Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

NVIDIA Isaac Perceptor

NVIDIA Isaac™ Perceptor, built on Isaac ROS, is a reference workflow of NVIDIA-accelerated libraries and AI models that helps you quickly build robust autonomous mobile robots (AMRs). These robots are designed to perceive, localize, and operate in unstructured environments like warehouses, factories, and outdoor settings.

Download NowForumsDocumentation


How NVIDIA Isaac Perceptor Works

Today’s unstructured environments pose unique predictability challenges for AMRs, including task-specific complexities like load pickup and dropoff. NVIDIA-accelerated libraries and AI models help you overcome these complexities by enabling advanced 3D perception capabilities that ensure optimal performance and modularity for your specific needs.

You can integrate one or all of Perceptor’s technologies into your own AMR software stack to achieve advanced AI for perception capabilities or evaluate it with the NVIDIA Nova Orin Developer Kit.

A diagram showing  how NVIDIA Isaac Perceptor works

Key Benefits

    Fully Optimized for Mobile Robots

    Explore technologies that are purpose-built for developers of autonomous forklifts and industrial mobile robots, powering robust visual odometry and 3D surround vision for obstacle detection, and occupancy mapping.

    Scalable Sensor Architecture

    Tap into the industry’s first scalable architecture for one to eight cameras with time synchronization across all the cameras and Inertial Measurement Units (IMUs). 

    Ready for Deployment

    Take advantage of pre-integrated, extensively tested subgraphs for mobile robots to ensure seamless integration with existing software stacks and robots.


      Key Features

      Visual AI for real-time 3D occupancy grid

      Real-Time 3D Occupancy Grid

      Get results 100X faster than with CPU-centric methods using nvblox. This NVIDIA® CUDA®-accelerated 3D reconstruction library can identify obstacles up to 5 meters away to provide a 2D costmap.

      An image showing accelerated stereo visual odometry

      Accelerated Stereo Visual Odometry

      Seamlessly navigate environments with sparse visual features or repetitive patterns by fusing input from multiple viewpoints using NVIDIA cuVSLAM.

      Comparison of AI-based depth perception

      AI-Based Depth Perception

      Take advantage of stereo DNN for dense, detailed, robust complexity. The stereo disparity is calculated from a time-synchronized image pair sourced from a stereo camera and used to produce a depth image or a point cloud for a scene.

      Open Ecosystem

      Built on ROS

      NVIDIA Isaac Manipulator is built on the open-source ROS 2 (Robot Operating System) software framework. This lets the millions of developers in the ROS community easily take advantage of NVIDIA-accelerated libraries and AI models to accelerate their AI robot development and deployment workflows.

      Learn More About Isaac ROS
      Open Robotics ROS logo

      ROS is a trademark of Open Robotics

      Wheel.me Self-Driving Robots Use RGo and the NVIDIA Isaac Platform

      Wheel.me stands out with its ambitious mission: to transform anything that moves into an autonomous mobile robot (AMR). Learn how the company, in collaboration with NVIDIA and RGo Robotics, is reshaping the landscape of mobile robotics.

      Read the Case Study

      Isaac Perceptor Learning Library

      Guide

      Isaac Perceptor: Overview

      Get started with an introduction to the basics of Isaac Perceptor.

      Tech Blog

      Create, Design, and Deploy Robotics Applications Using NVIDIA Isaac Workflows

      Learn more about the AI features used to accelerate the development of multi-camera, 3D surround-vision capabilities for AI-based autonomous mobile robots.

      Tutorial

      Autonomous Navigation With Isaac Perceptor and Nav2

      This tutorial will help you run autonomous navigation with the Nova Carter robot. It uses the Isaac Perceptor stack for local camera-based 3D perception, AMCL for lidar localization, and Nav2 for navigation.


      More Resources

      Decorative image representing forums

      Explore the Community

      Get Training and Certification

      Meet the Program for Startups


        NVIDIA Nova Orin Developer Kit

        This powerful compute and sensor platform is designed to help robot OEMs and software companies accelerate the development and deployment of AMRs. Key features include:

        • Precise, multi-sensor time synchronization within <100us of sensor data acquisition time

        • Documentation and software for evaluation on your robot

        • Sensor reference models (in NVIDIA Isaac Sim) for development in simulation.

        • Get yours today from Leopard Imaging or Segway Robotics.

         The NVIDIA Jetson Nova Orin Developer Kit

        Ecosystem

        Our industry partners and collaborators are integrating NVIDIA Isaac Perceptor and accelerated computing into their platforms and solutions.

         NVIDIA Isaac Manipulator Ecosystem and Industry partner - Franka Robotics
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Intrinsic
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Picknik
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Solomon
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Techman
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - UR / MIR / Teradyne Robotics
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Vention
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Yaskawa
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Yaskawa
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Yaskawa
        NVIDIA Isaac Manipulator Ecosystem and Industry partner - Yaskawa

        Latest Robotic News


        Get started today with NVIDIA Isaac Perceptor.

        Download NowDocumentation