Drake: Robotics Planning, Control And Analysis Toolbox
From MIT:
Drake ("dragon" in Middle English) is a toolbox maintained by the Robot Locomotion Group at the MIT Computer Science and Artificial Intelligence Lab (CSAIL). It is a collection of tools for analyzing the dynamics of our robots and building control systems for them in MATLAB and C++, with a heavy emphasis on optimization-based design/analysis. Here is a quick summary of capabilities:
Simulation
Rigid-body dynamics including contact/collisions (hybrid+LCP) and kinematic loops
Basic aerodynamics/fluid dynamics
Sensor models (lidar, depth camera, imu, contact force/torque; cameras coming soon)
Hand-derived models for many canonical control dynamical systems
Easily add your own models/components
Some support for stochastic models
For all of the above we aim to expose sparsity and provide analytical gradients / symbolic analysis
Primary limitations: code is optimized for analysis / planning / control design (as opposed to speed, generality)...
​... Most of these models/tools are described in the companion textbook from an MIT course/MOOC . We've also recently started populating the Drake Gallery (contributions welcome!)... ( git repo )
ABB's largest ever robot is 25 percent faster than competitor robots in high payload range
ABB has introduced its highest payload, multipurpose industrial robot, the IRB 8700. The robot has a reach of 3.5 meters and is capable of handling a payload of up to 800 kg (1000 kg with the wrist down; 630 kg with LeanID). Designed for the ultimate in uptime, reliability and reduced maintenance, the IRB 8700 provides the lowest total cost of ownership among competitor high payload robot models. The new robot is targeted for material handling applications in the automotive, transportation and other heavy industries.
“When designing the IRB 8700, we focused on combining ABB’s largest ever model with an unusually long reach for a robot in the high payload class,” said John Bubnikovich, vice president, sales and marketing, ABB Robotics North America. “Utilizing ABB’s superior motion control technology at high moments of inertia, the new robot automatically adapts and adjusts its speed to accommodate heavy and wide parts. With a compact footprint, optimized counterweight, parallel linkages, stiff axes and fewer drive motors, the IRB 8700 keeps its momentum down and speed up, providing unmatched agility and performance.”
The IRB 8700, ABB’s largest ever robot offers all the functionality and expertise of the ABB portfolio in a much bigger package. The robot has only one motor and one gear per robot axis, while most other robots in this size class use dual motors and/or gears. In addition, there are no gas springs; only a reliable counterweight and mechanical springs for counter balancing. Together these design elements mean the IRB 8700 has fewer components and is able to deliver shorter cycle times and higher accuracy – making it 25% faster than any comparable competitor robots in its payload range. Full Press Release:
Amazon's robotics group asked the FCC to test special wireless equipment
Jillian D'Onfro for Business Insider: Amazon is ramping up its robotics efforts and testing new technology that could make it safer to operate the fleet of robots toiling in its warehouses, according to recent FCC filings.
The FCC gave Amazon Robotics an expedited experimental license to test a "proximity sensing system" that the company hopes to deploy in fulfillment centers outside the U.S.
Amazon Robotics "seeks to evaluate radiolocation technology to be used in the operation of robotics in fulfillment centers outside the United States," the company said in the filing, the first such FCC filing by Amazon Robotics.
While Amazon stresses that the technology is strictly for internal use, and not something it intends to sell to "end users," the filing underscores the company's increasing investment and innovation in robotics, which has the potential to transform a broad swath of industrial and consumer markets. Cont'd...
There's a five-story vending machine dispensing used cars in Nashville
From Mashable:
That's right; online used car retailer Carvana has officially unveiled its first vending machine completely stocked with cars. Standing at five stories tall, the coin-operated (yes, really) glass tower vending machine can house as many as 20 used cars at a time. The facility also includes a welcome center and three customer delivery bays to which the cars are dispensed... ( full story )
Simbe Robotics launches new retail robot
By Silicon Valley Robotics via Robohub: The area of service robotics is getting active, with a new retail robot startup launching today. Tally is one of several robotics startups launching today at Haxlr8r’s 7th Demo Day. Tally is an inventory tracking robot platform fromSimbe Robotics and the “world’s first robotic autonomous shelf auditing and analytics solution” according to the press release.
Tally is in trials with several North American retailers and will traverse aisles scanning and auditing merchandise to help stores maintain ideal product placement, fill inventory gaps, and find misplaced or mispriced items. Tally is also capable of autonomously returning to base to charge.
“When it comes to the retail industry, shopper experience is everything. If a product is unavailable at the time the shopper wants to buy it, the retailer has missed an opportunity and disappointed their customer,” according to Brad Bogolea, CEO and Co-founder of Simbe Robotics. “Tally helps retailers address these challenges by providing more precise and timely analysis of the state of in-store merchandise and freeing up staff to focus on customer service.” Cont'd...
