Partners:<a href="https://www.mitec.cat/en/" target="_blank">Mitec Enginy, S.L.</a><a href="https://bcnvision.es/en" target="_blank">Bcnvision</a>&nbsp;Problem:The customer <a href="https://www.isotubi.com/en/" target="_blank">Isotubi, S.L.</a>, which is a part of <a href="https://www.grupolapuente.com/en/" target="_blank">Grupo Lapuente</a>, has been working in the stainless steel world for more than 40 years.They decided to automate one of their processes that was performed manually before – the picking of 6 type of pipe parts from a container where they are randomly positioned and placing them into Isotubi’s wedging machine. The final, fully automatized solution needed to be fast and easily changed to meet the customer’s requirements and increase productivity.&nbsp;Solution:<a href="https://www.photoneo.com/phoxi-3d-scanner/" target="_blank">PhoXi 3D Scanner L</a>The pipe parts are picked and placed by a Staübli TX2-90L robot equipped with 3D vision from Photoneo in the form of a PhoXi 3D Scanner model L.The scanner scans and detects the parts in the container, determines which parts can be taken by the robot, and calculates the picking point and the trajectories for the robot.&nbsp;The robotic arm is equipped with a vacuum cup to pick the randomly positioned parts from the container one by one. Subsequently, the robot places the parts onto a repositioning table.&nbsp;Discussion:The customer tested a number of different vision systems but finally decided for the PhoXi 3D Scanner for several reasons. The scanner provides reliable and robust performance, the user interface program is very intuitive, user-friendly, and functional, and Photoneo offers high-quality local and email support.The automation of the pick &amp; place task resulted in labor and time savings, shorter cycle time, and greater productivity.Another significant advantage of the solution is the possibility to change between different types of parts by switching the ID solutions of the BPS. This provides great versatility and reduces the time required for changing the different pipe parts.

Automation cell by Mitec Enginy, S.L. featuring Photoneo PhoXi 3D Scanner

The customer decided to automate the process of picking 6 different types of pipe parts from a bin and placing them into a swedging machine. The solution consists of a Staübli TX2-90L robot equipped with a Photoneo PhoXi 3D Scanner.

