Invention Grant
- Patent Title: Using data from a radar sensor for machine learning based perception
-
Application No.: US15792190Application Date: 2017-10-24
-
Publication No.: US10534071B2Publication Date: 2020-01-14
- Inventor: Bhavana Chakraborty , Berenike Beck
- Applicant: Robert Bosch GmbH
- Applicant Address: DE Stuttgart
- Assignee: Robert Bosch GmbH
- Current Assignee: Robert Bosch GmbH
- Current Assignee Address: DE Stuttgart
- Agency: Michael Best & Friedrich LLP
- Main IPC: G01S7/41
- IPC: G01S7/41 ; G01S13/58 ; G01S13/60 ; G01S13/93 ; G01S13/89

Abstract:
A system for providing a range speed response pattern to a learning system as an image. The system includes a radar sensor and an electronic controller. In one example, the electronic controller is configured to receive a radar signal, obtain a beat signal, apply a fast Fourier transform to the beat signal to generate a transform, apply a power spectral density periodogram to the beat signal to generate an estimate, and filter the transform with the estimate to generate a filtered transform. The electronic controller is further configured to store the filtered transform in a column of a matrix, apply the power spectral density periodogram to each row of the matrix, generate a range speed response pattern from the matrix, generate a signal to control the vehicle's motion based on the range speed response pattern, and control a steering apparatus, an engine, and/or a braking system of the vehicle.
Public/Granted literature
- US20190120936A1 USING DATA FROM A RADAR SENSOR FOR MACHINE LEARNING BASED PERCEPTION Public/Granted day:2019-04-25
Information query