NVIDIA has introduced the Isaac Autonomous Mobile Robot (AMR) platform that extends NVIDIA Isaac capabilities for building and deploying robotics applications, bringing mapping, site analytics and fleet optimisation onto NVIDIA EGX servers.
Besides optimising operational efficiency and accelerating deployment of AMRs, the new platform can save logistics businesses billions of dollars.
AMR deployments are estimated to reach 53,000 sites by 2025, up from 9,000 in 2020, according to Interact Analysis.
Amid supply chain constraints due to increasing e-commerce and lack of workers, businesses need to clear the hurdle of rapidly and autonomously developing high-accuracy robot maps. It’s no mean feat as they need to be continuously updated as operations scale or fluctuate.
Every environmental change needs a reoptimisation of routes to maximise operational efficiency. Here’s where the Isaac AMR platform comes in. It uses NVIDIA Omniverse to create digital twins of the facility and simulates the behaviour of robot fleets, people and other machines in the digital twins with high-fidelity physics and perception.
Isaac AMR consists of GPU-accelerated AI technologies and SDKs including DeepMap, Metropolis and ReOpt.
DeepMap’s cloud-based SDK helps accelerate robot mapping of large facilities from weeks to days, while achieving centimetre-level accuracy.
NVIDIA Metropolis is a video analytics platform that provides access to cameras and sensors deployed all over the factory or warehouse floor, improving situational awareness.
NVIDIA ReOpt AI software libraries optimise vehicle route planning and logistics in real time, which can be applied to fleets of AMRs.
Available on NVIDIA EGX servers, Isaac AMR enhances the development of AI-driven logistics by providing a complete path to build industrial and human-robot simulations as well as route optimisations.