An Open Source Driving Agent from comma.ai
From comma.ai: Last week, we open sourced an advanced driver assistance system in order to help accelerate the future of self driving cars and provide a platform anyone can build on top of. We released both openpilot, driving agent research software, and NEO, a robotics platform capable of running openpilot, under the MIT license.
openpilot is an open source adaptive cruise control and lane keeping assist system, both safety features available on modern cars. We would like to build the best ones on the market, and help you retrofit them to existing cars.
NEO is an open source robotics research platform. It is centered around an Android phone, similar to Android Based Robots. The modern smartphone is an incredible platform packed with sensors and processing power. NEO also includes a cooling solution and a CAN interface board. CAN is a networking protocol used in cars, trucks, power wheelchairs, golf carts, and many other robotics applications.
With a forthcoming openpilot release, it will become easier for researchers to add support for their own vehicle. On older cars, some actuators may be harder to control than others, but it should be very possible to control the gas electronically to have a gas only adaptive cruise control. It's also possible for researchers to add mechanical actuators for the controls that cannot be electronically actuated.
Have fun, be safe, and let's usher in the future of self driving cars together... (Github repo) (Interview)
Future Drones Will Fly as Silent as Owls, as Steady as Bees
Glenn McDonald for Seeker: Want to know what drones of the future will look like?
So does David Lentink, editor of Interface Focus, a journal that, as its title suggests, looks at the interface of different scientific disciplines. Each issue zeroes in on a particular intersection of physical sciences and life sciences and invites the world's top scholars to publish their latest work.
The latest issue of Interface Focus brings together biologists and engineers to discuss a topic that's relatively straightforward and, well, pretty empirically cool:
"It's completely focused on how animals fly and how that can help us build flying robots," said Lentink, assistant professor of mechanical engineering at Stanford. Can't argue with that.
The new issue features 18 newly published papers on various ways that engineers are borrowing ideas from nature to make the next generation of drones and aerial robots. Several of the papers detail prototype drones that have already been built and tested. Cont'd...
DIY Position Tracking Using HTC Vive's Lighthouse
From Alexander Shtuchkin:
Code & schematics for position tracking sensor using HTC Vive's Lighthouse system and a Teensy board.
General purpose indoor positioning sensor, good for robots, drones, etc.
3d position accuracy: currently ~10mm; less than 2mm possible with additional work.
Update frequency: 30 Hz
Output formats: Text; Mavlink ATT_POS_MOCAP via serial; Ublox GPS emulation (in works)
HTC Vive Station visibility requirements: full top hemisphere from sensor. Both stations need to be visible.
Positioning volume: same as HTC Vive, approx up to 4x4x3 meters.
Cost: ~$10 + Teensy 3.2 ($20) (+ Lighthouse stations (2x $135))
Skills to build: Low complexity soldering; Embedded C++ recommended for integration to your project.
(Github page)
Engineers Devise New Method to Heighten Senses of Soft Robot
Written by AZoRobotics: Most robots achieve grasping and tactile sensing through motorized means, which can be excessively bulky and rigid. A Cornell group has devised a way for a soft robot to feel its surroundings internally, in much the same way humans do.
A group led by Robert Shepherd, assistant professor of mechanical and aerospace engineering and principal investigator of Organic Robotics Lab, has published a paper describing how stretchable optical waveguides act as curvature, elongation and force sensors in a soft robotic hand.
Doctoral student Huichan Zhao is lead author of “Optoelectronically Innervated Soft Prosthetic Hand via Stretchable Optical Waveguides,” which is featured in the debut edition of Science Robotics. The paper published Dec. 6; also contributing were doctoral students Kevin O’Brien and Shuo Li, both of Shepherd’s lab. Cont'd.. .
MIT's Modular Robotic Chain Is Whatever You Want It to Be
Evan Ackerman for IEEE Spectrum: As sensors, computers, actuators, and batteries decrease in size and increase in efficiency, it becomes possible to make robots much smaller without sacrificing a whole lot of capability. There’s a lower limit on usefulness, however, if you’re making a robot that needs to interact with humans or human-scale objects. You can continue to leverage shrinking components if you make robots that are modular: in other words, big robots that are made up of lots of little robots.
