US 11,745,766 B2
Unseen environment classification
Gautham Sholingar, Sunnyvale, CA (US); Sowndarya Sundar, Mountain View, CA (US); Jinesh Jain, Pacifica, CA (US); and Shreyasha Paudel, Sunnyvale, CA (US)
Assigned to Ford Global Technologies, LLC, Dearborn, MI (US)
Filed by Ford Global Technologies, LLC, Dearborn, MI (US)
Filed on Jan. 26, 2021, as Appl. No. 17/158,088.
Prior Publication US 2022/0234617 A1, Jul. 28, 2022
Int. Cl. B60W 40/00 (2006.01); B60W 60/00 (2020.01); G06F 16/28 (2019.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); B60W 30/095 (2012.01); B60W 30/09 (2012.01); B60W 40/06 (2012.01); B60W 50/00 (2006.01)
CPC B60W 60/0015 (2020.02) [B60W 30/09 (2013.01); B60W 30/0956 (2013.01); B60W 40/06 (2013.01); B60W 50/0097 (2013.01); G06F 16/285 (2019.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); B60W 2420/42 (2013.01); B60W 2555/20 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising: a computer including a processor and a memory, the memory including instructions executable by the processor such that the processor is programmed to:
process vehicle sensor data with a deep neural network to generate a prediction indicative of one or more objects based on the vehicle sensor data and determine an object uncertainty corresponding to the prediction;
then, upon determining that the object uncertainty is greater than an uncertainty threshold:
segment the vehicle sensor data into a foreground portion and a background portion;
classify the foreground portion as including an unseen object class when a foreground epistemic uncertainty is greater than a foreground epistemic uncertainty threshold;
classify the background portion as including unseen background when a background epistemic uncertainty is greater than a background epistemic uncertainty threshold; and
transmit the data and a data classification to a server.