DataBloomOne of the biggest names in racing is going even bigger. Performance automaker Lotus launched its first SUV, the Eletre, earlier this week. The fully electric vehicle sacrifices little in terms of speed and outperforms when it comes to technology. It features an immersive digital cockpit, lengthy battery range of up to 370 miles and Read article >
The post Think Fast: Lotus Eletre Tops Charts in Driving and AI Compute Speeds, Powered by NVIDIA DRIVE Orin appeared first on NVIDIA Blog.
The future is autonomous, and AI is already transforming the transportation industry. But what exactly is an autonomous vehicle and how does it work? Autonomous…
The future is autonomous, and AI is already transforming the transportation industry. But what exactly is an autonomous vehicle and how does it work?
Autonomous vehicles are born in the data center. They require a combination of sensors, high-performance hardware, software, and high-definition mapping to operate without a human at the wheel. While the concept of this technology has existed for decades, production self-driving systems have just recently become possible due to breakthroughs in AI and compute.
Specifically, massive leaps in high-performance computing have opened new possibilities in developing, training, testing, validating, and operating autonomous vehicles. The Introduction to Autonomous Vehicles GTC session walks through these breakthroughs, how current self-driving technology works, and what’s on the horizon for intelligent transportation.
The deep neural networks that run in the vehicle are trained on massive amounts of driving data. They must learn how to identify and react to objects in the real world—an incredibly time-consuming and costly process.
A test fleet of 50 vehicles generates about 1.6 petabytes of data each day, which must be ingested, encoded, and stored before any further processing can be done.
Then, the data must be combed through to find scenarios useful for training, such as new situations or situations underrepresented in the current dataset. These useful frames typically amount to just 10% of the total collected data.
You must then label every object in the scene, including traffic lights and signs, vehicles, pedestrians, and animals, so that the DNNs can learn to identify them as well as checking for accuracy.
NVIDIA DGX data center solutions have made this onerous process into a streamlined operation by providing a veritable data factory for training and testing. With high-performance compute, you can automate the curation and labeling process, as well as run many DNN tests in parallel.
When a new model or set of models is ready to be deployed, you can then validate the networks by replaying the model against thousands of hours of driving scenarios in the data center. Simulation also provides the capability to test these models in the countless edge cases an autonomous vehicle could encounter in the real world.
NVIDIA DRIVE Sim is built on NVIDIA Omniverse to deliver a powerful, cloud-based simulation platform capable of generating a wide range of real-world scenarios for AV development and validation. It creates highly accurate, digital twins of real-world environments using precision map data.
It can run just the AV software, which is known as software-in-the-loop, or the software running on the same compute as it would in the vehicle for hardware-in-the-loop testing.
You can truly tailor situations to your specific needs using the NVIDIA DRIVE Replicator tool, which can generate entirely new data. These scenarios include physically based sensor data, along with the corresponding ground truth, to complement real-world driving data and reduce the time and cost of development.
Validated deep neural networks run in the vehicle on centralized, high-performance AI compute.
Redundant and diverse sensors, including camera, radar, lidar, and ultrasonics, collect data from the surrounding environment as the car drives. The DNNs use this data to detect objects and infer information to make driving decisions.
Processing this data while running multiple DNNs concurrently requires an incredibly high-performance AI platform.
NVIDIA DRIVE Orin is a highly advanced, software-defined compute platform for autonomous vehicles. It achieves 254 trillion operations per second, enough to handle these functions while achieving systematic safety standards for public road operations.
In addition to DNNs for perception, AVs rely on maps with centimeter-level detail for accurate localization, which is the vehicle’s ability to locate itself in the world.
Proper localization requires constantly updated maps that reflect current road conditions, such as a work zone or a lane closure, so vehicles can accurately measure distances in the environment. These maps must efficiently scale across AV fleets, with fast processing and minimal data storage. Finally, they must be able to function worldwide, so AVs can operate at scale.
NVIDIA DRIVE Map is a multimodal mapping platform designed to enable the highest levels of autonomy while improving safety. It combines survey maps built by dedicated mapping vehicles with AI-based crowdsourced mapping from customer vehicles. DRIVE Map includes four localization layers—camera, lidar, radar, and GNSS—providing the redundancy and versatility required by the most advanced AI drivers.
The AV development process isn’t linear. As humans, we never stop learning, and AI operates in the same way.
Autonomous vehicles will continue to get smarter over time as the software is trained for new tasks, enhanced, tested, and validated, then updated to the vehicle over the air.
This pipeline is continuous, with data from the vehicle constantly being collected to continuously train and improve the networks, which are then fed back into the vehicle. AI is used at all stages of the real-time computing pipeline, from perception, mapping, and localization to planning and control.
This continuous cycle is what turns vehicles from their traditional fixed-function operation to software-defined devices. Most vehicles are as advanced as they will ever be at the point of sale. With this new software-defined architecture, automakers can continually update vehicles throughout their lives with new features and functionality.
One of China’s popular battery-electric startups now has the brains to boot. NETA Auto, a Zheijiang-based electric automaker, this week announced it will build its future electric vehicles on the NVIDIA DRIVE Orin platform. These EVs will be software defined, with automated driving and intelligent features that will be continuously upgraded via over-the-air updates. This Read article >
The post Neural NETA: Automaker Selects NVIDIA DRIVE Orin for AI-Powered Vehicles appeared first on NVIDIA Blog.
