Next-generation sensor fusion for

next-generation ADAS and sensors

25th Nov, 2021

‌The technology of BASELABS Dynamic Grid

In essence, BASELABS Dynamic Grid divides the environment into small areas, so-called cells. For each cell, the algorithm determines whether it is occupied or not. If an object occupies a cell, its velocity and driving direction are also calculated. Finally, static and dynamic objects are separated and provided together with free space, e.g., for maneuver decisions and path planning.

‌

"With the Dynamic Grid, we present a superior alternative to the combination of classical tracking methods and a static occupancy grid. The Dynamic Grid processes the data in an integrated manner in a self-contained algorithm. Thus, we avoid inconsistencies that the combination of the two different methods of tracking and static grid fusion in the classical approach often entails. The Dynamic Grid can show its strengths, especially in scenarios with many objects and different directions of motion in the vehicle's environment. In addition, the algorithm can recognize objects of any shape without being trained on them at great expense," emphasizes Norman Mattern, Head of Product Development at BASELABS.

From a software technology perspective, the Dynamic Grid is a library. It is suitable for both prototyping and production purposes.

‌‌

A broader view: How do current sensor fusion approaches relate to  BASELABS Dynamic Grid?

Current sensor fusion approaches, like the combination of object fusion and static grid fusion, feature high modularity. Despite its benefits, this approach relies on an early and irreversible reduction of information. Eric Richter, a Co-founder and one of our leading sensor fusion experts, outlines how this inherent property of the current-generation sensor fusion approaches results in a high risk of failure in challenging scenarios. He introduces BASELABS Dynamic Grid as an alternative to conventional approaches to overcome their limitations.

Key take-aways:

• Current sensor fusion approaches have inherent properties that limit their applicability for next-generation driving functions and sensors.
• Integrated sensor fusion approaches resolve these limitations and thus enable next-gen driving functions.
• The Dynamic Grid is the integrated next-gen sensor fusion technology, ready for series production.

Read Eric's article

‌‌

BASELABS supports you on your journey to production

Sourcing software from a supplier is a matter of trust and support to ensure that you achieve your project goals. Our team supports you in multiple ways regarding the application of BASELABS Dynamic Grid for your project – from pre-purchase to implementation.

• Consulting, e.g., regarding software architecture, suitability for particular sensor instances, expected output performance, and suitability for specific use cases
• Application or R&D project, e.g., use-case specific parametrization, architecture, or feature implementation
• General support, e.g., getting started, bug identification, integration

Feel free to book a brief call with Marcus Obst, our Head of Business Development.