Menu
Exemplary Workflow with BASELABS Create Embedded

Sensor Fusion Library for NVIDIA DRIVE Platforms

The NVIDIA DRIVE platform offers several hardware and software features that support the development of automated driving functions. The software library BASELABS Create Embedded allows for the fast and efficient development of Level 2 ADAS and automated driving functions, such as AEB, ACC and Highway Pilot. With the software sensor fusion algorithms are seamlessly developed and executed on the DRIVE platforms.

  • Typical sensor fusion result of BASELABS Create Embedded. The sensor fusion combines detections and objects from all configured sensors to provide a unified object list of the vehicle’s surrounding. For each object, quantities like position, velocity, and class are determined. The sensor fusion eliminates individual sensor weaknesses like limited lateral or longitudinal accuracy, limited detectability or false positives. The resulting sensor fusion system integrates for the NVIDIA DRIVE platform.
    Typical sensor fusion result of BASELABS Create Embedded. The sensor fusion combines detections and objects from all configured sensors to provide a unified object list of the vehicle’s surrounding. For each object, quantities like position, velocity, and class are determined. The sensor fusion eliminates individual sensor weaknesses like limited lateral or longitudinal accuracy, limited detectability or false positives. The resulting sensor fusion system integrates for the NVIDIA DRIVE platform.
    Image 1 of 1
  • Image 1 of 1

Many modern driving functions depend on AI and deep learning methods whose results are often fed into a sensor fusion. While AI-based methods require extensive parallelization and therefore often run on GPUs, object fusion can be sequentially executed on CPUs. With the support of the ARM CPU family, the object fusion of BASELABS Create Embedded runs on the ARM part of NVIDIA DRIVE platforms.

BASELABS Create Embedded is a software solution for the fast and efficient development of sensor fusion systems for automated driving functions. Its embedded library contains fusion algorithms that combine data from radar, camera, and lidar sensors. The resulting object fusion provides a unified object list of the vehicle environment and serves as an input for automated driving functions.

  • A typical development workflow in combination with the NVIDIA DRIVE platform would start by recording some measurement data using ROS. Then, with the sensor fusion designer of BASELABS Create Embedded, all sensors are individually configured and a specific sensor fusion system or library is generated including an appropriate ROS node. The resulting C library and the ROS node (C++) are compiled for PC and the NVIDIA DRIVE platform. The sensor fusion ROS node is now integrated into a larger application that performs additional processing steps such as path planning or decision making. The final ROS application can be executed on PC including diagnostics and visualization functionality or on NVIDIA DRIVE platforms - with recorded measurement data from ROSbag files or with physically connected sensors.
    A typical development workflow in combination with the NVIDIA DRIVE platform would start by recording some measurement data using ROS. Then, with the sensor fusion designer of BASELABS Create Embedded, all sensors are individually configured and a specific sensor fusion system or library is generated including an appropriate ROS node. The resulting C library and the ROS node (C++) are compiled for PC and the NVIDIA DRIVE platform. The sensor fusion ROS node is now integrated into a larger application that performs additional processing steps such as path planning or decision making. The final ROS application can be executed on PC including diagnostics and visualization functionality or on NVIDIA DRIVE platforms - with recorded measurement data from ROSbag files or with physically connected sensors.
    Image 1 of 1
  • Develop custom sensor fusion algorithms with the graphical sensor fusion designer
  • Use built-in sensor models for typical automotive sensors, e.g. camera & radar
  • Implement custom sensor models with the sensor fusion SDK
  • Get MISRA compliant, numerically stable and human-readable C-source code
  • Developed according to ASPICE and ISO 26262
  • Use the sensor fusion designer to configure, customize, and parameterize radar, camera and, lidar sensors of your vehicle setup. A specific object fusion library is generated from this configuration that integrates into any C/C++ application or middleware.
    Use the sensor fusion designer to configure, customize, and parameterize radar, camera and, lidar sensors of your vehicle setup. A specific object fusion library is generated from this configuration that integrates into any C/C++ application or middleware.
    Image 1 of 1
  • Automated ROS integration and ROS node generation 
  • Execute the sensor fusion algorithm on NVIDIA DRIVE platforms
  • Built-in sensor fusion visualization 
  • Set parameters during design-time and at runtime
  • Generate sensor fusion ROS nodes with BASELABS Create Embedded in seconds and integrate these ROS nodes into your application.
    Generate sensor fusion ROS nodes with BASELABS Create Embedded in seconds and integrate these ROS nodes into your application.
    Image 1 of 1

Contact & further information

  • BASELABS Create Embedded

    A library for the development of embedded sensor fusion systems for automated driving functions.

    More information

  • Contact

    Get in touch with Eric Richter, Director Innovation Technology of BASELABS.

    Contact us

  • Sensor Fusion Hub

    Gain valuable insights into Sensor Fusion - From Object Fusion to Dynamic Grids. 

    Learn more
Top of page