US 11,703,335 B2
Coordinating and learning maps dynamically
Randall J. St. Romain, Ann Arbor, MI (US); and Schuyler H. Cohen, Ann Arbor, MI (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Jun. 19, 2020, as Appl. No. 16/906,578.
Prior Publication US 2021/0396528 A1, Dec. 23, 2021
Int. Cl. G01C 21/32 (2006.01); G06F 16/29 (2019.01); G01C 21/34 (2006.01); G06N 20/00 (2019.01); G01C 21/36 (2006.01); G06F 16/23 (2019.01)
CPC G01C 21/32 (2013.01) [G01C 21/3453 (2013.01); G01C 21/3691 (2013.01); G06F 16/23 (2019.01); G06F 16/29 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for updating an in-vehicle map of a host vehicle, comprising:
a plurality of external sensors of the host vehicle configured to monitor activities of other vehicles in a surrounding environment;
a computing device having a receiver operatively connected to the first plurality of sensors, the computing device including processing circuitry configured to:
determine whether the activities of the other vehicles deviate from the map;
geo-fence a map region in which the activities of the other vehicles deviate from the map;
receive a data stream from the external sensors focused on the geo-fenced map region;
analyze patterns of behavior of the activities of the other vehicles from the data stream;
determine a confidence level of the behavior based on a number of the other vehicles exhibiting the behavior, wherein the confidence level is directly proportional to the number of the other vehicles that exhibit the behavior, and
determine whether to update a database of the in-vehicle map with the behavior.