’s online store. No offline stores have been announced. India is one of 37 countries where the new Xbox Series family will be up for pre-order on Tuesday, in addition to the US, the UK, Canada, Australia, New Zealand, and parts of Europe, Middle East, and Africa.
While the Xbox Series X and Series S pre-order date was announced alongside the prices — Rs. 49,990 for the Series X and Rs. 34,990 for the Series S — and launch date (November 10) last week, we didn’t have details on an exact pre-order time and where it would be available. Now we know. Gadgets 360 has also reached out to Microsoft India on details regarding special discounts (credit / debit card cashback offers) and financing options (no-cost EMIs), and we will update if we hear back.
For those outside India, here’s where you can pre-order the Xbox Series X and Series S. In the US, pre-orders go live Tuesday, September 22 at 8am PT / 11am ET on Microsoft Store, Amazon, Best Buy, GameStop, Walmart, Target, Sam’s Club, Newegg, and other participating retailers. Up north in Canada, pre-orders also go live at 8am PT / 11am ET on Microsoft Store, Amazon, Walmart, Best Buy, EB Games, The Source, and other participating retailers.
Across the pond in the UK, Xbox Series X and Series S pre-orders will be available Tuesday 8am BST on Microsoft Store, GAME, Amazon, Dixons, Currys PC World, Argos, John Lewis, Smyths Toys, VERY, AO, Tesco, Simply Game, Shopto and other participating retailers. In mainland Europe, as well as the Middle East and Africa, you can pre-order online starting at 9am CEST on Microsoft Store, Amazon, MediaMarkt, GameStop, FNAC, Elkjøp/Elgiganten, and other participating retailers.
Down under all the way in Australia, Xbox Series X and Series S pre-orders kick off Tuesday, September 22 at 8am AEST on Microsoft Store, JB Hifi, EB Games, Telstra, Harvey Norman, and other participating retailers. And in nearby New Zealand, you can pre-order both new Xbox Series consoles starting 8am NZST on Microsoft Store, JB HiFi, EB Games, Spark, and other participating retailers.
In select markets, both Xbox Series X and Series S are available under a subscription programme, Xbox All Access, which bundles the consoles with the Xbox Game Pass membership.
Xbox Series S and Series X will launch in 37 countries — including India — on November 10, and 41 countries during “holiday 2020”.
Netflix engineer builds SnapCamera lens to bring a comic book vibe to video calls
Snapchat’s Lens Studio has built-in recognition for 5 hand gestures that means you don’t have to unmute to say hi or BRB.
If you need something to ease the frustration of conversations via video chat, consider a new Snap Camera lens. Cameron Hunter, a senior software engineer at Netflix, created Meeting Gestures. Instead of unmuting to say, “hi,” or “ok,” this lens communicates the information with a gesture instead.
When you raise your index finger, “Question” pops up on your video feed in a red comic-book word bubble. Hunter used the smile recognition in Snap Camera to display “ha, ha” bubbles. Moving outside the frame brings up “I’ll be right back” in a word bubble that fills the screen.
Snap Camera is simple to install and use. It works on Zoom, Skype, Microsoft Teams, and Twitch. Once you’ve got Snap Camera installed, set your video conference camera to Snap Camera. You have to run Snap Camera and your web conferencing software at the same time.
Most lenses have a more user friendly name. On Tuesday, Hunter said he was working with SnapChat to resolve an issue with the name of the lens.
That link will bring up Hunter’s lens. The word bubbles will look backward to you but will read correctly for viewers.
Build your own lens
Hunter’s Twitter post sparked several ideas about additional gestures for the Snap Camera library, including sign language. Hunter tweeted that you can lock messages or images to tracked objects such as a hand or a head. Snap Lens Studio does not support the middle finger gesture. Twitter user Johnny Xmas suggested the Meeting Gestures lens would be helpful during a large-scale scrum.
Ryan Brown, content and creative lead at Twitter, built his own meeting friendly lens. When you hold up an open palm, a flash of fire pops up and a heart flashes up when you hold up an index finger.
Lens Studio has a guide that explains how to make a lens. You can create Face Lenses for front camera experiences and World Lenses for rear camera experiences.