Precise picking & placement of pipe parts

The artificial intelligence behind self-driving cars, medical image analysis and other computer vision applications relies on what’s called deep neural networks.Loosely modeled on the brain, these consist of layers of interconnected “neurons” -- mathematical functions that send and receive information -- that “fire” in response to features of the input data. The first layer processes a raw data input -- such as pixels in an image -- and passes that information to the next layer above, triggering some of those neurons, which then pass a signal to even higher layers until eventually it arrives at a determination of what is in the input image.But here’s the problem, says Duke computer science professor <a href="https://users.cs.duke.edu/~cynthia/" target="_blank">Cynthia Rudin</a>. “We can input, say, a medical image, and observe what comes out the other end (‘this is a picture of a malignant lesion’, but it’s hard to know what happened in between.”It’s what’s known as the “black box” problem. What happens in the mind of the machine -- the network’s hidden layers -- is often inscrutable, even to the people who built it.“The problem with deep learning models is they’re so complex that we don't actually know what they’re learning,” said <a href="https://users.cs.duke.edu/~zhichen/" target="_blank">Zhi Chen</a>, a Ph.D. student in Rudin’s lab at Duke. “They can often leverage information we don’t want them to. Their reasoning processes can be completely wrong.”Rudin, Chen and Duke undergraduate Yijie Bei have <a href="https://www.nature.com/articles/s42256-020-00265-z.epdf?sharing_token=rnt3d7MyMKCIsdmakZ6UD9RgN0jAjWel9jnR3ZoTv0Os8uNdVbb_6aStiZ6Kf4MXH4NUK5rvR11dIRoM_Db_5QmRJolVhHlG355smFFoBfLpSm3L7HYplm9ijBjS_lP_7uT89LyJdEUj0SOWi98AHQNFfkcYVQ8d0CMCVV9_TIQ%3D" target="_blank">come up with a way</a> to address this issue. By modifying the reasoning process behind the predictions, it is possible that researchers can better troubleshoot the networks or understand whether they are trustworthy.Most approaches attempt to uncover what led a computer vision system to the right answer after the fact, by pointing to the key features or pixels that identified an image: “The growth in this chest X-ray was classified as malignant because, to the model, these areas are critical in the classification of lung cancer.” Such approaches don’t reveal the network’s reasoning, just where it was looking.The Duke team tried a different tack. Instead of attempting to account for a network’s decision-making on a post hoc basis, <a href="https://www.nature.com/articles/s42256-020-00265-z.epdf?sharing_token=rnt3d7MyMKCIsdmakZ6UD9RgN0jAjWel9jnR3ZoTv0Os8uNdVbb_6aStiZ6Kf4MXH4NUK5rvR11dIRoM_Db_5QmRJolVhHlG355smFFoBfLpSm3L7HYplm9ijBjS_lP_7uT89LyJdEUj0SOWi98AHQNFfkcYVQ8d0CMCVV9_TIQ%3D" target="_blank">their method</a> trains the network to show its work by expressing its understanding about concepts along the way. Their method works by revealing how much the network calls to mind different concepts to help decipher what it sees. “It disentangles how different concepts are represented within the layers of the network,” Rudin said.Given an image of a library, for example, the approach makes it possible to determine whether and how much the different layers of the neural network rely on their mental representation of “books” to identify the scene.The researchers found that, with a small adjustment to a neural network, it is possible to identify objects and scenes in images just as accurately as the original network, and yet gain substantial interpretability in the network’s reasoning process. “The technique is very simple to apply,” Rudin said.<iframe src="https://www.youtube.com/embed/D_LBBQEsQYw?&amp;wmode=opaque" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 790px; height: 419px;"></iframe>The method controls the way information flows through the network. It involves replacing one standard part of a neural network with a new part. The new part constrains only a single neuron in the network to fire in response to a particular concept that humans understand. The concepts could be categories of everyday objects, such as “book” or “bike.” But they could also be general characteristics, such as such as “metal,” “wood,” “cold” or “warm.” By having only one neuron control the information about one concept at a time, it is much easier to understand how the network “thinks.”The researchers tried their approach on a neural network trained by millions of labeled images to recognize various kinds of indoor and outdoor scenes, from classrooms and food courts to playgrounds and patios. Then they turned it on images it hadn’t seen before. They also looked to see which concepts the network layers drew on the most as they processed the data.Chen pulls up a plot showing what happened when they fed a picture of an orange sunset into the network. Their trained neural network says that warm colors in the sunset image, like orange, tend to be associated with the concept “bed” in earlier layers of the network. In short, the network activates the “bed neuron” highly in early layers. As the image travels through successive layers, the network gradually relies on a more sophisticated mental representation of each concept, and the “airplane” concept becomes more activated than the notion of beds, perhaps because “airplanes” are more often associated with skies and clouds.It’s only a small part of what’s going on, to be sure. But from this trajectory the researchers are able to capture important aspects of the network’s train of thought.The researchers say their module can be wired into any neural network that recognizes images. In one experiment, they connected it to a neural network trained to detect skin cancer in photos.Before an AI can learn to spot melanoma, it must learn what makes melanomas look different from normal moles and other benign spots on your skin, by sifting through thousands of training images labeled and marked up by skin cancer experts.But the network appeared to be summoning up a concept of “irregular border” that it formed on its own, without help from the training labels. The people annotating the images for use in artificial intelligence applications hadn’t made note of that feature, but the machine did.“Our method revealed a shortcoming in the dataset,” Rudin said. Perhaps if they had included this information in the data, it would have made it clearer whether the model was reasoning correctly. “This example just illustrates why we shouldn’t put blind faith in “black box” models with no clue of what goes on inside them, especially for tricky medical diagnoses,” Rudin said.<hr>The team’s <a href="https://www.nature.com/articles/s42256-020-00265-z.epdf?sharing_token=rnt3d7MyMKCIsdmakZ6UD9RgN0jAjWel9jnR3ZoTv0Os8uNdVbb_6aStiZ6Kf4MXH4NUK5rvR11dIRoM_Db_5QmRJolVhHlG355smFFoBfLpSm3L7HYplm9ijBjS_lP_7uT89LyJdEUj0SOWi98AHQNFfkcYVQ8d0CMCVV9_TIQ%3D" target="_blank">work</a> appeared Dec. 7 in the journal Nature Machine Intelligence.CITATION: "<a href="https://www.nature.com/articles/s42256-020-00265-z.epdf?sharing_token=rnt3d7MyMKCIsdmakZ6UD9RgN0jAjWel9jnR3ZoTv0Os8uNdVbb_6aStiZ6Kf4MXH4NUK5rvR11dIRoM_Db_5QmRJolVhHlG355smFFoBfLpSm3L7HYplm9ijBjS_lP_7uT89LyJdEUj0SOWi98AHQNFfkcYVQ8d0CMCVV9_TIQ%3D" target="_blank">Concept Whitening for Interpretable Image Recognition</a>,"Zhi Chen, Yijie Bei and Cynthia Rudin. Nature Machine Intelligence, Dec. 7, 2020. DOI: 10.1038/s42256-020-00265-z

