Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Clear out junk files and repair common Windows errors3Fix the driver behind crashes, sound loss and screen glitchesiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
NVIDIA’s headline brings together two distinct efforts: DRIVE AGX computing for vehicles and an Isaac robotics platform collaboration with BMW Group for factory logistics. In its May 2020 announcement, NVIDIA described plans for five AI-enabled robots to move materials and handle parts, developed and tested using simulation and real and synthetic data. That BMW announcement does not establish the specific Ampere configuration, performance, or availability of the DRIVE AGX system referenced in the headline.
What did NVIDIA announce with BMW?
On May 14, 2020, NVIDIA said BMW Group had selected its open Isaac robotics platform for factory-logistics work. NVIDIA described an end-to-end development process covering training, testing, and deployment, with the goal of improving logistics as BMW built increasingly customized vehicles. The announcement said BMW planned to deploy the system in factories worldwide; that was a stated plan, not confirmation that the rollout subsequently happened.
The plan covered five AI-enabled robots. Some were intended to navigate autonomously while transporting materials; others were designed to manipulate, select, and organize parts. NVIDIA framed the project as a way to develop a robotics pipeline for BMW’s logistics operations, rather than as an autonomous-driving project.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
How was Isaac intended to support factory robotics?
Training with real and synthetic data
NVIDIA said the robots used deep neural networks for perception, segmentation, pose estimation, and human pose estimation. Training drew on both real and synthetic data. For example, ray-traced synthetic machine parts could add training examples without relying solely on physical parts and recorded factory data.
#1 Best Overall
- The NVIDIA Jetson AGX Orin 64GB Developer Kit makes it easy to get started with Jetson Orin. Compact size, lots of connectors, and up to 275 TOPS of AI performance make this developer kit perfect for prototyping advanced AI-powered robots and other autonomous machines.
- The developer kit includes a Jetson AGX Orin 64GB module, and can emulate all the Jetson Orin modules. It supports multiple concurrent AI application pipelines with the NVIDIA Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed IO and fast memory bandwidth. Now you can develop solutions using your largest and most complex AI models to solve problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs the NVIDIA AI software stack, and use-case specific application frameworks are available, including Isaac for robotics, DeepStream for vision AI, and Riva for conversational AI. You can save significant time with NVIDIA Omniverse Replicator for synthetic data generation (SDG), and by using NVIDIA TAO toolkit to fine-tune pretrained AI models from the NGC catalog.
- Jetson ecosystem partners offer additional AI and system software, developer tools, and custom software development. They can also help with cameras and other sensors, as well as carrier boards and design services for your product.
- With the computing capability of more than 8 Jetson AGX Xavier systems in a developer kit that integrates the latest NVIDIA GPU technology with the world’s most advanced deep learning software stack, you’ll have the flexibility to create tomorrow’s AI solution as well as today’s.
Testing in simulation
NVIDIA said the robots were continuously tested in Isaac simulators. Its technical account also described staff in different geographies working together in a shared simulated Omniverse environment. Simulation offered a way to develop and test robot behavior without treating a live factory as the only test setting.
Moving from development to deployment
NVIDIA described a workflow that connected training and simulation to deployment on computers at the edge, including Jetson and EGX systems. Its May 2020 account specifically named Jetson AGX Xavier among the hardware intended to power the planned robots. The announcement presents a development approach and a deployment plan; it does not by itself establish how many factories later received the robots or what outcomes they achieved.
Rank #2
- AGX Orin 64GB Development Kit makes it easy to get started with AGX Orin. Its compact size, rich interfaces, and AI performance of up to 275 TOPS make it ideal for building advanced AI robots and other autonomous machine prototypes.
- The development kit includes AGX Orin 64GB module and can emulate all Orin modules. It utilizes the Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth. You can leverage the largest and most complex AI models to develop solutions for problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs AI software and provides application frameworks for specific use cases, such as Isaac for robotics, DeepStream for visual AI, and Riva for conversational AI. Using Omniverse Replicator for Synthetic Data Generation (SDG) can save you significant time; while fine-tuning pre-trained AI models from the NGC catalog using the TAO toolkit can further enhance your results.
- Yahboom offers four kits for users to choose from. The AIlarge model voice module utilizes examples of AI large models and multimodal models; it provides 1TB/2TB SSDs with pre-flashed driver image files; and an 8MP USB industrial camera for image processing.
- It offers various online and offline mainstream AI large model development materials. The system is pre-configured with AI vision examples, ROS case studies, and AI large models. It supports offline/online deployment of large models for voice interaction, real-time video analysis, and visual positioning, helping you quickly get started with localized AI agent development.
What hardware did NVIDIA name for the BMW robotics work?
| System or hardware | Role described by NVIDIA |
|---|---|
| DGX systems | Training and testing |
| Isaac simulation | Simulating and testing robot behavior |
| Quadro GPUs with ray tracing | Generating synthetic parts for training |
| Jetson and EGX edge computers | Computing on the robots |
| Jetson AGX Xavier | Specifically named among the hardware powering the planned robots |
An earlier NVIDIA example, published April 9, 2020, described a Smart Transport Robot using the Isaac framework on Jetson AGX Xavier for simultaneous localization and mapping (SLAM) with 3D pose estimation in a changing indoor logistics environment. That is a related example, not proof that the BMW robots all used the same configuration.
