PRESENTATION

AI Algorithms for ADAS – Rule Based vs 4D-AI on LiDAR point clouds

In the development of ADAS and AD algorithms, AI is often understood implying NN training and validation. But Artificial Intelligence exceeds by far the domain of NN programming and depending on the use case, NN is not always the best choice. This paper presents State-of-the-Art AI programming and distinguishes cases favoring NN from cases favoring a rule based approach. Application examples like Highway Pilot, City Pilot and Traffic Monitoring are discussed isolating differentiating features requiring different approaches. The paper focuses on pure point clouds from LiDAR as this is the more recent data domain with limited accomplishments in automotive apps.

Filip Geuens

XenomatiX

Filip Geuens (°1970) is CEO of XenomatiX, a Belgium-based tier II automotive supplier, provider of true solid state lidar technology. Filip spent his entire career in optical metrology.He started as the 7th employee at a company called Krypton, developing optical coordinate measuring machines. The company was acquired by Metris which was later bought by Nikon, evolving from 70, to 700 and finally to 27.000 employees. In his previous role Filip was CTO of Nikon Metrology, one of the 6 business units of Nikon. That business unit is developing optical 3D inspection systems for quality control in automotive and aerospace. Early 2015 Filip decides to leave Nikon to build and grow XenomatiX. His past experience in optical systems and automotive business allowed him to appreciate the technology XenomatiX started developing in 2012. Today, the company employs around 30 people in Belgium, Germany, China and the US, and has built solid partnership with key automotive players. Filip holds a BE degree in Mechatronics Engineer from the university of Leuven, Belgium as well as a MS in Operations Management.