When customers walk into a Microsoft Experience Center in New York City, Sydney or London, they’re instantly met with stunning graphics displayed on multiple screens and high-definition video walls inside a multi-story building. Built to showcase the latest technologies, Microsoft Experience Centers surround customers with vibrant, immersive graphics as they explore new products, watch technical Read article >
The post Microsoft Experience Centers Display Scalable, Real-Time Graphics With NVIDIA RTX and Mosaic Technology appeared first on NVIDIA Blog.
Learn the steps for reducing disk usage on NVIDIA Jetson in this webinar on November 1.
Learn the steps for reducing disk usage on NVIDIA Jetson in this webinar on November 1.
This spook-tacular Halloween edition of GFN Thursday features a special treat: 40% off a six-month GeForce NOW Priority Membership — get it for just $29.99 for a limited time. Several sweet new games are also joining the GeForce NOW library. Creatures of the night can now stream vampire survival game V Rising from the cloud. Read article >
The post Make Gaming a Priority: Special Membership Discount Hits GeForce NOW for Limited Time appeared first on NVIDIA Blog.
Find out how federal agencies are adopting AI to improve cybersecurity in this November 16 webinar featuring Booz Allen Hamilton.
Find out how federal agencies are adopting AI to improve cybersecurity in this November 16 webinar featuring Booz Allen Hamilton.
Edge AI is the deployment of AI applications in devices throughout the physical world. It’s called “edge AI” because the AI computation is done near the…
Edge AI is the deployment of AI applications in devices throughout the physical world. It’s called “edge AI” because the AI computation is done near the user at the edge of the network, close to where the data is located, rather than centrally in a cloud computing facility or private data center.
There’s a new sidewalk-savvy robot, and it’s delivering coffee, grub and a taste of fun. The bot is garnering interest for Oakland, Calif., startup Cartken. The company, founded in 2019, has rapidly deployed robots for a handful of customer applications, including for Starbucks and Grubhub deliveries. Cartken CEO Chris Bersch said that he and co-founders Read article >
The post Jetson-Driven Grub Getter: Cartken Rolls Out Robots-as-a-Service for Deliveries appeared first on NVIDIA Blog.
Medical imaging is an essential instrument for healthcare, powering screening, diagnostics, and treatment workflows around the world. Innovations and…
Medical imaging is an essential instrument for healthcare, powering screening, diagnostics, and treatment workflows around the world. Innovations and breakthroughs in computer vision are transforming the healthcare landscape with new SDKs accelerating this renaissance.
MONAI, the Medical Open Network for AI, houses many of these SDKs in its open-source suite built to drive medical AI workflows. To learn more about MONAI, see Open-Source Healthcare AI Innovation Continues to Expand with MONAI v1.0.
To run these SDKs in the cloud and connect them to the medical imaging ecosystem, platforms are needed that are accessible, secure, and strategically integrated into infrastructure like storage and networking.
Recently announced, the Google Cloud Medical Imaging Suite is one such platform that enables development of AI for imaging to support faster, more accurate diagnosis of images, increase productivity for healthcare workers, and improve access to better care and outcomes for patients. Google Cloud has adopted MONAI into their medical imaging suite, providing radiologists and pathologists with critical and compelling tools for simplifying the development and adoption of AI into their clinical practice.
The Google Cloud Imaging Suite addresses common pain points organizations face in developing artificial intelligence and machine learning (ML) models and it uses AI and ML to enable data interoperability. It includes services for imaging storage with the Cloud Healthcare API, allowing easy and secure data exchange using DICOMweb. The enterprise-grade development environment is fully managed, highly scalable, and includes services for de-identification.
The Medical Imaging Suite also includes Imaging Lab, helping to automate the highly manual and repetitive task of labeling medical images with AI-assisted annotation tools from MONAI. The Google Cloud Medical Imaging Lab is an extension of the base Jupyter environment which is packaged with the Google Cloud Deep Learning VM (DLVM) product.
This extension is accomplished by adding additional software packages to the base DLVM image, which add graphical capabilities to the Jupyter environment. This makes it possible to develop Python notebooks that interact with several medical imaging applications. This graphical environment includes the popular image analysis application 3DSlicer, pre-installed with the MONAILabel plugin.
The Jupyter-based architecture allows data scientists to leverage the power of the Python language, including PyTorch models, and to quickly visualize the results using graphical applications such as 3DSlicer. The MONAILabel server is configured to have secure access to the Google Cloud Healthcare API such that it can store images and the result of image annotations in the DICOM format.
The Google Cloud Medical Imaging Suite also includes services to build cohorts and image datasets, enabling organizations to view and search petabytes of imaging data to perform advanced analytics and create training datasets with zero operational overhead using BigQuery and Looker.
Imaging AI pipelines help to accelerate development of scalable AI models and imaging deployment offers flexible options for cloud, on-prem, or edge deployment. These services are both included in the suite and allow organizations to meet diverse sovereignty, data security, and privacy requirements while providing centralized management and policy enforcement.
MONAI provides a suite of open source tools for training, labeling, and deploying medical models into the imaging ecosystem. With regular updates and feature releases, MONAI continues to add critical and compelling components to simplify the development and adoption of AI into clinical practice.
MONAI adds critical path services to Google Cloud Medical Imaging Suite, and enables data scientists and developers on Medical Imaging Suite with the following services:
MONAI, integrated inside of Google Cloud Medical Imaging Suite, is poised to transform the end-to-end, medical AI lifecycle. Starting with data labeling to training models and running them at scale, MONAI on the medical imaging suite is being integrated into medical ecosystems using interoperable industry standards with hardware and software services in the cloud to drive this at scale.
Visit Google Medical Imaging Suite to get started.