LogicTronix is offering ADAS solutions for Automotive Manufacturers, OEM/ODM vendors. Our ADAS Solution is based on Xilinx MPSoC FPGA Platform, Xilinx MPSoC is power efficient and high performing multi-processing system on chip device or heterogenous platform. This MPSoC platform is best suited for sensor fusion and machine learning acceleration. Single device or platform is capable to process LIDAR, Cameras, RADAR and UltraSound sensors and perform Machine Learning Workload over the fused sensor information.
Feature of LogicTronix ADAS Solution
- Offering Sensor Fusion Capability : using LIDAR, GMSL/FPD Link Camera and Ultrasound Sensors
- Machine Learning Capability : performing the Machine learning algorithms for feature extraction and processing streams. We implement LIDAR based Point Cloud 3D Detection (Point Pillar) ML model, Object (Vehicle, Pedestrian, animal) detection, recognition ML model, Lane detection/tracking algorithm.
- Offering parking aid feature with 8 number of Automotive grade Ultrasound sensors
- Collision Avoidance system and early warning using RADAR (upcoming feature).
- Offering feature towards ADAS Level 2 functionality
Watch LogicTronix ADAS Webinar [May 9th 2022]
LogicTronix ADAS 2.0 (Coming Soon)
LIDAR Point Cloud 3D detection Demo:
LogicTronix ADAS 1.0 [Brief]
In MPSoC we are offering ADAS Sensor Fusion (Computer Vision+ LIDAR + UltraSound) and Machine Learning acceleration over those sensors input.
The most suitable interface for ADAS solution are GMSL and FPD Link, our ADAS solution takes the GMSL 2 Camera link interface with more than 4 Camera and those camera are pre-processed, here is pre-processing algorithms we performed:
And pre-processed stream is passed to Machine Learning Pipeline inside MPSoC FPGA.
Reference Tutorials by LogicTronix: ADAS [Automotive] Solutions
- ADAS Reference Design with Xilinx MPSoC FPGA and AI/ML – by LogicTronix [LRFD-031]: PDF Link
- ADAS tutorial at Hackster: Link
For more information about our ADAS Solutions and upcoming features on ADAS, please write us at: firstname.lastname@example.org.