Found in Robotics News & Content, with a score of 0.43
…heterogeneous computing with an eight-core CPU up to 2.84GHz, GPU up to 587MHz, and Flight DSP up to 800MHz. Will 5G help drone operations beyond the visual line of sight (BVLOS) or in GPS-denied environments? Sweet: Yes – many enterprise robots are using 4G as a robust telemetry backhaul for tracking. 5G significantly increases network capacity to enable video, edge AI processing, and real-time command and control. 5G connectivity provides ultra-high reliability and low latency connectivity during flight, allowing drones to operate BVLOS. 5G’s low latency is especially useful in navigation scenarios where drones fly in GPS-denied environments. In this…
Found in Robotics News & Content, with a score of 0.43
…on the NVIDIA Jetson Orin NX while undersea. “NVIDIA GPUs are involved in a large portion of our pipeline because, basically, when the images come in, we use DeepSeeColor to color correct them, and then we can do the fish detection and transmit that to a scientist up at the surface on a boat,” said Stewart Jamieson, a robotics Ph.D. candidate at MIT and an AI developer at WARPLab. CUREE cameras detect fish and reefs CUREE includes four forward-facing cameras, four hydrophones for underwater audio capture, depth sensors and inertial measurement unit sensors. GPS doesn’t work underwater, so it is…
Found in Robotics News & Content, with a score of 0.41
…new additive manufacturing build manager takes advantage of the GPU-accelerated processing and Python scriptability inherent to Dyndrite’s engine. According to the company, this combination enables customers to simplify and automate build preparation across their additive manufacturing technologies at supercharged speeds. HP is committed to supporting multi-platform additive workflows across machine fleets, including HP Multi Jet Fusion, Binder Jetting (BJT), Laser Powder Bed Fusion (LPBF), Selective Laser Melting (SLM), Direct Metal Laser Sintering (DMLS), Selective Heat Sintering (SHS), Electron Beam Melting (EBM), Selective Laser Sintering (SLS), Fused Deposition Modeling (FDM), High Speed Extrusion (HSE), Stereolithography (SLA), Digital Light Projector (DLP), Laminated…
Found in Robotics News & Content, with a score of 0.41
…multiple AI application pipelines with the NVIDIA Ampere architecture GPU (graphics processing unit), next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth, explained NVIDIA. Developers will be able to develop systems for their largest and most complex AI models in natural language understanding, 3D perception, and multi-sensor fusion, it claimed. To demonstrate the performance improvement, NVIDIA ran some computer vision benchmarks using the NVIDIA JetPack 5.1. Testing included some dense INT8 and FP16 pretrained models from NGC. The same models were also run for comparison on Jetson Xavier NX. The company ran the following benchmarks: NVIDIA PeopleNet…
Found in Robotics News & Content, with a score of 0.39
…power efficiency lower than a typical computing platform running GPUs by implementing NVIDIA Jetson is important for enabling us to do these kinds of missions,” said Towal. Oceanic surveying meets edge AI Saildrone relies on the NVIDIA JetPack SDK for access to a full development environment for hardware-accelerated edge AI on the Jetson platform. It runs machine learning on the module for image-based vessel detection to aid navigation, said NVIDIA. Saildrone pilots set waypoints and optimize the routes using “metocean” data—which includes meteorological and oceanographic information—returned from the vehicle. All of the USVs are monitored around the clock, and operators…
Found in Robotics News & Content, with a score of 0.38
…The vision systems use NVIDIA’s Jetson NX Carrier Board GPUs. Rajat Aggarwal, CEO of DreamVu, said NVIDIA’s chips have helped the company take advantage of more sophisticated software to better take advantage of artificial intelligence. Robots that can only take advantage of CPUs from Intel are more limited power-wise, Aggarwal said. Those limitations can pose problems since a good vision system needs a robust amount of data to work well. Photoneo combines two technologies to make new light technology Another important part of a vision system is its ability to take in light to analyze environments. Photoneo says its patented…
Found in Robotics News & Content, with a score of 0.36
…“NVIDIA was helpful when setting up our product, since GPUs [graphics processing units] are integral to any AI application,” said Vuine. “We have close relationships with the robot guys,” he noted. “Our incentives are perfectly aligned—we allow them to enlarge the total addressible market. Variance for end effectors is usually a barrier to adoption. They also bring interesting use cases for MIRAI, such as plugging in cables or gear picking.” “We also have a distribution network in Germany and the U.S.,” Vuine added. “In terms of robot platforms, there are some obvious manufacturers to work with next. Our customers like…
Found in Robotics News & Content, with a score of 0.36
…now have access to more computing power (e.g., Nvidia GPUs, Omniverse, etc.), data, cloud-computing platforms (e.g., Amazon AWS), new hardware and advanced engineering. Many robotics startup companies are capitalizing on this “super evolution” of technology to build more intelligent and more capable machines. In parallel, there’s another phenomenon happening in the world: a “convergence of technologies.” It means that engineers are coming up with different silver bullets — engineering different algorithms, different hardware architectures, different methods, etc. — to solve the same fundamental problems. The Perl programming language motto, “there’s more than one way to do it,” perfectly captures what…
Found in Robotics News & Content, with a score of 0.35
…[trillions of operations per second] performance, with eight CPUs, GPU, and cameras all integrated,” said Singh. “The vision processors support seven cameras concurrently, giving 360-degree awareness. This enables smaller, lighter, and safer drones.” “The main camera has 8K resolution, which can be used to detect and classify defects in real time for inspections,” he said. In addition, the Qualcomm RB5 5G is intended to support increased autonomy, including visual-intertial odometry (VIO) and navigation in GPS-denied environments. “Situational awareness and obstacle avoidance enable BVLOS [beyond visual line-of-sight] and follow-me applications,” said Singh. “I'm really excited about unmanned aerial mobility—you could call…
Found in Robotics News & Content, with a score of 0.35
…of autonomous systems at Deere. “Machine learning running on GPUs [graphics processing units] intepret the inputs.” The self-driving tractor also continuously checks its position relative to a geofence, ensuring it is operating where it is supposed to, and it is accurate to less than an inch (2.5 cm), said Kovar. Redundant safety systems include RGB and depth, and the neural network classifies each pixel on NVIDIA processors, said Pell. “If the system encounters an object it doesn't recognize, the machine stops,” he explained. “Unlike an autonomous vehicle on the road, we don't need to worry about getting rear-ended when it…
Found in Robotics News & Content, with a score of 0.33
…modern and secure accelerated data centers in which CPUs, GPUs and DPUs are able to combine into a single computing unit that’s fully programmable, AI-enabled and can deliver levels of security and compute power not previously possible.” Optimized to offload critical networking, storage and security tasks from CPUs, BlueField-2 DPUs enable organizations to “transform their IT infrastructure into state-of-the-art data centers that are accelerated, fully programmable and armed with “zero-trust” security features to prevent data breaches and cyberattacks,“ according to NVIDIA. According to the company, a single BlueField-2 DPU can deliver the same data center services that could consume up…
Found in Robotics News & Content, with a score of 0.33
…collaborate on a single scene, simultaneously,” said J. J. Franzen, CIO at South Park. “Using our NVIDIA RTX A6000 GPUs and Omniverse will provide our creative geniuses more opportunities to cause ever greater trouble on the show.” Availability and pricing NVIDIA Omniverse Enterprise is currently in limited early access. The platform will be available later this year on a subscription basis from the company's partner network — including ASUS, BOXX Technologies, Dell Technologies, HP, Lenovo, PNY and Supermicro. Information on pricing for Omniverse Enterprise is available at NVIDIA's Web site.