/Autosens BXL

Autosens BXL

12 - 15 September 2022 | Brussels, BE

Where do we see ADAS en AV going?

Imec

13 September

11h30: Latest developments in RADAR Chaired by: Wilfried Philips Scientific Lead Sensor Fusion imec/Ghent University

15h20: Prof. Jan Aelterman, IPI Research Group, Ghent University-Imec

The Real-World Value of Cooperative Sensor and Multi-Exposure Fusion in Automotive Perception Sensor fusion is key to robust environment perception. Unfortunately, the throughput requirements of “datalevel” fusion are prohibitive, a problem exacerbated by higher-fidelity sensors: e.g. 16+bit HDR vs 10-bit video. Practical architectures instead rely on “late” fusion: Each sensor processes its data into low throughput semantic data before fusion. This limits the potential accuracy improvement. Instead, Imec/Ghent University proposes “cooperative” fusion, introduced at Autosens 2019 by prof. Philips. This retains the simplicity of late fusion but increases robustness/accuracy: sensors improve their decision using well-chosen feedback from other sensors. Unfortunately, increased-fidelity-sensors like HDR cameras cause increased memory and compukevontational requirements. We demonstrate that this problem can be avoided using content- and picturequality-preserving HDR-to-SDR conversion. This talk further covers real-world benefits of cooperative fusion, using Radar/Lidar/HDR-camera traffic data acquired in Belgium. These benefits are realized on many key performance indicators: vulnerable road user (VRU) detection/tracking accuracy and stability and processing-induced latency (track initialization delay).

14 September

10h30: Imaging and perception radar Chaired by: Wilfried Philips Scientific Lead Sensor Fusion imec/Ghent University

11h50: Marcus Dahlem, Program Manager – Optical 3D Sensing, IMEC

Photonic integrated circuits for solid-state LiDAR Research and development in LiDAR (Light Detection and Ranging) technology has significantly grown over the last years, with a strong demand from the automotive industry. Size, weight and cost are some of the major driving forces when exploring new LiDAR architectures. Emerging systems try to break away from mechanical scanning devices by using optical phased arrays (OPAs) or focal plane arrays. Furthermore, photonic integrated circuits (PICs) open the possibility of densely packing most of the required photonic building blocks on a single Si/SiN chip using CMOS-compatible foundry processes. In this talk, we summarize our recent work in PICbased components for developing solid-state LiDAR systems, with a focus on 2D beamsteering chips operating in NIR and SWIR wavelengths.

15 September

13h02: 140 GHz radar for in-cabin sensing: Li Huang, Business Team Lead, Connectivity Program Line, imec

By using higher frequencies (140 GHz) and digital modulation, radar performance can be brought to new levels, and to smaller form factors. Besides better radars, imec is taking the lead in event-based sensor fusion between passive and active sensing modalities, paving the way to highly energy efficient and fast perception for improved safety. In this talk, we will present opportunities and challenges related to these new radar and sensor fusion technologies. 

Event details

AutoSens has always been at the forefront of automotive imaging and perception insights and keeping a finger on the pulse of what’s hot and what’s not. This year, the agenda will focus on:

  • The changing face of the ADAS and automotive market
  • Developments in camera image quality
  • Leveraging RADAR, ultrasonic, LiDAR and thermal imaging
  • Approaches to sensor fusion in automotive perception
  • Architecture and data flow, AI and machine learning considerations for imaging
  • Simulation and robust validation of sensor systems, including digital twins and training data

Discover more