Amazon has filed a patent for a simulation system that generates radar data for autonomous vehicle simulations. The system uses a data store of real-world object radar data and attributes to construct radar data for simulations. During the simulation, the generated radar data is provided to a simulated radar sensor of a simulated vehicle. The system aims to improve the accuracy and realism of autonomous vehicle simulations. GlobalData’s report on Amazon gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Amazon, dynamic premium pricing was a key innovation area identified from patents. Amazon's grant share as of September 2023 was 81%. Grant share is based on the ratio of number of grants to total number of patents.

Simulation system for generating radar data for autonomous vehicles

Source: United States Patent and Trademark Office (USPTO). Credit: Amazon.com Inc

A recently filed patent (Publication Number: US20230311930A1) describes a system and method for simulating radar data in a vehicle operating in an environment. The system includes a radar point cloud data store, one or more processors, and computer-readable media storing instructions for performing various operations.

The system receives log data based on sensor data captured by the vehicle, including radar data associated with the environment. It determines attributes associated with an object represented in the log data and a radar point cloud associated with the object. The object entry, comprising the attributes and the radar point cloud, is stored in the radar point cloud data store.

In addition, the system receives simulated object data associated with a simulated object in a simulation. It determines a second set of attributes associated with the simulated object and compares them with the attributes of the object represented in the log data. Based on this comparison, the system uses the object entry for the simulation and renders the simulated object, including providing the radar point cloud as input to a simulated radar sensor.

The system also includes a radar point cloud data store that stores multiple object entries, each including attributes such as range, azimuth, yaw, doppler value, width, and height of the object.

The method described in the patent involves receiving log data based on sensor data captured by a vehicle in an environment, determining an object represented in the log data and an attribute associated with the object, and determining a set of radar points associated with the object. The method stores object simulation data, including the attribute and the radar points, in a data store.

The method further involves receiving simulation data representing a simulated environment, determining a simulated object within the simulated environment and a second attribute associated with the simulated object, and retrieving the object simulation data from the data store based on the attribute and the second attribute. The method retrieves the radar points and generates simulation radar data based on them, rendering the simulated object during the simulation by providing the simulation radar data as input to a simulated radar sensor.

Overall, this patent describes a system and method for simulating radar data in a vehicle operating in an environment, allowing for realistic simulations and analysis of radar-based systems.

To know more about GlobalData’s detailed insights on Amazon, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.