Various examples are directed to systems and methods for routing an autonomous vehicle. For example, a system may access temporal data comprising a first temporal data item. The first temporal data item may describe a first roadway condition, a first time, and a first location. The system may also access a routing graph that comprises a plurality of route components and determine that a first route component of the routing graph corresponds to the first location. The system may generate a constrained routing graph at least in part by modifying the first route component based at least in part on the first roadway condition. The system may additionally generate a route for an autonomous vehicle using the constrained routing graph; and cause the autonomous vehicle to begin traversing the route.

A field shape identification unit in a server control unit identifies, on the basis of position information about a work vehicle, the shape of a work field through which the work vehicle has traveled while working. A degree-of-overlap determination unit in the server control unit compares the shape of the work field identified by the field shape identification unit to the shape of a reference field and determines whether the degree of overlap between the work field and the reference field is greater than or equal to a prescribed degree. When the degree-of-overlap determination unit determines that the degree of overlap between the work field and the reference field is equal to or greater than a prescribed degree, an information management unit associates work-related information pertaining to the work in the work field with the reference field and manages the same.

A system for selection of physical asset transfer paths using mixed-payload aeronautic excursions includes a client-interface module operating on at least a server, the client-interface module, configured to receive an initial location, a terminal location, and a description of at least an element of non-sapient payload, a path-selection module operating on the at least a server configured to identify at least an aeronautic path from the initial location to the terminal location and a plurality of aeronautic excursions traversing the at least an aeronautic path and select an aeronautic excursion of the plurality of aeronautic excursions based on a plurality of excess non-sapient payload storage estimations corresponding the plurality of aeronautic excursions, and a capacity estimation artificial intelligence module operating on the at least a server, the capacity estimation artificial intelligence module designed and configured to generate the plurality of excess non-sapient payload storage estimations.

A traffic analysis system analyzes location data from a plurality of vehicles to determine journeys made by the vehicles. Vehicles may make one or more rest stops during a journey. The traffic analysis system compares rest periods to journey criteria to determine whether a rest period delineates the end of a journey, or whether a rest period is still within the journey. In this way, a plurality of trips can be chained together into a journey to provide more accurate analysis of traffic patterns.

Methods and systems for detecting when users deviate from a provided transportation route and for correcting the transportation route in response to such user deviations is presented. In one embodiment, a method is provided including detecting a changed condition for a transportation route between a first location and a second location. The transportation route may include multiple transportation segments. A first transportation segment designating a first modality may be identified, wherein the changed condition decreases a likelihood that vehicles associated with the first modality will be available to service the first transportation segment. In response, a second transportation segment designating a second modality different from the first modality is generated. The first transportation segment is then replaced with the second transportation segment in the transportation route.

Systems and methods are provided for ride order dispatching. Such method may comprise obtaining information on a location of a vehicle and a time to input into a trained neural network algorithm; and based on a policy generated from the trained neural network algorithm, obtaining action information for the vehicle, the action information comprising: staying at a current position of the vehicle, re-positioning the vehicle, or accepting a ride order.

The disclosed system may include a non-transitory memory and one or more hardware processors configured to execute instructions from the non-transitory memory to perform operations including determining online data and offline data from a mobile application, wherein the online data is determined based on the mobile application being online and the offline data is determined based on the mobile application being offline, determining travel distance data from a remote device associated with the vehicle, aggregating at least a portion of the online data, at least a portion of the offline data, and at least a portion of the travel distance data, generating data associated with the aggregation of the portion of the online data, the portion of the offline data, and the portion of the travel distance data, and causing the mobile application to display the generated data. Other methods, systems, and computer-readable media are disclosed.

Disclosed is a method for controlling an automated guided vehicle, comprising: if an item transportation request is received, planning a path of a target automated guided vehicle to obtain an initial path; and performing the following control steps on the basis of the initial path: taking at least part of the travel path from the initial path as the path to-be-traveled; controlling the target automated guided vehicle to travel according to the path to-be-traveled determining whether the end position of the path to-be-traveled is the target end position, and if the end position of the to-be-traveled path is not the target end position, re-planning the path of the target automated guided vehicle, and taking the updated path as the initial path to continue the control steps.

The present disclosure provides methods, devices and systems for route deviation quantification and vehicular route learning based thereon. In some examples, there is provided a method for route deviation quantification of a suggested route. The method comprises: obtaining a ground truth route based on a filtered trajectory, the filtered trajectory including an inferred location of origin and an inferred location of destination; obtaining a suggested route generated based on the inferred location of origin and the inferred location of destination; quantifying a deviation of the suggested route from the ground truth route by calculating an off course ratio based on a combined length of road segments in the suggested route that are matched to corresponding road segments in the ground truth route and a combined length of road segments in the ground truth route.

A controller includes a memory and a processor. The memory stores drop-off data regarding a first user who gets off a ride-sharing vehicle and pick-up data regarding a second user who gets on the ride-sharing vehicle. The processor is configured to execute vehicle control including at least one of drop-off of the first user and pick-up of the second user based on at least one of the drop-off data and the pick-up data. The vehicle control includes, executing at least one of first zone setting processing that is processing of setting a first zone where the drop-off is executed and second zone setting processing that is processing of setting a second zone where the pick-up is executed, and executing first zone resetting processing of resetting the first zone in a space not overlapping the second zone.