The RS-Lidar-M1. (Photo: Robosense)
RoboSense is offering the solid-state lidar RS-LiDAR-M1Simple (Simple Sensor Version), which is less than half the size of the previous version at 4.3 x 1.9 x 4.7 inches (110 x 50 x 120 millimeters).
It is equipped with enhanced hardware performance virtually equal to the serial production version provided to OEMs. The main body design of this automotive-grade solid-state lidar is finalized and ready for shipment.
The RS-LiDAR-M1Smart main body is embedded with an artificial intelligence (AI) perception algorithm that takes advantage of lidar’s potential to transform conventional 3D lidar sensors to a full data analysis and comprehension system, outputting semantic-level structured environment information in real time to be used directly for autonomous vehicle decision making.
The RS-LiDAR-M1 family has the performance advantages of traditional mechanical lidar, simultaneously taking into consideration requirements for the mass production of vehicles.
The RS-LiDAR-M1Smart Features
- Adapts to complex traffic conditions.
- Supports multiple driving scenarios.
- Supports dense traffic flow, such as mixing pedestrians and vehicles in intersections during peak hours.
- Comprehensive perception of a wide range of dynamic, static and background objects.
- Achieves semantic-level prediction for 3D point clouds.
- Handles the challenges caused by two-wheel vehicles (motorcycles, bicycles, etc.) and pedestrians who do not follow traffic rules.
- Over-segmentation and under-segmentation are fixed based on the clustering algorithm. The robustness against sparse point clouds ensures the integrity of object detection.
- Outputs two redundant channels of data: the original point cloud and the object list. The two channels of data are redundant to provide vehicles with a wide range of sensing results, including dynamic and static and inside and outside the road.