Nvidia has announced updates to its robotics simulation tools that will enable companies to build and test virtual robots in a variety of realistic environments and operating conditions, all securely in the cloud.
Unveiled at CES, improvements to Nvidia’s Isaac Sim, a suite of robotics simulation tools, include the ability to simulate human behavior in environments such as warehouses or manufacturing plants to help collaborative robots (cobots) or autonomous mobile robots understand and identify common behavior and potential obstacles they will face in the real world.
Robotics platform improvements will accelerate the development and deployment of autonomous robots, Nvidia says, by making it easier to develop, validate, and deploy artificial intelligence (AI) to ensure they can operate successfully and safely in a variety of environments.
“Simulation is a critical technology that will enable the development of complex software systems that will power the next wave of smarter, more autonomous robots. In simulation, virtual robots are a testing ground for their complex software stacks and multiple AI models,” said Gerard Andrews, senior product manager at Nvidia.
Accuracy and safety
By adding simulations of human behavior and interaction in the environment, such as lifting and moving objects, pushing carts, and moving to new locations, it is possible to test how adding robots to the environment can unfold without endangering humans.
Common events such as people interacting with an industrial environment or moving through a warehouse, and less common events such as unforeseen emergencies and other scenarios can be simulated to help create robots that can respond in different ways. .
To this end, using Nvidia RTX technology, Isaac Sim has improved sensor support, which allows the display of physically accurate sensor data in real time, including ray tracing to provide more accurate sensor data in various lighting conditions or depending on reflective materials.
This allows worlds to be modeled based on physically accurate sensory models, minimizing differences between the simulation and the real environment to provide the most accurate robot training possible.
Virtual robots available in the cloud
The new version of Isaac Sim also provides a host of new 3D ready-to-model objects, including warehouse parts and popular robots, so developers and users can get started quickly.
Built on Nvidia Omniverse, the company’s platform for creating and operating applications from the metaverse, Isaac Sim is available via the cloud, giving teams working on robotics projects the ability to collaborate with accessibility, flexibility, and scalability for testing and training virtual robots.
“With access to the cloud and its vast array of photorealistic and physically accurate modeling capabilities, Isaac Sim is poised to set new methodologies for developing intelligent robots,” said Gerard Andrews.
Other CES 2023 announcements