“Parrot collaborates with Canonical to launch the Parrot S.L.A.M.dunk, a new development kit for the creation of autonomous and obstacle avoidance drones and robots. Powered by Ubuntu and ROS (Robot Operating System), it gives developers a familiar environment to prototype solutions such as autonomous driving, 3D mapping, or simply using the on board stereo camera and sensors for data gathering.”
“Daniel Schmoldt completed his academic training in 1987 from the University of Wisconsin-Madison with degrees in mathematics, computer science, and forest science. The latter included completion of both Masters and Ph.D. programs. From 1987 until 2001, he held several research scientist positions with the U.S. Forest Service while conducting research in a variety of forestry areas: wildfire management, atmospheric deposition, artificial intelligence, decision support systems, ecosystem management, machine vision systems, and automation in forest products utilization. From 1997-2004, he served as Joint Editor-in-Chief for the Elsevier journal, Computers and Electronics in Agriculture, and remains on their editorial board. Since 2001, he has filled a newly created position as National Program Leader for Instrumentation and Sensors with the National Institute of Food and Agriculture, and helps to prioritize, develop, focus, and coordinate USDA research, education, and extension programs covering the development of sensors, instrumentation, and automation technologies related to precision agriculture/forestry, robotics, processing of agricultural and forest products, detection of contaminants in agricul tural products, and monitoring and management of air, soil, and water quality. His current $100M+ portfolio of grant programs include specialty crops, agroclimatology, robotics, engineering, nanotechnology, and cyber-physical systems. Finally, he currently serves as the USDA representative to several Office of Science and Technology Policy working groups on engineering and technology.”
Boris Sofman and Hanns Tappeiner of Anki - “While the applications for robotics are plentiful in theory, matching technical capabilities to real world customer needs at high reliability and practical price points is incredibly difficult, leaving behind large numbers of ambitious, but ultimately failed, attempts to apply robotics to consumer applications. In this talk we will share a bit of our journey with Anki, a company we started working on in 2008 with the goal of identifying and entering markets where robotics and AI can have a real, measurable impact in a short time frame, and then using the technologies and learnings developed for one product as building blocks for the next. We enjoyed an eventful path from our early days as three Robotics Institute PhD students working out of a Pittsburgh living room to a 150 person company (with over a dozen CMU RI grads!) with offices in San Francisco, London, Munich and Shenzhen. We will share a few of the stories and learnings along the journey through multiple product releases, four rounds of venture funding, challenges at the overlap of many disciplines, large scale mass production, and seemingly endless strings of highs and lows. Finally, we are excited to share our next product, Cozmo, a robot character that uses a deep combination of robotics, AI, game design, and animated film-style animation with the aim of bringing a physical character to life with a level of personality, emotion and interaction that has never been possible outside of a screen. This interdisciplinary approach has led us to build a small animation studio within a robotics company with a novel approach to animating physical characters, showing intense levels of attachment and emotional response in all of our early testing. Along with a look at the many years of research and development leading to this product, we will discuss why the SDK that will be released with the launch in October could unlock one of the most capable and affordable robotic platforms for research and education.”
John Payne's insight:
This presentation includes an overview of the technology used in Cozmo, but mainly focuses on the realities of building and ramping up a startup business.
”Maybe there’s a way to organize your plantings such that a machine could pass through… But a top cut on your corn is going to be complicated because stalks don’t always have a regular height. Once you’ve top cut your corn, what do you do for the beans? Perhaps another pass through with a low cut, but your bean processing will now have to deal with corn stalks. Perhaps your third pass will be your squash harvester which could finally just roll through and catch everything that’s left.”
John Payne's insight:
The primary constraint here is that imposed by the use of large, heavy, expensive equipment, that must move across the ground relatively quickly (so it's cost can be spread over a large area) to be economically reasonable.
Listen to RobotsPodcast | SoundCloud is an audio platform that lets you listen to what you love and share the sounds you create.. 3 Tracks. 11 Followers. Stream Tracks and Playlists from RobotsPodcast on your desktop or mobile device.
“A team of researchers from the University of South Carolina, Zhejiang University in China, and Chinese security firm Qihoo 360 has found a potential fault in Tesla's AutoPilot semi-autonomous driving system. The team was able to exploit weaknesses in the system that lead researcher and USC Professor Wenyuan Xu said "highly motivated people" could use "to cause personal damage or property damage."”
Anyone who thinks racing is all about the drivers is in for a rude shock. Roborace will run alongside Formula E, but details about how the cars would actually work have been hard to come by. Now, we finally have a bit more info about what will make it tick.
“This guide is for anyone who is curious about machine learning but has no idea where to start. I imagine there are a lot of people who tried reading the wikipedia article, got frustrated and gave up wishing someone would just give them a high-level explanation. That’s what this is.”
“This video shows the latest results on the whole-body control of humanoid robots achieved by the Dynamic Interaction Control Lab at the Italian Institute of Technology. The control of the robot is achieved by regulating the interaction forces between the robot and its surrounding environment. The force and torque exchanged between the robot's feet and the floor is regulated so that the robot keeps its balance even when strongly perturbed.”