New research offers clues to what goes on inside the minds of machines as they learn to see. A method developed by Cynthia Rudin's lab reveals how much a neural network calls to mind different concepts as an image travels through the network’s layers.

Duke team disentangles neural networks to understand how they see the world

Accurate Neural Network Computer Vision Without The 'Black Box'

When a natural disaster occurs, on-the-ground emergency response teams act quickly to make life-saving decisions. Reducing the response time in such situations is critical to reduce damage impact and save lives. Helpful efforts are being taken to reduce the burden, such as a&nbsp;<a href="http://www.undp.org/content/buildingdamageassessment/en/home.html" target="_blank">damage assessment tool by UNDP</a>, though few automated methods exist. In recent work, MIT is creating tools that can automatically analyze images.At the upcoming&nbsp;<a href="https://eccv2020.eu/" target="_blank">European Conference on Computer Vision</a> (ECCV) conference, researchers from MIT and&nbsp;<a href="https://www.hbku.edu.qa/en/qcri/about" target="_blank">QCRI</a> are presenting a new computer vision model capable of detecting incidents in images posted on social media platforms, such as&nbsp;<a href="https://twitter.com/" target="_blank">Twitter</a> and&nbsp;<a href="https://www.flickr.com/" target="_blank">Flickr</a>. They are also releasing the Incidents Dataset, a collection of 446,684 images labeled with 43 different incidents, including earthquakes, floods, wildfires, and car accidents. The paper, code, and data is available at the&nbsp;<a href="http://incidentsdataset.csail.mit.edu/" target="_blank">project page</a> with interactive demos.&nbsp;"I’m excited for this dataset to enable further research in detecting incidents in images, and to ideally spur interest in the computer vision community in general," says Ethan Weber, an author on the paper and MEng student working with Professor&nbsp;<a href="https://groups.csail.mit.edu/vision/torralbalab/" target="_blank">Antonio Torralba</a>.The team’s new dataset aims to fill a void in the field, where existing datasets are limited in both the number of images and the diversity of incident categories. The authors go on to explain how the dataset was created, how a model can be created to detect incidents in images, and how to filter for incidents in noisy social media data.&nbsp;One experiment filters 40 million Flickr images to find incidents. Additional experiments filter images posted on Twitter during earthquakes, floods, and other natural disasters. For example, the team filtered natural disaster-related tweets into specific incidents in a process that was validated by correlating tweet frequency with databases provided by the&nbsp;<a href="https://www.noaa.gov/" target="_blank">National Oceanic and Atmospheric Administration</a> (NOAA).As interest in automated response grows, competitions have emerged to further increase efforts in this direction--though not necessarily restricted to using images. The&nbsp;<a href="https://www.nist.gov/" target="_blank">National Institute of Standards of Technology</a> (NIST) launched a&nbsp;<a href="https://www.herox.com/ASAPS1" target="_blank">competition</a> to promote fast analysis of unstructured data streams (social media, surveillance feeds, audio, text). Furthermore, last year the&nbsp;<a href="https://www.diu.mil/" target="_blank">Defense Innovation Unit</a> (DIU) hosted a&nbsp;<a href="https://www.challenge.gov/challenge/diu-xview2-assessing-building-damage/" target="_blank">challenge</a> to advance building damage assessment techniques in satellite imagery. Instead of having humans look at satellite images and label where damage occurred, computers can help with rapid analysis.Weber says that both social media and satellite imagery are valuable forms of data to help with emergency response. Social media provides on-the-ground insights, while satellite imagery provides expansive insights, such as determining which areas are most affected by a wildfire. Realizing this interconnectedness, Weber and MIT alum&nbsp;<a href="https://www.linkedin.com/in/mohamed-hassan-kane-4b50328a" target="_blank">Hassan Kane</a> teamed up and participated in the DIU challenge. Their team placed on the leaderboard for damage assessment, and they presented their award-winning&nbsp;<a href="https://arxiv.org/abs/2004.05525" target="_blank">work</a> in the&nbsp;<a href="https://ai4earthscience.github.io/iclr-2020-workshop/" target="_blank">AI for Earth Science</a> workshop at the ICLR 2020 conference.With computer vision showing promising signs in both on-the-ground and satellite imagery, the MIT and QCRI researchers are now working on next steps. Enabled by the new ECCV dataset, the researchers hope to go beyond detecting incidents in damage.&nbsp;"Now that we have the data, we're interested in localizing and quantifying damage,” says Weber. “We're working with emergency-response organizations to stay focussed and create research with real-world benefits."The Incidents Dataset presented in the ECCV paper is an effort by many contributors, including Weber, Nuria Marzo, Dim Papadopoulos, Aritro Biswas, Agata Lapedriza, Ferda Ofli, Muhammad Imran, and Antonio Torralba. More details on the study can be found on the project site.

