AEye fuses LiDAR and camera for low-cost, high-performance AV sensing
Autonomous Vehicle Technology announces 2019 ACES Award Winner in Autonomy | Sensors
In late 2017, AEye introduced a form of intelligent data collection it calls iDAR (Intelligent Detection and Ranging), which fuses solid-state agile LiDAR with a low-light HD camera, then integrates artificial intelligence to bring intelligence to the sensor layer. The company says it solves the challenges that current and classic LiDAR sensors cannot: the lengthy processing time and massive computing power required to collect and assemble data sets.
The solution uses a distributed architecture and edge processing to dynamically track targets and objects of interest while assessing general surroundings. Its software-configurable hardware enables vehicle control system software to selectively customize data collection in real time, while edge processing reduces control loop latency. By combining software extensibility, artificial intelligence, and smart agile sensors, iDAR is able to capture more intelligent information with less data for optimal performance and safety.
In Spring 2018, the company introduced an enhancement called Dynamic Vixels, a new sensor data type that combines pixels from 2D cameras with voxels from LiDAR, to enable iDAR to target and identify objects within a scene a claimed 10-20x more accurately than LiDAR-only products. The platform can extract value from orthogonal datasets and allow other sensors to be seamlessly integrated to provide a complete artificial-perception system. AEye says its iDAR-powered AE100 can interrogate 100% of a scene, while typical fixed-pattern LiDAR systems are only capable of interrogating 6% of any scene due to vertical gaps inherent in raster or spinning systems.
Click to view AVT’s 2019 ACES Award Winners best in class of