Velodyne Lidar Usa, Inc.

Vishal Jain

David S Hall

Mathew Noel Rekow

Anand Gopalan

Deepak Guntur Ranganath

A lidar method and system for training and using a machine learning model are disclosed. An example method includes: obtaining a map of a background scene, the map including three-dimensional (3D) point cloud data; obtaining at least one point cloud representation of at least one foreground object, the at least one point cloud representation including 3D point cloud data, wherein one or more lidar sensors were used to generate the 3D point cloud data for the map and the at least one point cloud representation; generating a lidar scene by placing the at least one point cloud representation within the map; and training the machine learning model using the generated lidar scene. The model can be used to identify objects and control a vehicle.

Lidar scene generation for training machine learning models

The present disclosure relates generally to systems and methods for generating, processing and correlating data from multiple sensors in an autonomous navigation system, and more particularly to the utilization of configurable and dynamic sensor modules within light detection and ranging systems that enable an improved correlation between sensor data as well as configurability and responsiveness of the system to its surrounding environment.

Growing community of inventors

Walnut Creek, CA, United States of America

Vishal Jain