John Payne's insight:
Purists might complain that what's shown isn't recognizably Tai Chi, to which I'd add "yet". If iCub can do this, how much harder could it be to get it to do a nearly perfect long form?
Innovative food systems such as agroecology can become the norm if we weave a web of legitimacy from science, politics, society and values.
John Payne's insight:
While not a substitute to the paths to legitimacy described in this article, there are a couple of others I believe to be important: the leverage that can be provided by automation, and the influence of a powerful ally that stands to profit from making that automation available. I'm referring to the agricultural equipment industry, which, if it were to embrace the full potential of robotics to enable better agricultural practices, could both accelerate the adoption of those practices and profit handsomely from doing so.
“On display this week at the InterDrone show in Las Vegas, the PD6B-AW-ARM is described by Prodrone as ‘the world's first dual robot arm large-format drone.’ Built around the airframe of the company's existing PD6B-AW model, it features two remotely-operated 5-axis robotic arms that can grasp, carry and release a payload of up to 10 kg (22 lb). Algorithms in its onboard software allow it retain stability as its center of gravity shifts while lifting objects.”
Abstract: “Current learning-based robot grasping approaches exploit human-labeled datasets for training the models. However, there are two problems with such a methodology: (a) since each object can be grasped in multiple ways, manually labeling grasp locations is not a trivial task; (b) human labeling is biased by semantics. In this paper, we take the leap of increasing the available training data to 40 times more than prior work, leading to a dataset size of 50K data points collected over 700 hours of robot grasping attempts. This allows us to train a Convolutional Neural Network (CNN) for the task of predicting grasp locations without severe overfitting. In our formulation, we recast the regression problem to an 18- way binary classification over image patches. We also present a multi-stage learning approach where a CNN trained in one stage is used to collect hard negatives in subsequent stages. Our experiments clearly show the benefit of using large-scale datasets (and multi-stage training) for the task of grasping. We also compare to several baselines and show state-of-the-art performance on generalization to unseen objects for grasping.”
The images, discovered by Henner while researching satellite photographs of oil fields, look like post-apocalyptic wastelands.
John Payne's insight:
Pointing the finger at "factory farming" is slightly off the mark. The problem lies with farming methods, methods which are about as likely to be practiced on a family farm as on a corporate farm, and which have pre-historical origins. To date, technology has mostly served to accelerate the damage, but technology may also provide the means to halt and begin to reverse that damage.
Promising practices for corporates, investors, and entrepreneurs to drive long-term innovation and avoid an investment bust.
John Payne's insight:
This is an irreducibly complex look at a very complex tangle of realities, involving everybody from potential corporate investors with existing ag-related businesses to protect, to sustainability-motivated entrepreneurs, to typically conservative farmers, to consumers who have been voting with their dollars for food that more closely resembles its natural state.
There's still some way to go before US laws allow the kind of delivery service Amazon imagines, but a new initiative from the federal government is promising to speed things up and allow Google to test its delivery drones in the US.
Taking pre-orders at a discounted price through the month of July, they set out with a goal of $100,000 in sales, but have left that far behind, with $813,235 in pre-orders at the stroke of midnight. https://farmbot.io #farmbot
“In short, there’s a systems problem with the many incarnations of ‘sustainable food.’ Good intentions notwithstanding, most alternatives leave untouched the underlying structures and forces of the agri-food system. They don’t ask how farmers can listen to their land, scientists can listen to farmers, eaters can listen to restaurant workers and the government can listen to people’s needs. Sustainable food, it turns out, lacks a science with which to deal with a system as complex as farming and food. But there is an approach that embraces complexity and change. It involves developing the capacity to listen, to grow new connections, and to build solidarity among animals, plants and people. It’s called agroecology.”
John Payne's insight:
Perhaps the most important contribution robotics can make to enabling better land management and food production practices is in the realm of data collection, building a strong foundation upon which to build a true science of sustainable methods.
A new Ford and MIT research project is aimed at improving ride-hailing services by predicting the movement of pedestrians. LiDAR sensors and cameras will be used to identify pedestrians and their movements around a location, allowing vehicles to be dispatched to areas that are predicted hot-spots.
Lately the US Army has been exploring tethered versions that could help plug some holes in its military strategy, and has now placed an order with drone-maker CyPhy Works for a wired aerial vehicle that could provide an eye in the sky for days at a time.
Sharing your scoops to your social media accounts is a must to distribute your curated content. Not only will it drive traffic and leads through your content, but it will help show your expertise with your followers.
How to integrate my topics' content to my website?
Integrating your curated content to your website or blog will allow you to increase your website visitors’ engagement, boost SEO and acquire new visitors. By redirecting your social media traffic to your website, Scoop.it will also help you generate more qualified traffic and leads from your curation work.
Distributing your curated content through a newsletter is a great way to nurture and engage your email subscribers will developing your traffic and visibility.
Creating engaging newsletters with your curated content is really easy.