When a natural disaster occurs, on-the-ground emergency response teams act quickly to make life-saving decisions. Reducing the response time in such situations is critical to reduce damage impact and save lives.

Detecting and responding to incidents with images

Discussions surrounding the latest robotic technology tend to focus primarily on the prospect of creating fully autonomous robots. Despite significant advancements in artificial intelligence and machine learning, autonomous robots are still not quite ready to handle the “edge cases” that the world presents—particularly in unstructured and unpredictable environments like the outdoors.Keeping humans in the loop is critical to any successful robotics implementation. Despite what science fiction movies portray, humans are still very much needed for decision-making, error handling and error recovery in unstructured environments. This is especially true among applications that rely heavily on human intellect or physical capabilities, such as those in the health care, aerospace, or energy industries.As the robots of today move beyond the factory floor and into the outside world, the spectrum of robotic technology has expanded. On one end of the spectrum, teleoperation has made it possible for operators to be in complete control while controlling robots from a safe distance. With teleoperation, a person is responsible for 100 percent of the decision-making and the direct actions of the robot through the use of a remote controller.On the other end of the spectrum, there are fully autonomous robots, which keep humans completely out of the loop. Fully autonomous robots are responsible for all decision-making and actions, as well as all error handling and recovery. They must adapt to varying environments and recover from errors entirely on their own. Even though popular culture wants us to believe that AI-driven robots are now primed to take over all of humanity, it will be a long time—perhaps several decades—before we see fully autonomous, outdoor mobile robotic systems, simply because robots cannot yet fully think, act or respond to adaptions on their own, especially in unstructured or changing environments.<img class="fr-fic fr-dib" src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1592916512228-TheAutonomySpectrum+%281%29.png" style="width: 464px;">In between these two extremes — and readily available for implementation today — is “supervised autonomy.” This type of autonomy has two distinct levels: in the first level, a person is making the decisions and the robot is responsible for the direct action. In the second level, the robot is responsible for the high-level decision-making and the direct actions, and operator remains in the loop solely for error handling and recovery.Supervised autonomy can allow robots to perform duties that are otherwise hazardous to humans, while still giving the robot operators to full control over specific tasks. This technology also can serve as a force multiplier when there are labor shortages. In addition, because this technology transfers physically demanding tasks to the robot, older workers can stay on the job longer while using their expertise to optimize control of the robots.Unlike full autonomy, supervised autonomy is ready now for environments that are both controlled (not open to the public) and populated only by trained personnel.For instance, industries such as aviation, construction, energy, and oil and gas, which all share common requirements for trained personnel, controlled environments, resilience to external factors, and the cognitive ability to learn and adapt, can especially benefit from supervised autonomy.Although this technology has the potential to <a href="https://www.resquared.com/industries" rel="noopener noreferrer" target="_blank">benefit many industries</a>, the energy industry could find it particularly useful. The maintenance of high-voltage power lines is, without a doubt, one of the most hazardous manual labor jobs across any industry. Using robots to conduct dangerous inspection or repair tasks could protect workers from serious or even fatal injuries from falls, burns and electrocutions. At first, robots could be teleoperated by experienced operators. Once the system has learned from the experiences and data collected during teleoperation tasks, it could transition to a supervised autonomous system. Since workers would only be involved in a supervisory capacity to assist with error handling and recovery, they would be kept completely out of harm’s way.Overall, the time is right for businesses to consider using supervised robotic autonomy to augment their staff and operations. Whether on the factory floor, in the operating room, or 40 feet in the air on a power line, supervised autonomy can help to keep workers out of harm’s way while improving productivity.<hr>Author Bio:&nbsp; <a href="https://www.resquared.com/jorgenpedersen" target="_blank">Jorgen Pedersen</a>, President and CEO, founded RE2 Robotics in July of 2001. Jorgen has contributed to the growth of the unmanned systems market for the past 20 years, beginning his career at Carnegie Mellon's National Robotics Engineering Center (NREC). Jorgen has held several leadership positions within the Robotics industry. He served as the Chairman of the Robotics Division of the National Defense Industrial Association (NDIA). Jorgen has also served in key roles such as a member of the Board of Trustees for NDIA and the Board of Directors for the National Advanced Mobility Consortium. Jorgen is the 2016 Carnegie Science Start-up Entrepreneur of the Year recipient. Jorgen was presented with the 2008 Army SBIR Achievement Award for the development of the Small Robot Toolkit for unmanned ground vehicles and the 2011 Tibbetts Award for SBIR Excellence. Jorgen holds a M.S. degree in Robotics and a B.S. degree in Electrical and Computer Engineering from Carnegie Mellon University. Connect with Jorgen on <a href="https://www.linkedin.com/in/jorgenre2/" target="_blank">LinkedIn</a> &amp; <a href="https://twitter.com/JorgenRE2" target="_blank">Twitter</a>.

