Sensor Fusion Insights

Thoughtful considerations are required when making strategic or technical decisions for sensor fusion. BASELABS experts share strategic and technical advise to enrich your thinking.

10.08.2022 - A Sensor Fusion Benchmark of ARM CPUs

With ARMs Cortex-A76 and Cortex-A55 becoming more and more available in the automotive industry, Norman Mattern, Head of Productmanagement, was curious how the efficiency of those CPU micro-architectures improved compared to their predecessors Cortex-A72 and Cortex-A53 when executing sensor fusion code. Read his article when you are interested in the results of our experiments on this.

07.06.2022 - Mit Dynamic Grid zu neuen Fahrfunktionen - Sensorfusion der nächsten Generation

Aktuelle Sensorfusionsansätze sind in der Regel für Autobahnbedingungen ausgelegt. Für städtische Szenarien hingegen sind integrierte Sensorfusionstechnologien erforderlich, die die Einschränkungen aktueller Ansätze überwinden.

Read the article

22.03.2022 - Why the best way to detect objects is not to detect them - A Comparison of Environmental Model Architectures for Automated Driving

Automated driving functions with higher automation levels require safe path planning that considers dynamic objects. If object dynamics are derived using approaches that rely on object detection, this involves severe risks due to error propagation in the processing chain. Eric Richter explains how integrated sensor fusion algorithms like the dynamic grid avoid these errors and provide the basis for safe path planning.

Read Eric's article

10.12.2021 Sensor Fusion — It’s all about Prediction

Sensor fusion systems spend a significant amount of resources in predicting the future. Eric Richter explains how a multiple model approach can better predict different object classes and thus dramatically improve sensor fusion performance.
In summary, sensor fusion systems should support class-specific motion models using multiple model approaches to account for different object behaviors, to initialize tracks using multiple hypotheses to cope with initialization ambiguities,to apply different sensor models depending on the object class, and to efficiently handle the hypotheses to save CPU and memory resources.

Read Eric's article

24.11.2021 - Next-Generation Sensor Fusion for Next-Generation Sensors and Driving Functions

Current sensor fusion approaches have inherent properties that limit their applicability for next-generation driving functions and sensors. Integrated sensor fusion approaches like the Dynamic Grid resolve these limitations and thus, enable next-generation driving functions.

In his article, Eric Richter will show why.

30.07.2021 How software sourcing can leverage your competitive advantage — if you pay enough attention

Learn why library sourcing is a winning strategy for sensor fusion software and how it combines in-house development and software licensing advantages. Strategic software sourcing - for sensor fusion software and others - is one of the most impactful factors for delivering driving automation systems in time and budget. Read Robin's article

24.06.2021 The underestimated factor in your automated driving software strategy

Your software is aging. Only regular maintenance ensures smooth operation, which ties up essential resources. Due to that, it is impossible to cover the increasing complexity of software development with constant resources. That is why Robin Schubert, CEO of BASELABS, considers strategic software sourcing one of the most impactful factors for delivering driving automation systems in time and budget in the years to come. Read Robin's article

12.05.2021 Sensor Fusion and DMIPS

Predicting the runtime of sensor fusion algorithms is essential for selecting a particular embedded platform that is suitable for the intended driving function. Therefore, our product manager Norman Mattern analyzed whether DMIPS is a valuable metric for the runtime prediction on different platforms, like Infineon AURIX and ARM Cortex. Read Norman's article

31.03.2021: Driving Towards Level 2+ | Safe and scalable sensor fusion ecosystem with Infineon's AURIX™

The underlying hardware and software ecosystem needs to be safe and scalable to efficiently handle the complexity of sensor fusion development for safety-critical automotive applications. The sensor fusion platform BASELABS Create Embedded is the perfect fit for the Infineon AURIX™ microcontroller TC3xx family when approaching the development of ADAS systems that vehicle owners can trust.
The cooperation between Infineon and BASELABS has resulted in a safe and reliable sensor fusion platform for safety-critical applications and automated driving. In this context, the whitepaper "Driving Towards Level 2+ Sensor Fusion for ADAS" has been published: Download Whitepaper

05.02.2021 Sensor Models — Key Ingredient for Sensor Fusion in Automated Driving

BASELABS sensor fusion expert, Eric Richter, explains why sensor models are a key ingredient for sensor fusion and how they influence the performance of the environmental model. In conclusion, Eric calls for a scalable sensor fusion architecture that separates sensor models from algorithms and that enables reusability of major architecture parts when exchanging or adding sensors.
The modular and ISO 26262 certified sensor fusion library BASELABS Create Embedded includes such a scalable architecture and allows fast sensor exchanges and modifications.
Read Eric's article

For more information, please visit our Press Releases and Articles website or contact Holger Löbel.

Contact & further information

Top of page