In some ways, it’s more complicated to do this, because if one robot is complicated, robots tend to be complicated. If you can get all of the communication and coordination figured out, though, a modular system offers tons of advantages: robots that come in any size you want, any configuration you want, and that are exceptionally easy to repair and reconfigure on the fly.
MIT’s ChainFORM is an interesting take on this idea: it’s an evolution of last year’s LineFORM multifunctional snake robot that introduces modularity to the system, letting you tear of a strip of exactly how much robot you need, and then reconfigure it to do all kinds of things. Cont'd...
Boeing buys Liquid Robotics to boost autonomous surveillance at sea
Alan Boyle for Geekwire: The Boeing Co. says it has agreed to acquire Liquid Robotics, its teammate in a years-long effort to create surfboard-sized robots that can use wave power to roam the seas.
The acquisition is expected to help Boeing create military communication networks that can transmit information autonomously from the sea to satellites via Sensor Hosting Autonomous Remote Craft, or SHARCs.
Liquid Robotics was founded in 2007 and currently has about 100 employees in California and Hawaii. Once the deal is completed, the company will become a subsidiary of Boeing. The arrangement is similar to the one that applies to Insitu, a Boeing subsidiary that is headquartered in Bingen, Wash., and manufactures ScanEagle military-grade drones. Cont'd...
Stanford study concludes next generation of robots won't try to kill us
Bruce Brown for DigitalTrends: It sounds like we can all take a breath and forget about robot attacks occurring — at least anytime soon. Robots turning against their makers is a common theme in science fiction. However, there’s “no cause for concern that AI poses an imminent threat to humanity,” according to Fast Company, citing the first report from the One Hundred Year Study on Artificial Intelligence (AI100).
The Stanford University-hosted project represents a standing committee of AI scientists. The AI100 project is ongoing but will not issue reports annually — the next one will be published “in a few years.” The first report, Artificial Intelligence and Life in 2030, downloadable at this link, looks at how advances in AI will make a difference in the U.S. between now and 2030. Areas of change explored by the report include transportation, healthcare, education, the workplace, and policing and public safety. Cont'd...
Robotics entrepreneur unveils spider creation set to take gaming world by storm
David Clensy for Bristol Post: For Silas Adekunle, the fascination has always been about how the very best robotics learns from biology.
There is a twinkle in the eye of the 25-year-old Reach Robotics founder, as he introduces me to Mekamon – the spider-like robot with which he plans to transform the future of augmented reality gaming among techies around the world.
Silas only graduated from the University of the West of England in 2014, but is already employing 10 people in his rapidly growing tech company. Cont'd...
Innovative Machine Learning Training Method Opens New Possibilities for Artificial Intelligence
From AZoRobotics: As a result of a new machine learning algorithm formulated by engineering researchers Parham Aarabi (ECE) and Wenzhi Guo (ECE MASc 1T5) at University of Toronto, smartphones may soon be able to provide users with honest answers.
The researchers prepared an algorithm that was capable of learning directly from human instructions, instead of an existing set of examples, and surpassed conventional techniques of training neural networks by 160%.
But more astonishingly, their algorithm also surpassed its own training by 9% - it learned to identify hair in pictures with better reliability than that enabled by the training, signifying a major leap forward for artificial intelligence. Cont'd...
Irishman's soft robotics exosuit wins major tech award
Colm Gorey for SiliconRepublic: Irishman Conor Walsh’s soft robotics exosuit was among the award winners at the recent Rolex Awards, due to the creator’s continuing efforts to develop tech for the benefit of humanity.
Now in its 40th year, the Rolex Awards are part of an international philanthropic programme that supports new and ongoing projects by individuals taking on major challenges to benefit humankind.
Hosted last night at a public awards ceremony in Los Angeles, the awards were presented to 10 laureates – including five young laureates – that included such wide-ranging topics as opthamology and agritech. Cont'd...
Care-O-bot 4 celebrates its premiere as a shopping assistant
By Fraunhofer IPA via RoboHub: In January 2015, Fraunhofer IPA presented a prototype of the “Care-O-bot 4” service robot. The charming helper is now proving its worth in the real world. “Paul” the robot has been greeting customers in Saturn-Markt Ingolstadt since the end of October 2016 and directing them towards their desired products.
