US 12,332,614 B2
Combining rule-based and learned sensor fusion for autonomous systems and applications
Hans Jonas Nilsson, Los Gatos, CA (US); Michael Cox, Menlo Park, CA (US); Sangmin Oh, San Jose, CA (US); Joachim Pehserl, Lynnwood, WA (US); and Aidin Ehsanibenafati, Santa Clara, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Mar. 18, 2022, as Appl. No. 17/698,695.
Claims priority of provisional application 63/163,675, filed on Mar. 19, 2021.
Prior Publication US 2022/0297706 A1, Sep. 22, 2022
Int. Cl. G05B 13/02 (2006.01); G01S 13/86 (2006.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01)
CPC G05B 13/027 (2013.01) [G01S 13/865 (2013.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); B60W 2556/35 (2020.02)] 33 Claims
OG exemplary drawing
 
1. One or more processors comprising:
processing circuitry to:
generate a first fused output by applying learned fusion to first data generated using a first sensor processing pipeline and second data generated using a second sensor processing pipeline;
generate a second fused output by applying rule-based fusion to the first data, the second data, and the first fused output; and
perform one or more operations based at least on the second fused output,
wherein the first fused output is capable of compliance with a first automotive integrity safety level (ASIL) and the second fused output is capable of compliance with a second ASIL level, the second ASIL level being a higher ASIL level than the first ASIL level.