Found in Robotics News & Content, with a score of 0.16
…and more. All our code is open-source under an MIT license. For more information, see the PDF download “BenchBot: Evaluating Robotics Research in Photorealistic 3D Simulation and on Real Robots.” A lot of moving parts isn’t necessarily a good thing if they complicate the user experience, so designing the user experience was also a central focus in developing BenchBot. There are three basic commands for controlling the system: benchbot_install - -help benchbot_run - -help benchbot_submit - -help The following command helps builds powerful evaluation workflows across multiple environments: benchbot_batch - -help Here’s a simple Python command for interacting with the…
Found in Robotics News & Content, with a score of 0.90
…the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. “The Robotics Medal means more than its generous cash prize and resources at MassRobotics,” Rus added. “It reflects the powerful contributions women have made, are making, and will make to this important, vibrant and growing industry.” Winner will have access to MassRobotics' network The Robotics Medal recipient will be named a MassRobotics Fellow and gain access to manufacturing and robotics expertise through the MassRobotics network, along with access to robotics labs and office space at MassRobotics in Boston. At the facility, the winner will have access to prototyping facilities including…
Found in Robotics News & Content, with a score of 0.60
…the Harvard Biorobotics Lab, the Yale GRAB Lab, and MIT founded RightHand Robotics in 2015 to apply computer vision and machine learning to real-world grasping problems. The company said its data-driven, intelligent picking platform provides flexible and scalable automation for predictable order fulfillment. RightHand said RightPick 3, its latest robotic piece-picking system, “enables retailers to rise up to the new realities of online commerce.” RightPick 3 has a modular, industrialized hardware design and well-defined software application programming interfaces (APIs), said the company. It is designed to be integrator-friendly and complies with international standards, RightHand said. The company claimed that RightPick…
Found in Robotics News & Content, with a score of 0.57
…from that.” Founders bring industry experience Saad is an MIT alumnus and co-founder of MassRobotics, an organization that supports more than 60 resident startups at its shared workspace in Boston. He previously led MassRobotics' partnership program, building relationships with more than 40 corporations. Saad has worked with entrepreneurs, researchers, and technologists from around the world. He also brings business management and development experience from multinationals Siemens and Nokia. Saad told Robotics 24/7 that he will be leaving MassRobotics after a transition period. “We are excited that Fady will remain involved in the robotics ecosystem and that his new efforts will…
Found in Robotics News & Content, with a score of 0.27
…have been bought by several hospitals, as well as MIT. MatrixSpace designs a smarter drone Matthew King, vice president of autonomous systems at MatrixSpace Inc., said his company is developing an “AI software defined sensing and autonomous response platform” for drones. King said it starts with the company’s millimeter-wave radar and mesh network device, which he claimed no other autonomous drone making company has developed. “This has an AI sensor-fusion and perception layer that feeds into the mission autonomy engine onboard the drone that enables it to execute any mission that’s programmed into it,” King said. “Whether that is scanning…
Found in Robotics News & Content, with a score of 2.71
…be administered to minimize any damage to the brain. MIT says teleoperated robot could democratize care The MIT team said it envisions that its robotic system could be installed at smaller hospitals and remotely guided by trained surgeons at larger medical centers. The system includes a medical-grade robotic arm with a magnet attached to its wrist. With a joystick and live imaging, an operator can adjust the magnet's orientation and manipulate the arm to guide a soft and thin magnetic wire through arteries and vessels. The researchers demonstrated the system in a “phantom,” a transparent model with vessels replicating complex…
Found in Robotics News & Content, with a score of 0.30
…on display was what Jim Rice, a professor at MIT, calls “sustaining innovation.” This type of innovation represents “the combining and application of a mix of inventions, existing processes, and technologies in a new way to create improvements in cost, quality, cash, and/or service.” A great example of this recommended to me by several fellow MODEX attendees was the new goods-to-person system from OPEX, which decouples robots from its high-density storage medium. Goods-to-person isn’t new for the industry or OPEX, but the new product is a sustaining innovation based on what the company has already done. Industry consolidation continues One…
Found in Robotics News & Content, with a score of 0.57
…the Harvard Biorobotics Lab, the Yale GRAB Lab, and MIT founded RightHand Robotics in 2015. Their stated goal was to apply grasping intelligence powered by computer vision and applied machine learning to real-world problems. The Somerville, Mass.-based company said its data-driven picking platform provides flexible and scalable automation for predictable order fulfillment. It raised $66 million in Series E funding last month. RightHand said it will be at the following events: MODEX 2022: The RightHand Robotics team is at Booth B8622, and the Vanderlande team is at at Booth B5406 from March 28 to 31 in Atlanta. LogiMAT 2022: RightHand…
Found in Robotics News & Content, with a score of 1.16
…Shah, an associate professor of aeronautics and astronautics at MIT; Ira Moskowitz, CEO of the Advanced Robotics for Manufacturing (ARM) Institute; and Elisabeth Reynolds, special assistant to the president for manufacturing and economic development at the National Economic Council. U.S. Secretary of Labor Marty Walsh Walsh recalled being approached about MassRobotics wanting to build a facility at 12 Channel St. in Boston back in 2015. He said he thought it was the perfect opportunity to show Boston’s commitment to technology and innovation. In the years since, the robotics space has only become more important. “It’s really clear to me and…
Found in Robotics News & Content, with a score of 3.75
Researchers at MIT's Improbable AI Lab and the Institute of AI and Fundamental Interactions have been working on ways to improve a robotic mini-cheetah's strides. Their model-free reinforcement learning system helped the legged robot break the record for the fastest run recorded. The mini-cheetah has an indoor sprint of 3.9 meters per second (8.7 miles per hour), an outdoor 10-meter dash of 3.4 m/s (7.6 mph), and an indoor spin of 5.7 radians per second, according to the project's website. MIT News spoke to Gabriel Margolis, a Ph.D. student at MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), and Ge…
Found in Robotics News & Content, with a score of 0.52
…from Harvard Biorobotics Lab, the Yale GRAB Lab, and MIT founded RightHand Robotics in 2015. The Somerville, Mass.-based company applies computer vision and machine learning for its RightPick piece-picking system. RightHand raised $66 million in Series C funding last month. Partnership program intended to ease robotics adoption RightHand Robotics said its Partner Integrator program will make it easier for end customers to adopt robotic picking by working with their preferred automation suppliers. “The Partner Integrator program aligns business goals of system integrators, OEM technology providers, certified robot integrator partners, and other related sales alliance members,” said Paul Eyre, director of…
Found in Robotics News & Content, with a score of 0.54
…now the Low-Power Computer Vision Challenge), outperforming teams from MIT, Qualcomm, Amazon, and others. ENOT has raised unspecified seed funding from New Nordic Venture. ENOT intends to cut computing costs ENOT.ai said its framework takes a trained neural network as input, after which it selects the sub-network with the lowest latency to ensure no accuracy degradation. The company said its neural architecture selection technology can achieve optimization ratios resulting in acceleration up to 20x and compression up to 25x. This can outperform other methods and reduce total hardware computing resource costs by as much as 70%, it claimed. ENOT explained…