Toyota Invests $1 Billion in AI and Robots, Will Open R&D Lab in Silicon Valley
By Erico Guizzo and Evan Ackerman for IEEE Spectrum: Today in Tokyo, Toyota announced that it is investing US $1 billion over the next five years to establish a new R&D arm headquartered in Silicon Valley and focused on artificial intelligence and robotics. The Toyota Research Institute (TRI) plans to hire hundreds of engineers to staff a main facility in Palo Alto, Calif., near Stanford University, and a second facility located near MIT in Cambridge, Mass.
Former DARPA program manager Dr. Gill Pratt, an executive technical advisor at Toyota, was named CEO of TRI, which will begin operations in January. Toyota president Akio Toyoda said in a press conference that the company pursues innovation and new technologies “to make life better for our customers and society as a whole,” adding that he wanted to “work with Gill not just because he’s an amazing researcher and engineer, but because I believe his goals and motivations are the same as ours.” Cont'd...
Skype founders invent self-driving robot that can deliver groceries for £1
By Sophie Curtis, video by Robert Midgley: You've heard of Amazon's plan to deliver packages using drones; now a new company called Starship is promising to disrupt local delivery with the launch of a self-driving robot that can deliver groceries to customers' doors in under 30 minutes for less than £1.
The Starship robot has been developed by Skype co-founders Ahti Heinla and Janus Friis. It drives on pavements at an average speed of 4mph, and uses proprietary mapping and navigation technology to avoid crashing into obstacles, (check out the video we made). Cont'd...
UCSD to create robots that see, think and do
By Gary Robbins for the San Diego Union Tribune: UC San Diego is creating a robotics institute that will develop machines that can interpret everything from subtle facial expressions to walking styles to size up what people are thinking, doing and feeling.
The “See-Think-Do” technology is largely meant to anticipate and fulfill people’s everyday needs, especially the soaring number of older Americans who want to live out their lives in their own homes.
Engineers envision robots that are so good at sizing up people, places and situations that they could help evacuate crowds from dangerous areas and pick through the rubble of an earthquake to look for survivors.
The newly created Contextual Robotics Institute will be formally announced on Friday when some of the nation’s top scientists meet at UC San Diego to discuss the future of robotics. The campus has already lined up support from such San Diego companies as Qualcomm, which needs new markets for its computer chips, and Northrop Grumman, which develops unmanned aerial vehicles.
“Our plan is to do the research and development that’s needed to realize robots of the future — robots that are safe, useful and autonomous in any environment,” said Albert Pisano, dean of UC San Diego’s Jacobs School of Engineering. Cont'd...
How Sensorimotor Intelligence May Develop
From Institute of Science and Technology Austria:
Robotic systems controlled by a neural network spontaneously develop self-organized behaviors. Researchers propose a novel learning rule in PNAS to explain the development of sensorimotor intelligence.
It is fascinating to observe a robot exploring its physical possibilities and surroundings, and subsequently developing different self-taught behaviors without any instructions. In their paper (DOI: 10.1073/pnas.1508400112) published on October, 26, 2015 in PNAS (Proceedings of the National Academy of Sciences), Professor Ralf Der from the Max Planck Institute for Mathematics in the Sciences, und Georg Martius, Postdoc and Fellow at the Institute for Science and Technology (IST Austria), demonstrate the emergence of sensorimotor intelligence in robots based on their proposed learning rule...
... To test their hypothesis, the authors use bioinspired robots consisting of a humanoid and a hexapod robot in physically realistic computer simulations. The robots receive sensory input from their bodies but are not given any form of instruction or task. What can then be observed is a rich spectrum of rhythmic behaviors of the robots as they explore various movements. Solely because of the tight coupling of environment, body, and brain (in this case an artificial neural network), the robots can obtain feedback from their situation and adapt quickly. This, together with a simple, learned self-model, allows them to develop a form of sensorimotor intelligence... ( full article ) ( paper ) ( videos and other materials )
Six-axis robotic arm called Eva, which weighs 2.3 kilograms and will cost $3,000
Suryansh Chandra claims the affordable robotic arm his company Automata is developing could lead to robots becoming as ubiquitous as desktop 3D printers.
"Today, every design studio has a 3D printer," Chandra says. "Soon, we hope to get to the point where every design studio has a robotic arm."
Chandra founded Automata together with Mostafa Elsayed five months ago, after they became frustrated by the expense and complexity of industrial robots while working at the research division at Zaha Hadid Architects.
"If you're out to get a robot today, you'd have to spend 50 or 60 thousand dollars," Chandra explains. "Our goal is to democratise robotics through a low cost hardware platform and easy to use software."
Automata's first product is a plastic six-axis robotic arm called Eva, which weighs 2.3 kilograms and will cost $3,000 (£2,000).