 In this article, CEO Jorgen Pedersen discusses how supervised autonomy can allow robots to perform duties that are otherwise hazardous to humans, while still giving the robot operators full control over specific tasks. 

On the spectrum between teleoperation and full autonomy, and readily available for implementation today, is supervised autonomy

The Role of Supervised Autonomy in Mobile Manipulation

For the past two decades, <a href="https://www.resquared.com/" rel="noopener noreferrer" target="_blank">RE2 Robotics</a> has remained committed to its mission of creating innovative technologies that that make a positive impact on the world. Founded in 2001 by <a href="https://www.resquared.com/jorgenpedersen" rel="noopener noreferrer" target="_blank">Jorgen Pedersen</a>, RE2 Robotics thrives on researching, designing and developing mobile manipulation systems with human-like performance, intuitive robot interfaces, and advanced autonomy software that enable users to safely and efficiently interact with their environments—whether indoors, outdoors or underwater.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1591743732873-Copy+of+eBookMDMSBlog.jpg">RE2 Robotics' Maritime Dexterous Manipulation SystemFrom concept to creation, we conduct cutting-edge research and develop <a href="https://www.resquared.com/products" rel="noopener noreferrer" target="_blank">single and dual robotic manipulator arms</a> onsite in our collaborative facility, which is located in Pittsburgh’s historic Lawrenceville neighborhood. Our team has expertise in all disciplines of robotics—from machine learning and computer vision to electromechanical design. We remain dedicated to solving our customers’ most difficult robotics engineering problems while forming long-lasting relationships that meet their current and future technical challenges.&nbsp;By combining strength, dexterity, and efficiency all in a compact, rugged, lightweight package, our robotic arms provide human-like capabilities far beyond traditional industrial arms and cooperative robots. &nbsp;The goal of our technology is to improve worker safety and efficiency through the use of teleoperation, supervised autonomy, and intelligent mobile robotic systems. Today, we are pushing the boundaries of what is possible through robotics with the development of our autonomy software modules–<a href="https://www.resquared.com/products" rel="noopener noreferrer" target="_blank">RE2 Detect™ and RE2 Intellect™</a>, which integrate artificial intelligence, computer vision, and machine-learning capabilities within our robotic systems—allowing our proven technology to operate nearly anywhere on the planet.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1591743829000-FukuHDMS.png">RE2's Highly Dexterous Manipulation System (HDMS) with our Imitative ControllerTo learn more about our innovative robotic technologies, please visit our website: <a href="http://www.resquared.com" rel="noopener noreferrer" target="_blank">www.resquared.com.</a>Follow us on <a href="https://twitter.com/re2robotics" rel="noopener noreferrer" target="_blank">Twitter</a>, <a href="https://www.linkedin.com/company/re2" rel="noopener noreferrer" target="_blank">LinkedIn</a>, <a href="https://www.facebook.com/RE2Inc/" rel="noopener noreferrer" target="_blank">Facebook</a>, <a href="https://www.instagram.com/re2.robotics/" rel="noopener noreferrer" target="_blank">Instagram</a>, and <a href="https://www.youtube.com/channel/UCg-lVHa1UDSsFJIsvy-3pBQ" rel="noopener noreferrer" target="_blank">YouTube</a>!

