Found in Robotics News & Content, with a score of 0.77
…Manipulator is a collection of foundation models and modular GPU-accelerated libraries that help industrial automation companies build scalable and repeatable workflows for dynamic manipulation tasks by accelerating AI model training and task reprogramming. Foundation models are based on a transformer deep learning architecture that allows a neural network to learn by tracking relationships in data. They’re generally trained on huge datasets and can be used to process and understand sensor and robot information as magically as ChatGPT for text. This enables robot perception and decision-making like never before and provides zero-shot learning - the ability to perform tasks without prior…
Found in Robotics News & Content, with a score of 0.24
…faster cycle times, each PickOne iPC runs off one GPU, allowing the system to process images faster than generalized AI. “We deal on the order of 10s of milliseconds,” Nieves said. “I don't have to have a constellation of computational power.” But it takes more than Goldilocks-sized computing to speed up pick cycles. Plus One exclusively deploys camera-off-robot hardware placement for image acquisition. After the robot arm picks a piece and moves out of the picking area, the camera captures the next image so the software can start analyzing it. “By the time the robot comes back, it already knows…
Found in Robotics News & Content, with a score of 0.64
…processes a large number of cameras and LiDAR data in real time by accelerating the full stack on the GPU and several other processors built into the NVIDIA Jetson AGX Orin module. MiR said the MiR1200 pallet jack’s ability to navigate in tight spaces with minimal changes to the existing infrastructure makes it the perfect fit for optimizing logistics efficiency and ensuring timely delivery of pallets. Teradyne Robotics, MiR’s parent company, also recently announced another partnership with NVIDIA through Universal Robots.
Found in Robotics News & Content, with a score of 1.05
…all kinds of robots, from simple consumer ‘bots to GPU-fueled, AI-powered systems. The Center was founded in 2022 with a $8.8 million capital investment from the Innovation Institute at the Massachusetts Technology Collaborative (MassTech) and Boston University, with support of MassRobotics, and industry partners AETLabs, Ava Robotics, Boston Scientific, GreenSight, Intel and Ubiros. At the inaugural celebration, Boston University Provost Ad Interim Kenneth Lutchen led opening remarks and introduced Commonwealth of Massachusetts Secretary of Economic Development Yvonne Hao who initiated the ribbon cutting. Speakers also included: MassTech Collaborative executive director Carolyn Kirk Amazon Robotics Chief Technologist Tye Brady ASML senior…
Found in Robotics News & Content, with a score of 1.15
…- a collection of foundation models, robotics tools and GPU-accelerated libraries. During Monday’s keynote, NVIDIA founder and CEO Jensen Huang demonstrated Project GR00T, a general-purpose foundation model for humanoid robot learning. Project GR00T uses various new tools from the NVIDIA Isaac robotics platform to create AI for humanoid robots. “Building foundation models for general humanoid robots is one of the most exciting problems to solve in AI today,” Huang said. “The enabling technologies are coming together for leading roboticists around the world to take giant leaps toward artificial general robotics.” NVIDIA also announced a new computer for humanoid robots based…
Found in Robotics News & Content, with a score of 0.68
…microservice solves complex routing problems with multiple constraints using GPU-accelerated evolutionary algorithms. All of this happens in real time, while Isaac Mission Control coordinates the entire fleet using map data and route graphs from cuOpt to send and execute AMR commands. AI agents on the move AI agents can assist in large-scale industrial environments by, for example, managing fleets of robots in a factory or identifying streamlined configurations for human-robot collaboration in supply chain distribution centers. To build these complex agents, developers need digital twins that function as AI gyms - physically accurate environments for AI evaluation, simulation and training.…
Found in Robotics News & Content, with a score of 0.90
…RK3588 SoC with an eight-core CPU, a Mali G610 GPU, and an NPU with up to 6 TOPs with support for up to four MIPI CSI cameras. RGo Perception Engine can function in dynamic environments RGo’s Perception Engine is fully integrated into the JAGUAR board. It can track robot pose, location, and heading to centimeter-scale accuracy. RGo said its machine vision software can function in dynamic, unstructured, or repetitive environments, indoors and outdoors, and on fast-moving machines such as forklifts and cart tuggers. The companies said their system can be integrated into a wide range of industrial robots such as…
Found in Robotics News & Content, with a score of 0.89
…April 2023, Kodiak Robotics introduced its fifth-generation hardware in its autonomous truck fleet. The update increased sensor redundancy and GPU processing power. “The Ryder facility will serve as a base to conduct testing and to validate the truckport operational model,” Burnette added. “Leveraging existing infrastructure eliminates the need for Kodiak to build and develop real estate, and it allows us to focus on launching and scaling driverless truck deployment.”
Found in Robotics News & Content, with a score of 0.69
…robotics together. At the center of the relationship is GPU-accelerated large language models (LLMs), which bring higher levels of adaptability and intelligence to various machines. The “human” brain of robotics “Autonomous robots powered by artificial intelligence are being increasingly utilized for improving efficiency, decreasing costs and tackling labor shortages,” Talla said. LLMs work as the language center in the robot “brain” and will allow them to better understand and more naturally respond to human prompts. As such, these machines will have the ability to learn from not only human interaction, but their robot counterparts. “Given these attributes, generative AI is…
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 0.56
…and four ARM Cortex-A55 at 1.8 GHz, a Mali G610-GPU, and an NPU with up to 6 TOPS (trillions of operations per second). JAGUAR opens up a wide range of possibilities for AI and machine learning applications, Theobroma Systems said. The JAGUAR system is designed for robust AMRs. Click on image to enlarge. Source: Theobroma Systems System has multiple interfaces, single power supply Two SuperSpeed USB 3.1 interfaces enable high-resolution cameras, stereo cameras, or sensors such as 2D and 3D lidar, as well as ToF sensors to be connected. Four MIPI-CSI interfaces allow the cost-efficient connection of high-resolution cameras, said…
Found in Robotics News & Content, with a score of 1.74
…a coding LLM. Then, it iterates between reward sampling, GPU-accelerated reward evaluation, and reward reflection to progressively improve its reward outputs. Click on image to enlarge. Source: NVIDIA Research Eureka AI trains robots Eureka-generated reward programs — which enable trial-and-error learning for robots — can outperform expert human-written ones on more than 80% of tasks, according to the paper. This leads to an average performance improvement of more than 50% for the bots, said NVIDIA. The AI agent taps the GPT-4 LLM and generative AI to write software code that rewards robots for reinforcement learning. It doesn’t require task-specific prompting…