A computing system can be configured to generate, for an autonomous vehicle, a route through a transportation network comprising a plurality of segments. The method can include receiving sets of agent attention data from additional autonomous vehicles that are respectively currently located at one or more other segments of the transportation network. The method can include inputting the sets of agent attention data into a value iteration graph neural network that comprises a plurality of nodes that respectively correspond to the plurality of segments of the transportation network. The method can include receiving node values respectively for the segments as an output of the value iteration graph neural network. The method can include selecting a next segment to include in the route for the autonomous vehicle based at least in part on the node values.

A method and to a device for controlling an autonomously driving passenger transport vehicle. The driving behavior of the passenger transport vehicle is adapted to an ascertained passenger situation. When the vehicle is empty, driving may be rather aggressive, whereas in the case of there being occupants in the vehicle, more attention may be paid to their comfort and safety.

Various technologies described herein pertain to routing an autonomous vehicle based upon risk of takeover of the autonomous vehicle by a human operator. A computing system receives an origin location and a destination location of the autonomous vehicle. The computing system identifies a route for the autonomous vehicle to follow from the origin location to the destination location based upon output of a computer-implemented model. The computer-implemented model is generated based upon labeled data indicative of instances in which autonomous vehicles are observed to transition from operating autonomously to operating based upon conduction by human operators while the autonomous vehicles are executing predefined maneuvers. The computer-implemented model takes, as input, an indication of a maneuver in the predefined maneuvers that is performed by the autonomous vehicle when the autonomous vehicle follows a candidate route. The autonomous vehicle then follows the route from the origin location to the destination location.

System, method and product for vehicle navigation. A method comprising obtaining a location of a vehicle and obtaining a data about the passenger in the vehicle. Based on the data, a constraint on a driving route of the vehicle is determined. The constraint is characterized in extending the driving route so as to extend a driving time to the destination to be longer than a minimal driving time from the location to the destination. A driving plan is generated based on the constraint, wherein the driving plan defining a route from the location to the destination, whereby the vehicle can be driven according to the driving plan.

A boarding-alighting position determination method determines a boarding position and an alighting position in a vehicle dispatch system that dispatches a vehicle in response to a vehicle dispatch request. A plurality of boarding position candidates and a plurality of alighting position candidates are calculated around a geographical point from which the vehicle dispatch request was transmitted. A vehicle position is detected when the vehicle dispatch request was transmitted. For each boarding position candidate, a travel route is calculated from the vehicle position at a time of the vehicle dispatch request to at least one of the alighting position candidates via the boarding position candidate. A travel time is calculated for the vehicle to travel the travel route calculated for each of the boarding position candidates. A selected boarding position is determined from among the boarding position candidates based on the traveling time for each boarding position candidate.

An autonomous driving system controls autonomous driving of a vehicle and calculates an interest level of a driver of the vehicle for the autonomous driving. In a driver-oriented mode, the autonomous driving system gives priority to at least one of setting by the driver, will of the driver, and ride quality. In a performance-oriented mode, the autonomous driving system gives priority to at least one of increase in a safety margin, reduction in a time to arrive at a destination, improvement in fuel economy, improvement in motion performance, and reduction in a frequency of notification to the driver. The autonomous driving system controls the autonomous driving in the driver-oriented mode in a case of a normal state, and controls the autonomous driving in the performance-oriented mode in a case of a low interest state where the interest level is lower than the normal state.

The present disclosure relates to a computer-implemented method for calculating a trajectory of a mobile platform. The method calculates an exact or approximate solution of an optimization problem, which minimizes the travel time from a predetermined starting state to a predetermined end state, wherein the jerk of the mobile platform is restricted in absolute value to a maximum jerk and wherein the acceleration of the mobile platform is restricted, wherein the limit of the acceleration can be dependent on the velocity of the mobile platform.

A control device for an automated driving vehicle has a first automated driving mode in which the automated driving vehicle, receiving a permission notice from an operations management controller, travels, according to automatic operation, along a controlled route managed by the operations management controller, in accordance with a traveling schedule provided from the operations management controller; and a second automated driving mode in which the automated driving vehicle travels, without a permission notice from the operations management controller, along a non-controlled route that is not managed by the operations management controller, according to automatic operation. The first automated driving mode and the second automated driving mode are switchable.

A method for using an autonomous vehicle includes receiving one or more user preferences for use of the autonomous vehicle. A destination is received for a trip using the autonomous vehicle. An arrival time is received for when the trip needs to be completed. A determination is made as to whether the user preferences includes a preference for physical activity for the trip. One or more routes are provided for the trip to the destination that permits the trip to be completed by the arrival time and that implements at least one of the user preferences. At least one of the routes comprises a hybrid route including one segment in which a physical activity selected by the user is suggested for traversing a distance of the one segment and another segment using the autonomous vehicle.

A path providing device is configured to provide path information to a vehicle. The path providing device includes a memory configured to store information used for estimating or updating an optimal path, and the memory includes a plurality of memories configured to store the information used for estimating or updating the optimal path in different storage spaces based on types of information to be stored.