Free tools Windows power users keep installed
One-click scans. No signup required.
Why did BMW see logistics as a computing challenge?
NVIDIA’s May 2020 release described BMW’s operations using figures that should be read as NVIDIA’s account at that time, not as independently verified or current BMW statistics.
Rank #3
- AGX Orin 64GB Development Kit makes it easy to get started with AGX Orin. Its compact size, rich interfaces, and AI performance of up to 275 TOPS make it ideal for building advanced AI robots and other autonomous machine prototypes.
- The development kit includes AGX Orin 64GB module and can emulate all Orin modules. It utilizes the Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth. You can leverage the largest and most complex AI models to develop solutions for problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs AI software and provides application frameworks for specific use cases, such as Isaac for robotics, DeepStream for visual AI, and Riva for conversational AI. Using Omniverse Replicator for Synthetic Data Generation (SDG) can save you significant time; while fine-tuning pre-trained AI models from the NGC catalog using the TAO toolkit can further enhance your results.
- Yahboom offers four kits for users to choose from. The AIlarge model voice module utilizes examples of AI large models and multimodal models; it provides 1TB/2TB SSDs with pre-flashed driver image files; and an 8MP USB industrial camera for image processing.
- It offers various online and offline mainstream AI large model development materials. The system is pre-configured with AI vision examples, ROS case studies, and AI large models. It supports offline/online deployment of large models for voice interaction, real-time video analysis, and visual positioning, helping you quickly get started with localized AI agent development.
| Figure in NVIDIA’s May 2020 account | What it described |
|---|---|
| More than 4,500 | Supplier sites |
| 230,000 | Unique part numbers |
| An average of 100 | Different options per vehicle |
| 99 percent | Customer orders described as uniquely different |
| Five | AI-enabled robots in the announced logistics response |
The release also said BMW sales had doubled over the preceding ten years to 2.5 million vehicles. That is a statement made by NVIDIA in 2020, not a current sales figure. Together, the figures explain the logistics problem the announcement emphasized: coordinating parts and material flow amid many vehicle configurations.
NVIDIA quoted BMW Group logistics executive Jürgen Maidl saying: “Manufacturing high-quality, highly customized cars, on multiple models, with higher volume, on one factory line requires advanced computing solutions from end-to-end.” The company’s April technical post quoted BMW Group as saying it was developing “our own robotics pipeline to redefine logistics at BMW Group and impact the industry at large.” Those are statements of rationale and ambition, not reported measures of project results.
Rank #4
- AGX Orin 64GB Development Kit makes it easy to get started with AGX Orin. Its compact size, rich interfaces, and AI performance of up to 275 TOPS make it ideal for building advanced AI robots and other autonomous machine prototypes.
- The development kit includes AGX Orin 64GB module and can emulate all Orin modules. It utilizes the Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth. You can leverage the largest and most complex AI models to develop solutions for problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs AI software and provides application frameworks for specific use cases, such as Isaac for robotics, DeepStream for visual AI, and Riva for conversational AI. Using Omniverse Replicator for Synthetic Data Generation (SDG) can save you significant time; while fine-tuning pre-trained AI models from the NGC catalog using the TAO toolkit can further enhance your results.
- Yahboom offers four kits for users to choose from. The AIlarge model voice module utilizes examples of AI large models and multimodal models; it provides 1TB/2TB SSDs with pre-flashed driver image files; and an 8MP USB industrial camera for image processing.
- It offers various online and offline mainstream AI large model development materials. The system is pre-configured with AI vision examples, ROS case studies, and AI large models. It supports offline/online deployment of large models for voice interaction, real-time video analysis, and visual positioning, helping you quickly get started with localized AI agent development.
How does DRIVE AGX relate to autonomous cars?
DRIVE AGX belongs to NVIDIA’s automotive-computing work, while the BMW Isaac announcement concerned factory robots. NVIDIA currently describes DRIVE AGX as in-vehicle AI computing and DRIVE AV as its autonomous-driving software stack. These are different use cases and software roles from Isaac’s factory-robotics tools.
| Platform or stack | Use described | Current NVIDIA figures checked October 4, 2026 |
|---|---|---|
| DRIVE AGX Orin | In-vehicle AI computing | Up to 254 TOPS |
| DRIVE AGX Thor | In-vehicle AI computing | More than 1,000 INT8 TOPS |
| DRIVE AV | Autonomous-driving software stack | Not stated here |
| Isaac | Robotics development and simulation tools, including the BMW factory-logistics use case | Not stated here |
The Orin and Thor figures are claims on NVIDIA’s current product page checked on October 4, 2026. They are not specifications for the earlier Ampere-infused DRIVE AGX announcement.
Best Value
- GPU:2560-core NVIDIA Blackwell architecture GPU with 96 fifth-gen Tensor Cores
- AI Performance:2070 TFLOPS
What is established about the Ampere-infused DRIVE AGX announcement?
The available NVIDIA material supports the distinction between automotive computing and BMW factory robotics, but it does not establish the original Ampere-era DRIVE AGX system’s exact configuration, performance figures, release schedule, or geographic availability. Current Orin and Thor specifications cannot fill that historical gap. They describe products on NVIDIA’s current page, not the system referenced in the older headline.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