RE2 Robotics' Highly Dexterous Manipulation System

RE2 Robotics develops robotic manipulation systems with human-like performance, intuitive robot interfaces and advanced autonomy software that can operate in both indoor and outdoor environments..

Get to Know RE2 Robotics

With advanced computer vision models and live public street cam video, a University of Michigan startup is tracking social distancing behaviors in real time at some of the most visited places in the world.<a href="https://pdi.voxel51.com/" target="_blank">Voxel51&rsquo;s new tool</a> shows&mdash;quite literally&mdash;an uptick in public gathering in Dublin on St. Patrick&rsquo;s Day, for example, and at New Jersey&rsquo;s Seaside Heights boardwalk during a recent weekend of unusually good weather.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1586440965050-VoxelCTA+%281%29.jpg">&quot;Innovation coming out of the startup world has been breathtaking. It feels like everyone in Silicon Valley and beyond is rising to the challenge, even if they don&rsquo;t have pockets as deep as Amazon and Google.&quot; &mdash;TechCrunch The tool uses the company&rsquo;s existing platform and underlying custom AI to continuously track vehicle, cyclist and pedestrian traffic at seven locations: Times Square; Abbey Road in London; Fremont Street in downtown Las Vegas; Seaside Heights in New Jersey; a beach in Ft. Lauderdale and intersections in Dublin and Prague. Several other locations are in beta, and more will be added soon.&nbsp;It assigns each place a &ldquo;physical distancing index,&rdquo; or PDI score, once every 15 minutes.Today, the researchers added information on case rates and death rates. They are in the process of adding additional curves to their graphs, such as weather.&ldquo;This pandemic is having an unprecedented impact on our daily lives and what we&rsquo;re trying to do is create a tool to improve public awareness,&rdquo; said&nbsp;<a href="https://web.eecs.umich.edu/~jjcorso/" target="_blank">Jason Corso</a>, professor of electrical and computer engineering at U-M and CEO of Voxel51, an Ann Arbor video analytics and data management company. &ldquo;The PDI score helps people understand and compare how the coronavirus is changing social behaviors over time and enables municipalities to visualize how they&rsquo;re doing from a public health perspective.&nbsp;&ldquo;Even though the virus is spreading, overall, we can see that the public response to the stay-at-home mandates has been rather dramatic and impressive.&rdquo;<iframe src="https://www.youtube.com/embed/SuS-ybvyTT4?&wmode=opaque" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 789px; height: 443px;"></iframe>While other projects are also tracking lockdown compliance, what&rsquo;s different about Voxel51&rsquo;s approach is that it&rsquo;s real-time, video-based and protects privacy. Data sources like mobile phones don&rsquo;t protect privacy and only offer approximate locations.On this new platform, viewers can click on a specific point in time on an individual city graph to see historic footage as well as additional details about policies such as school closures and stay-at-home orders.The graphs provide insights into the difficulty in limiting human activity in the face of good weather and special celebrations: Fort Lauderdale is one of the top destinations for students on spring break. &nbsp;As shown on the detailed graph for Florida, despite the governor issuing a public emergency Feb. 29, crowds were at all-time highs in early March, yet started to fall dramatically after the mayor closed bars and nightclubs March 17. And New York City&mdash;hit hardest by the pandemic&mdash;has a tough time keeping its 8 million tightly packed residents completely shuttered in.Voxel51 plans to add new locations regularly, as well as blog posts analyzing the data. The company is also accepting requests to add locations or specific installations of the system for local government and taxpayer usage. Views of different parks could help residents locate the least trafficked area to safely walk their dog, for example.The new curves, including those on case rates and death rates, could be illuminating as the pandemic continues.&ldquo;We expect to find rich information in the joint analysis of the physical distancing index and these other feeds,&rdquo; Corso said. &ldquo;There is even a chance that the PDI can feed into a predictive model for cities not yet greatly affected and the potential for a renewed outbreak next year.&rdquo;

Virtually visit (what should be) desolate intersections around the world during COVID-19.

