US 12,459,120 B2
Dynamic spatiotemporal beamforming self-diagonostic system
Jonathan Jenner Macoskey, Pittsburgh, PA (US); and Samarjit Das, Sewickley, PA (US)
Assigned to Robert Bosch GmbH, (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Dec. 31, 2020, as Appl. No. 17/139,355.
Prior Publication US 2022/0203536 A1, Jun. 30, 2022
Int. Cl. B25J 9/16 (2006.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06V 20/10 (2022.01)
CPC B25J 9/1674 (2013.01) [B25J 9/162 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06V 20/10 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method for self-diagnosing a data acquisition system for acquiring calibrated images of an area comprising:
collecting one or sound signals from at least a microphone array or hydrophone array;
by a controller:
(a) requesting the one or more sound signals, indicative of a measurement of a parameter, from a sensor associated with a position and direction of a mobile platform in the area;
(b) removing from the one or more sound signals, background noise associated with the mobile platform, thereby focusing on a measurement to a foreground signal, wherein the background noise is separated from the foreground signal that is of interest via a subspace approximation using singular value decomposition to acquire a high rank version of the signal, wherein the subspace approximation using the singular value decomposition is expressed by PBG=UrΣrVrT, where

OG Complex Work Unit Math
 S=diag(σ1, . . . , σn)∈Rr×r, σ1≥ . . . ≥σ1≥ . . . ≥σr≥0∪∈Rm×m, V∈Rn×n, m, n and r are positive integers;
(c) obtaining from the sensor a position and a direction of the mobile platform within the area;
storing the measurement, position and direction of the mobile platform within the area;
repeating the steps from (a) to (c);
assessing (or reading) a previous-in-time signal indicative of the stored a previous-in-time measurement of the parameter, obtained from the sensor associated with the position and direction of the mobile platform in the area, wherein previous-in-time background noise is separated from a previous-in-time foreground signal indicating movement of the mobile platform via subspace approximation using singular value decomposition; and
in response to a change detection indicating a difference between a spectrogram of the background noise and a previous-in-time spectrogram of the previous-in-time background noise exceeding a predetermined threshold at a predetermined frequency, outputting a status signal indicative of a change in operating characteristics of the mobile platform.