Care-O-bot 4, alias Paul, approaches Saturn customers and welcomes them to the store. If they ask him about a certain product, he accompanies the customer to the department and points them in the direction of the relevant shelf. As he indulges in small talk about the weather, or another subject, Paul turns out to be a most charming contact partner. However, he prefers to leave actual customer service to his human colleagues. Paul is able to call another member of staff for support via “Voice over IP”. Before Paul bids a fond farewell and returns to the store entrance, he still has time to ask for feedback. In this way, he discovers whether customers appreciated the interaction or not. Martin Wild, Chief Digital Officer at Media-Saturn-Holding: “With Paul, we are offering our customers the opportunity to get to know one of the most advanced robots in the world.” Cont'd...
Relay Is a Robot Butler Coming to a Hotel Near You
Nathaniel Mott for Inverse: Ordering room service can be a lesson in embarrassment. It could arrive right after you’ve taken off your clothes, while you’re indisposed, or while you’re in the middle of other hotel-related behavior. Thankfully, a robot butler named Relay is here to take that embarrassment (and other inconveniences) out of hotel deliveries.
Relay is basically an autonomous locker on wheels. Guests ask for an item, a hotel worker puts the object inside Relay’s compartment, and then the robot scoots over to the guest’s room with its cargo. It then calls the guests to let them know their item is ready before heading back down to the lobby so it can recharge before its next assignment. Cont'd...
Self-drive delivery van can be 'built in four hours'
Jane Wakefield for BBC News: A self-drive electric delivery van, that could be on UK streets next year, has been unveiled at the Wired 2016 conference in London.
The vehicle's stripped-back design and lightweight materials mean it can be assembled by one person in four hours, the firm behind it claims.
The vehicles will be "autonomous-ready", for when self-drive legislation is in place, the firm said.
The government wants to see self-drive cars on the roads by 2020.
"We find trucks today totally unacceptable. Loud, polluting and unfriendly," said Denis Sverdlov, chief executive of Charge, the automotive technology firm behind the truck.
"We are making trucks the way they should be - affordable, elegant, quiet, clean and safe." Cont'd...
New US Robotics Roadmap calls for increased regulations, education and research
From Phys.org: A new U.S. Robotics Roadmap released Oct. 31 calls for better policy frameworks to safely integrate new technologies, such as self-driving cars and commercial drones, into everyday life. The document also advocates for increased research efforts in the field of human-robot interaction to develop intelligent machines that will empower people to stay in their homes as they age. It calls for increased education efforts in the STEM fields from elementary school to adult learners
The roadmap's authors, more than 150 researchers from around the nation, also call for research to create more flexible robotics systems to accommodate the need for increased customization in manufacturing, for everything from cars to consumer electronics
The goal of the U.S. Robotics Roadmap is to determine how researchers can make a difference and solve societal problems in the United States. The document provides an overview of robotics in a wide range of areas, from manufacturing to consumer services, healthcare, autonomous vehicles and defense. The roadmap's authors make recommendation to ensure that the United States will continue to lead in the field of robotics, both in terms of research innovation, technology and policies. Cont'd...
As seen on TV! Neural Enhance
From Alex J. Champandard: As seen on TV! What if you could increase the resolution of your photos using technology from CSI laboratories? Thanks to deep learning and #NeuralEnhance, it's now possible to train a neural network to zoom in to your images at 2x or even 4x. You'll get even better results by increasing the number of neurons or training with a dataset similar to your low resolution image.
The catch? The neural network is hallucinating details based on its training from example images. It's not reconstructing your photo exactly as it would have been if it was HD. That's only possible in Hollywood — but using deep learning as "Creative AI" works and it is just as cool! (github)
Records 451 to 465 of 586
First | Previous | Next | Last
Featured Product
ATI Industrial Automation - MC-50 Manual Tool Changer
With intuitive and ergonomic lever operation, the patent-pending MC-50 Manual Robot Tool Changer provides a simple solution for quickly changing robotic end-of-arm tooling by hand. This compact and robust Tool Changer is designed for applications on collaborative robots that support payloads up to 25 kg and small industrial robots supporting payloads up to 10 kg. Featuring an ISO 50 mm mounting interface on the Master-side and Tool-side, the low-profile MC-50 mounts directly to most cobots and seamlessly integrates with many common cobot marketplace grippers and end-effectors.
