View in Browser

Please find in this issue:

• The environmental model for automated parking
• The expert gathering for sensor fusion is coming
• Webinar - What does it take to build a great environmental model for automated parking?
• Expert knowledge about sensor fusion at your fingertips
• BASELABS contributes to ISO 23150 working group
• Inside BASELABS: How Kevin dealt with the trade-off between accuracy and speed

‌Enjoy reading!

Your BASELABS team

‌The environmental model for automated parking

We added dedicated functionality for automated parking to our algorithm for processing high-resolution sensor data. BASELABS Dynamic Grid now detects parking spaces from semantically processed camera data. In combination with reliable free space estimation, the vehicle can automatically approach parking spaces and park independently from human interaction. This functionality perfectly matches the integrated detection of dynamic and static objects by the Dynamic Grid. Both the dynamic grid and the parking space extraction run on automotive CPUs in real-time and are implemented according to ISO 26262.
Norman Mattern, Head of Product Development at BASELABS, summarizes: “The Dynamic Grid has three key advantages that apply to automated parking as well: a high detection rate, a low false alarm rate, and it runs on automotive CPUs”.

Besides parking, the Dynamic Grid is suitable for all systems that use high-resolution sensor data and include path planning functionality. The output of the Dynamic Grid is also an excellent input for machine-learning-based algorithms.

‌Please note that we offer a webinar to introduce the functionality of the Dynamic Grid. You find more info below.

‌The expert gathering for sensor fusion is coming

The event emphasizes interactive formats such as moderated group discussions, extended Q&A sessions, or workshops to facilitate learning effects, exchange and networking. We provide a dedicated opportunity with a very limited number of participants to foster in-depth discussions.
We are looking forward to renowned speakers for the event:

• Jürgen Dickmann (Mercedes-Benz)
• Mirko Mählisch (CARIAD)
• Jens Honer (Valeo)
• Andreas Hartmann (Continental)
• Roman Streubel (Continental)
• Eric Richter (BASELABS)

Former participants say about the event:

"Great gathering of fusion community with open and interesting discussion." Christian Larsson, Einride AB

"Great place to share experiences with peers that speak your ‘professional language’." Christian Gießen, Continental AG

The Sensor Fusion Forum takes place November 8th, 2022, in Chemnitz, Germany. We look forward to meeting you and welcoming you to our sensor fusion community.

Seats are limited, so make sure to apply quickly 😊

Webinar - What does it take to build a great environmental model for automated parking?

‌BASELABS recently introduced an innovative low-level sensor fusion technology for partially and highly automated vehicles - the BASELABS Dynamic Grid.

Dynamic grid fusion is suited for automated parking applications. Besides its ability to detect and separate dynamic and static objects of all kinds, it also provides a dedicated feature to extract free parking spaces from the sensor data.

In our upcoming webinar, our experts will give you a detailed understanding of BASELABS Dynamic Grid, including the usage for valet parking and how it enables next-gen sensor fusion.

The webinar will be available on-demand afterward.

Please register with the button below.

BASELABS contributes to ISO 23150 working group

The standard describes the logical interface between in-vehicle environmental perception sensors (for example, radar, lidar, camera, ultrasonic) and the fusion unit, which generates an environmental model and interprets the scene around the vehicle based on the sensor data.
Eric Richter, Director of Technology Innovation, participates in the standard's development. The next version will be released later this year.

‌Most-viewed videos of the month on the BASELABS Youtube-Channel

‌How Kevin dealt with the trade-off between accuracy and speed

‌Kevin is one of our software engineers working on the BASELABS Dynamic Grid and had some challenges to overcome: "Current challenges arise from the requirement to implement procedures that are as general as possible, but also provide meaningful results in special use cases. I have mainly dealt with recognizing parking markings used to classify parking spaces. A particular difficulty is that the developed algorithm recognizes valid markings with sufficient reliability. At the same time, it should not consume many additional computation resources. Furthermore, distinguishing between relevant and irrelevant markings for parking spaces is not always easy. With the help and adaptation of methods described in the scientific literature, I implemented a method that extracts the relevant lines both sufficiently accurately and quickly."
The BASELABS Dynamic Grid is implemented in C++. It is developed using Continuous Integration, Code Reviews, Unit Testing Tools, and Virtual Validation and is runtime optimized for ARM processors.

Want to learn more about our Dynamic Grid and how it came to life?

Events 2022

• July, 14th: Webinar - What does it take to build a great environmental model for automated parking?, online
• September 07th - 08th: ADAS & Autonomous Vehicle Technology  Expo & Conference, San Jose, California, USA
• November, 08th: Sensor Fusion Forum, Chemnitz
• November 15th - 16th: ELIV Market Place, Baden-Baden

We look forward to welcoming you in person again soon - however, please note that announced events may change at short notice due to Covid-19.

©BASELABS GmbH 2022
BASELABS GmbH, Technologie-Campus 6, 09126 Chemnitz