"Unlike industrial robots that are heavy and expensive, Eva is low cost and lightweight," Chandra says. "She can pick up 750 grams when fully outstretched and about a kilogram in a more recessed position." Cont'd...
Rob Scharff's Soft Robotics 3D-printed hand responds to human grip
Dutch Design Week 2015: Delft University of Technology graduate Rob Scharff has created a soft robotic limb that can shake hands with people.
The hand was created as part of Scharff's Soft Robotics research project – which focuses on the ways robots can be integrated with more tactile materials, and so improve robot-human interactions. Cont'd...
Leeds could become the first 'self-repairing city' with a fleet of robotic civil servants
By Chloe Olewitz for Digital Trends: Most people don’t know a whole lot about the city of Leeds other than its distinct regional accent, but believe it or not, local Leeds University is actually known for being a pioneering research leader in the field of robotics. The university’s School of Civil Engineering has put together a key research team that is currently developing a fleet of civil service robots and drones that would effectively turn Leeds into a self-repairing city.
The robotics research project is funded with £4.2M ($6.5M) of national funds, focusing on autonomous machines that would fix infrastructure issues across the city of Leeds, and perhaps, eventually, beyond. Leeds’ robot fleet will focus on robotic fixes for citywide issues like burst or damaged utility pipes, broken or nonfunctional street lights, and road fractures that disturb drivers on their way to anywhere.
Three main branches of the project cover the functions of the Leeds robots: Perch and Repair; Perceive and Patch; and Fire and Forget. The Perch and Repair segment covers research into robotic drones that can land, or “perch” like birds atop tall structures like street lamps or building-mounted civil structures. The Perceive and Patch team leads research into drones that can survey popular roads or even particularly dangerous ones in order to identify and repair potholes where they exist, and in the future, even prevent them before they occur. Cont'd...
Robot Can Pick and Sort Fruit
A robotics breakthrough by product design and development firm Cambridge Consultants is set to boost productivity across the food chain – from the field to the warehouse. It paves the way for robots to take on complex picking and sorting tasks involving irregular organic items – sorting fruit and vegetables, for example, or locating and removing specific weeds among crops in a field.
“Traditional robots struggle when it comes to adapting to deal with uncertainty,” said Chris Roberts, head of industrial robotics at Cambridge Consultants. “Our innovative blend of existing technologies and novel signal processing techniques has resulted in a radical new system design that is poised to disrupt the industry.”
Robots Learning Judo Techniques to Fall Down Without Exploding
By Evan Ackerman for IEEE Spectrum: The best and worst part of the DARPA Robotics Challenge Finals waswatching all of those huge expensive humanoids topple over in a series of epic faceplants. Faceplants are called faceplants because you’re planting your face into the ground as a means of breaking your fall, which usually also breaks your face, among other things. This tends to happen when you’re unprepared for falling, which with most robots, is 100 percent of the time. Now researchers at Georgia Tech want to teach humanoid robots to fall more safely with techniques adapted from judo, which might protect them enough to actually be able to get up again.
Falling safely (or, as safely as you can), assuming that you have very little control over the nature of your fall, is all about controlling exactly when and how your body crashes down. During a fall, your body is busy converting potential energy to kinetic energy, all of which has to go somewhere when you hit the ground. If your face hits the ground first, then that’s where all the energy goes at once, but if you can manage to contact the ground with a bunch of different parts of your body at different times on the way down, the energy will be spread out. Ideally, the energy gets spread out to the point where each individual impact doesn’t do enough damage to hurt you in a permanent sort of way. Cont'd...
Interactive Video Annotation Tool for Computer Vision Research
From University of California, Irvine:
VATIC is a free, online, interactive video annotation tool for computer vision research that crowdsources work to Amazon's Mechanical Turk. Our tool makes it easy to build massive, affordable video data sets and can be deployed on a cloud. After three years of research, vatic is now used by labs around the world to annotate the next generation of data sets.
Features
Crowdsource video annotation to Mechanical Turk
Automatic quality assurance for good annotations
Complex payment schedules and bonuses
One-click worker compensation
Optimized interface for video annotation
Offline mode for expert annotator use (no MTurk)
( site ) ( github )
Records 421 to 435 of 886
First | Previous | Next | Last
Featured Product
Zaber's X-LRQ-DE Series: High Precision Stages with Built-in Controllers and Linear Encoders
Zaber's X-LRQ-DE Series of linear stages have high stiffness, load, and lifetime capabilities in a compact size. The integrated linear encoder combined with stage calibration provides high accuracy positioning over the full travel of the device. At 36 mm high, these stages are excellent for applications where a low profile is required. The X-LRQ-DE's innovative design allows speeds up to 205 mm/s and loads up to 100 kg. Like all Zaber products, the X-LRQ-DE Series is designed for easy set-up and operation.
