US 12,277,861 B2
Smart notifications for vehicle parking garage maneuvers
Bo Yu, Troy, MI (US); Brent Navin Roger Bacchus, Sterling Heights, MI (US); Jiabin Shen, Burnaby (CA); Yuan Zhang, Shanghai (CN); and Wenyuan Qi, Shanghai (CN)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Mar. 24, 2023, as Appl. No. 18/189,414.
Claims priority of application No. 202310273341.5 (CN), filed on Mar. 20, 2023.
Prior Publication US 2024/0321106 A1, Sep. 26, 2024
Int. Cl. G08G 1/16 (2006.01); G08G 1/01 (2006.01); G01C 21/20 (2006.01)
CPC G08G 1/167 (2013.01) [G08G 1/0129 (2013.01); G01C 21/206 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating notifications, comprising:
receiving historical vehicle-trajectory data, wherein the historical vehicle-trajectory data is indicative of a plurality of historical trajectories of a vehicle along a structure, each of the plurality of historical trajectories avoids stationary objects in the structure, and the historical vehicle-trajectory data includes a location and a heading of the vehicle for each of the plurality of historical trajectories along the structure;
clustering the plurality of historical trajectories of the vehicle along the structure by types of maneuvers to generate a plurality of trajectory clusters;
creating a probability distribution bitmap using the plurality of trajectory clusters, wherein the probability distribution bitmap is representative of the plurality of historical trajectories along the structure;
creating a topographic map based on the probability distribution bitmap, wherein the topographic map includes a notification zone and a no-notification zone, the no-notification zone has a first probability density, the notification zone has a second probability density, the first probability density is greater than the second probability density, the second probability density is equal to or less than a predetermined threshold, and the first probability density is greater than the predetermined threshold;
receiving, in real time, sensor data from a plurality of sensors of the vehicle;
predicting a future trajectory of the vehicle using the sensor data;
determining whether the future trajectory of the vehicle inside the structure crosses into the notification zone of the topographic map; and
in response to determining that the future trajectory of the vehicle crosses into the notification zone of the topographic map, generating a notification indicative that the vehicle will cross into the notification zone.