Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for payment cards, driver licenses, or other character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: Examples disclosed herein involve a computing system configured to (i) obtain (a) a first set of sensor data captured by a first sensor system of a first vehicle that indicates the first vehicle's movement and location with a first degree of accuracy and (b) a second set of sensor data captured by a second sensor system of a second vehicle that indicates the second vehicle's movement and location with a second degree of accuracy that differs from the first degree of accuracy, (ii) based on the first set of sensor data, derive a first trajectory for the first vehicle that is defined in terms of a source-agnostic coordinate frame, (iii) based on the second set of sensor data, derive a second trajectory for the second vehicle that is defined in terms of the source-agnostic coordinate frame, and (iv) store the first and second trajectories in a database of source-agnostic trajectories.