Live public street cams are tracking social distancing

The frame in which a human marks out the boundaries of an object makes a huge difference in how well AI software can identify that object through the rest of the video.

Computer vision: Finding the best teaching frame in a video for fake video fightback

Henrik Christensen shares his views on the impact of the robot revolution and stories from his life in European and US robotics research.

The impact of the robot revolution with roboticist Henrik Christensen

Even though it has the right of way, the connected and automated Lincoln MKZ stops at an intersection because another vehicle is running the light. Vehicle-to-vehicle communication enabled this safety feature. Photo by Michigan Photography

Mcity demonstrates the powerful pairing of connectivity and automation.

How self-driving cars can be safer with connected technology

Robots aren&rsquo;t yet household fixtures, but Georgia Tech researchers have already come up with a way domestic bots might recognize materials around the home.Using near-infrared light, similar to what&rsquo;s used in TV remotes, the robot can identify common materials used in household objects to better inform its actions. This might allow intelligent machines to understand, for example, the right bowl (paper versus metal) to put in a microwave or how hard to grasp a cup made of glass versus plastic.To classify materials, the researchers first determined hundreds of light wavelengths reflected from five common materials &ndash; paper, wood, plastic, metal, and fabric. With this information, they trained a neural network on 10,000 examples in order to create a machine-learning (ML) model that could be used by a robot to quickly identify a material.According to the researchers, a robot using their new ML model can identify materials without it first having to touch an object, a useful function for handling potentially fragile items. To do so, the robot holds a small spectrometer near an object to get a quick light measurement, which is then processed to identify the material.<iframe src="https://www.youtube.com/embed/fBv_xEai2AU?&wmode=opaque" allowfullscreen="" class="fr-draggable" style="width: 767px; height: 425px;" frameborder="0"></iframe>Classification of Household Materials via Spectroscopy&ldquo;Robots currently use conventional cameras or haptic sensing - the sense of touch - to estimate a material type,&rdquo; said Zackory Erickson, the first author on the research paper detailing the new work and Georgia Tech robotics Ph.D. student.&ldquo;This is the first time that we know of that spectroscopy and machine learning have been used for material classification in robotics research, and our accuracy is on par with existing methods.&rdquo;The team&rsquo;s new ML model yielded the best results using spectrometer measurements from near-infrared light. In fact, the accuracy was 99.9 percent with the full dataset of 10,000 measurements from 50 objects that the model had been trained on.&ldquo;While human eyes typically use three color receptors to see the world, our robot can be thought of as using hundreds of color receptors to recognize materials,&rdquo; said Charlie Kemp, associate professor in the Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech and Emory University and part of the research team. &ldquo;Instead of a conventional color camera that measures red, green, and blue light, our robot uses a spectrometer that measures light at hundreds of different wavelengths, some outside of the range of human vision.&rdquo;To see how results would compare using only a single light reading from each object, the team also trained the model on just 50 measurements, one from each object. Interestingly, accuracy in identifying the correct material only dropped to 95 percent. When using a spectrometer reading from objects the machine learning model had never seen, the robot still achieved an 81.6 percent success rate.&ldquo;Spectroscopy presents a reliable and effective way for robots to estimate materials of household objects,&rdquo; Erickson said. &ldquo;We&rsquo;ve demonstrated how a robot can use near-infrared spectroscopy to infer the materials of everyday objects like cups, bowls, and garments.&rdquo;Reference:The research is published in the Proceedings of the 2019 International Conference on Robotics and Automation (ICRA) in the paper titled Classification of Household Materials via Spectroscopy co-authored by <a href="http://zackory.com/" target="_blank">Zackory Erickson</a>, Nathan Luskey, <a href="https://www.cc.gatech.edu/~chernova/" target="_blank">Sonia Chernova</a>, and <a href="http://charliekemp.com" target="_blank">Charlie Kemp</a>.

 Robot Classifies Materials of Household Objects Using 'Light-Reading' Device 

computer vision

Latest Posts