Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining routing using reinforcement learning (RL) are provided. One of the methods includes: initializing a state of an RL model based on a routing solution, wherein the RL model comprises a plurality of improvement actions for applying to the state; applying one or more of the plurality of improvement actions to the state to obtain updated routing solutions until a predetermined condition is satisfied; applying a perturbation action to obtain a perturbed routing solution and feeding the perturbed routing solution back to the RL model for the RL model to perform the applying one or more of the plurality of improvement actions according to the policy; and determining a routing solution with a minimum cost from the updated routing solutions.

Abstract: A tracking server receives GPS data from a location tracking device located in a vehicle. The GPS data describes a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The tracking server identifies noisy GPS data included in the received GPS data and revises a portion of path corresponding to the noisy GPS data. The tracking server may update a map database to include one or more road segments associated with the revised portion of the path. Furthermore, the tracking server may calculate a fare for the trip based on the revised path.

Abstract: A map server receives geographic points from a location tracking device located in a vehicle. The received geographic points describe a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The map server identifies candidate geographic points for each received geographic point where each candidate geographic point is associated with a location on a known roadway. The map server determines a graph of the candidate geographic points and identifies different sub-graphs from the graph. The map server iteratively evaluates the sub-graphs to determine a shortest path from the starting location to the destination location without evaluating all the edges in the sub-graphs.

Abstract: A map server receives geographic points from a location tracking device located in a vehicle. The received geographic points describe a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The map server identifies candidate geographic points for each received geographic point where each candidate geographic point is associated with a location on a known roadway. The map server determines a graph of the candidate geographic points and identifies different sub-graphs from the graph. The map server iteratively evaluates the sub-graphs to determine a shortest path from the starting location to the destination location without evaluating all the edges in the sub-graphs.

Abstract: A tracking server receives GPS data from a location tracking device located in a vehicle. The GPS data describes a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The tracking server identifies noisy GPS data included in the received GPS data and revises a portion of path corresponding to the noisy GPS data. The tracking server may update a map database to include one or more road segments associated with the revised portion of the path. Furthermore, the tracking server may calculate a fare for the trip based on the revised path.

Abstract: A map server receives geographic points from a location tracking device located in a vehicle. The received geographic points describe a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The map server identifies candidate geographic points for each received geographic point where each candidate geographic point is associated with a location on a known roadway. The map server determines a graph of the candidate geographic points and identifies different sub-graphs from the graph. The map server iteratively evaluates the sub-graphs to determine a shortest path from the starting location to the destination location without evaluating all the edges in the sub-graphs.

Abstract: A tracking server receives GPS data from a location tracking device located in a vehicle. The GPS data describes a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The tracking server identifies noisy GPS data included in the received GPS data and revises a portion of path corresponding to the noisy GPS data. The tracking server may update a map database to include one or more road segments associated with the revised portion of the path. Furthermore, the tracking server may calculate a fare for the trip based on the revised path.

Abstract: A tracking server receives GPS data from a location tracking device located in a vehicle. The GPS data describes a path that is representative of a pathway of the vehicle used to complete a trip from a starting location to a destination location. The tracking server identifies noisy GPS data included in the received GPS data and revises a portion of path corresponding to the noisy GPS data. The tracking server may update a map database to include one or more road segments associated with the revised portion of the path. Furthermore, the tracking server may calculate a fare for the trip based on the revised path.