NVIDIA DRIVE Platform

The NVIDIA DRIVE Platform is an autonomous computing platform that enables automakers and Tier-1 suppliers to accelerate production of automated and autonomous vehicles. It scales from a palm-sized, energy efficient module for AutoCruise capabilities, to a powerful AI supercomputer capable of autonomous driving.

The DRIVE Platform is capable of understanding in real-time what's happening around the vehicle, precisely locate itself on an HD map, and plan a safe path forward. It's the world's most advanced self-driving car platform—combining deep learning, sensor fusion, and surround vision to change the driving experience.

The scalable architecture is available in a variety of configurations. These range from one passively cooled mobile processor operating at 10 watts, to a multi-chip configuration with two mobile processors and two discrete GPUs delivering 24 trillion deep learning operations per second. Multiple DRIVE platforms can be used in parallel to enable fully autonomous driving.

Can be added to any Perception Kit

AutonomouStuff has worked closely with NVIDIA to put together kits to help make your transition to autonomy as simple as possible with the NVIDIA Drive PX on Wheels.

Categories: , Brand:

Features

The Software

DRIVE PX can fuse data from 12 cameras, as well as lidar, radar, and ultrasonic sensors. This allows algorithms to accurately understand the full 360 degree environment around the car to produce a robust representation, including static and dynamic objects. Use of Deep Neural Networks (DNN) for the detection and classification of objects dramatically increases the accuracy of the resulting fused sensor data.

DRIVE PX platforms are built around deep learning and include a powerful framework (Caffe) to run DNN models designed and trained on NVIDIA DIGITS™. DRIVE PX also includes an advanced computer vision (CV) library and primitives. Together, these technologies deliver an impressive combination of detection and tracking.

DRIVE PX features a surround view solution that delivers a seamless 360-degree view around the car. It captures, processes, and stitches together multiple HD camera inputs. Then, DRIVE PX uses sophisticated structure-from-motion (SFM) and advanced stitching for better image rendering and reduced “ghosting”, such as where a line on the pavement can appear in two places at once.

Driveworks

  • Kernel version 4.4.38 kernel with RT_PREEMPT patches
  • Support for 64-bit user space and runtime libraries
  • NvMedia APIs for HW accelerated multimedia and camera input processing
  • NVIDIA CUDA 8.0 parallel computing platform
  • Graphics APIs:
    • OpenGL 4.5
    • OpenGL ES 3.2
    • EGL 1.5 with EGLStream extensions
  • Ubuntu 16.04 LTS target Root File System (RFS)

The Hardware

Powered by NVIDIA’s fastest SOCs and leveraging the same architecture as the world’s most powerful supercomputers, DRIVE PX enables self-driving applications to be developed faster and more accurately.

Key features of the platform include:

  • Dual NVIDIA Tegra® Parker processors delivering a combined 24 DNN Teraflops
  • Interfaces for up to 12 cameras, radar, lidar, GPS/IMU and ultrasonic sensors
  • Rich middleware for graphics, computer vision, and deep learning
  • Periodic software/OS updates

Media

Specifications

Hardware

SOC 2x Tegra Parker
GPU 2x Integrated Pascal + 2x Discrete Pascal
CPU 4x NVIDIA Denver + 8x ARM Cortex-A57
MEMORY 16GB LPDDR4
DISPLAY 2x HDMI, FPDLink III, GMSL
DATA STORAGE 128GB eMMC
DATA STORAGE 128GB eMMC
OTHER GMSL, CAN, UART, LIN, GPIOs
USB USB 3.0 + USB 2.0
CONNECTIVITY 1 Gigabit Ethernet, 10 Gigabit Ethernet
SAFETY CONTROLLER Infineon Aurix ASIL-D MCU
Nominal Power Consumption 80 W