QNX Platform for ADAS

Enabling advanced driver assistance systems and autonomous driving through software

Moving ADAS and Autonomous Driving From R&D Labs to Production

Autonomous cars contain the most complex hardware and software ever deployed by automakers. The software must process a flood of data from sensors such as cameras, LiDAR and radar in real time to form a model of the car’s surroundings and make safe decisions on control of the vehicle. This requires highly efficient, safe and secure software that can make use of special purpose hardware (accelerators) for vision processing and deep neural-net based machine learning algorithms.

The QNX Platform for ADAS (Advanced driver-assistance systems) provides a software foundation that enables the above functions to deliver advanced driver assistance systems (ADAS) and automated driving applications. The QNX Platform for ADAS is built upon the QNX OS for Safety, which is certified by TÜV Rheinland to ISO 26262 ASIL D.

Flexible, Modular and Hardware-optimized Approach to ADAS Safety

flexibility Created with Sketch.
Flexible Platform Approach

With one solution the QNX Platform for ADAS offers a foundational base that offers tremendous range for ADAS and automated driving applications to be built upon. From multi-camera surround views, to active safety systems such as emergency braking, all the way and fully autonomous driving systems.

highly-configurable Created with Sketch.
Reduced Recoding and Redesign for Software and Hardware

The autonomous car control system is a distributed processing environment that manages the flow of data from sensors to decision making, and finally to actuation of the physical components, such as steering, throttle and braking. Given the fast-paced innovation in both hardware and software, it is important to create modular software components that can be deployed independently from the underlying hardware implementation.

high-efficiency-technology Created with Sketch.
Optimized for Automotive Silicon

Automotive system-on-chips (SoCs) are continually getting faster and powerful to handle the computation load for image processing, machine learning and digital control algorithms. A BSP, or board support package, is the name given to the software responsible for hardware specific operations required to get a realtime operating system (RTOS) up and running. BlackBerry QNX and our partners have invested considerably in ensuring that the QNX Platform for ADAS software is built to be compatible with specialized processing cores available on a variety of ADAS processors. Automotive OEMs and Tier 1s can use QNX Platform with the assurance that it is optimized to perform with the world’s leading silicon processors.

Technology

The QNX Platform for ADAS offers numerous features, including:

  • Reference implementations for four camera surround view, single camera ADAS, sensor hub with multi-camera input
  • Low latency sensor data acquisition: support for camera, radar, LiDAR, IMU, GPS sensors
  • Publish and subscribe sensor data access
  • Data visualization
  • Network plugins to provide sensor data over automotive networks
  • Sensor data capture with time stamped data samples. Sensor data playback maintains timing fidelity
  • Configurable timestamp sources such as IEEE 1588 PTP or IEEE 802.1AS
  • Robot OS (ROS) integration for testing and prototyping. Export data using ROS to compatible tools such as Matlab
  • Integrated open source libraries including OpenCV, SOME/IP and others

Supported Sensors

  • Point Grey USB 3.0 cameras
  • Omnivision OV10640
  • Omnivision OV10635
  • Aptina AR0132 Enyo
  • GigE vision cameras
  • ONVIF Profile S cameras
  • Delphi ESR
  • Delphi SRR2
  • Velodyne VLP-16
  • Velodyne VLP-16 HiRes
  • Leddartech VU8
  • Xsens MTI G-710
  • Novatel GPS and IMU

Supported Processors

  • Renesas H3
  • Renesas V3M
  • Intel Denverton
  • Intel Apollo Lake

Resources

Product Brief: QNX Platform for ADAS

Download

Whitepaper: Automotive Functional Safety: No Hiding Place

Download

Press Release: BlackBerry and Baidu Partnering to Accelerate Connected and Autonomous Vehicle Technology

Read