Grid Fusion

BASELABS dynamic grid provides integrated dynamic object and free space fusion for automated driving functions with SAE level 3-4 in unstructured urban environments.

Integrated dynamic object and free space fusion

The dynamic grid is a new approach to detect stationary and dynamic objects and to estimate free space in an integrated algorithm. ECUs with integrated GPU are ideal for the use of the algorithm. Especially, it runs on CUDA-capable GPUs, e.g. on the Nvidia's Drive Xavier platform. The dynamic grid makes optimal use of their performance.


Use cases

Parking, stop&go, urban

Exemplary use cases for the dynamic grid are:

  • automated parking,
  • stop & go-use cases like traffic jam pilot,
  • urban and unstructured environments.

"The dynamic grid provided by BASELABS is a promising algorithm to significantly improve the environment perception in challenging environments."


Dr. Steen Kristensen

Sensior Expert and Teamleader Comprehensive Environment Model

Algorithm overview

The algorithm divides the environment into small areas, so-called cells. For each cell, the algorithm determines whether it is free or occupied. If it is occupied by an object, its velocity and driving direction are also calculated. Finally, static and dynamic objects are clearly separated from each other and provided together with the free space, e.g. for maneuver decisions and path planning.




Kalman filters and occupancy grids are multi-purpose, but not all-purpose

So far, two different approaches have been used for these two tasks – objects tracking and free space estimation. Kalman filter-based algorithms like the Extended Kalman Filter (EKF) are used to track vehicles and other road users. These algorithms use models to predict the behavior of the objects. This works very well for objects that match these models, but not if the objects behave very differently. For instance, if a system is designed to track cars, it is likely to perform insufficiently when faced with cyclists. Occupancy grid approaches are used to estimate the free space. These algorithms can detect any kind of object without the need for specific object models but has the disadvantage that it can only be used in static environments without too many missed moving objects as they usually distort the result and lead to false positive and false negative classifications.

How to process lidar point clouds for urban environments

Loading the player ...

Urban environments add new challenges for automated driving functions and the required environment models. While highway-like scenarios mainly contain objects that can be well modelled and detected using classical data fusion and tracking methods, the objects in cities are more diverse, more complex to model and partially unforeseeable. To address urban environments, high resolution lidar sensors are becoming more and more popular. However, classical algorithms like the occupancy grid have severe shortcomings when it comes to the processing of lidar point clouds in scenarios that contain both stationary and moving objects. The dynamic grid is a new approach that overcomes these shortcomings and determines free space as well as static and dynamic objects in an integrated algorithm.

Contact & More

Top of page