US 12,452,957 B2
Closed loop tasking and control of heterogeneous sensor networks
Denis Garagic, Salt Lake City, UT (US); Robert Ravier, Salt Lake City, UT (US); Travis Galoppo, Princeton, NC (US); Rex Jameson, Salt Lake City, UT (US); and Fraser M. Smith, Salt Lake City, UT (US)
Assigned to Sarcos Corp., Salt Lake City, UT (US)
Filed by Sarcos Corp., Salt Lake City, UT (US)
Filed on Oct. 4, 2024, as Appl. No. 18/907,392.
Claims priority of provisional application 63/588,675, filed on Oct. 6, 2023.
Prior Publication US 2025/0119982 A1, Apr. 10, 2025
Int. Cl. H04W 84/18 (2009.01); G06N 3/092 (2023.01); G06N 20/00 (2019.01); H04W 4/02 (2018.01); H04W 4/38 (2018.01); G06V 20/17 (2022.01)
CPC H04W 84/18 (2013.01) [G06N 20/00 (2019.01); H04W 4/02 (2013.01); H04W 4/38 (2018.02); G06N 3/092 (2023.01); G06V 20/17 (2022.01)] 33 Claims
OG exemplary drawing
 
1. A method for controlling a sensor node network, comprising:
obtaining sensor data from a plurality of sensors which include a plurality of sensor modalities, wherein the sensors are associated with sensor nodes;
combining the sensor data in a joint feature space that represents multimodal input from the plurality of sensor modalities;
detecting features from the sensor data using the joint feature space;
identifying neighboring sensor nodes to receive the features;
sending the features to other sensor nodes in the sensor node network; and
applying low-rank tensor regression to sensor data from separate sensor data modalities to enable discovery of cross-modality contextual correlations that are features in the sensor data from the plurality of sensors.