A method of improving a merging efficiency of an ego vehicle is described. The method includes determining one or more merge gaps between vehicles in a target lane of a multilane highway. The method also includes computing an exposure time in which the ego vehicle is specified to merge into the one or more merge gaps. The method further includes selecting a merge gap between a first vehicle and a second vehicle in the target lane of the multilane highway having a maximum exposure time.

An operation device for an autonomous vehicle includes a touch panel configured to display at least one of a start button and a deceleration button, and a notification button on the same screen. The autonomous vehicle is autonomously drivable. The start button is a button for starting driving of the autonomous vehicle in an autonomous drive mode. The deceleration button is a button for decelerating the autonomous vehicle during the autonomous drive mode. The notification button is a button for performing notification to an outside of the autonomous vehicle.

A method for replacing a first module (30, 40) of a vehicle (1) with a new module (30, 30′, 40). The vehicle (1) includes: at least one drive module (30); and at least one functional module (40). The vehicle (1) has a unique vehicle identity. The method includes: setting (s101) the vehicle (1) into a maintenance mode indicating that the vehicle (1) is not available for operation; and preparing (s102) the vehicle (1) for physical disconnection of the first module (30, 40); when the first module (30, 40) has been physically disconnected from the vehicle (1) and the new module (30, 30′, 40) has been physically connected to the vehicle (1): establishing (s103) an electrical connection between the new module (30, 30′, 40) and the vehicle (1); assigning (s104) the new module (30, 30′, 40) the unique vehicle identity of the vehicle (1); setting (s105) the vehicle (1) into an operational mode; and verifying s106) the electrical connection of the new module (30, 30′, 40).

A computer-implemented method for providing a digital road map for testing an at least partially automated vehicle system. the method includes: accessing a database in which are stored permissible characteristics of the road properties for a multitude of road properties; creating at least one road map section by one of the possible characteristics being selected for the road map section for the first of the multitude of road properties, in each particular case in automated fashion from the database; providing the digital road map, the digital road map including the at least one road map section.

Various technologies described herein pertain to controlling an autonomous vehicle to provide indicators to distinguish the autonomous vehicle from other autonomous vehicles in a fleet. The autonomous vehicle includes a vehicle propulsion system, a braking system, a notification system, and a computing system. The notification system outputs an indicator that is perceivable external to the autonomous vehicle. The computing system receives data specifying an identity of a passenger to be picked up by the autonomous vehicle. Moreover, the computing system controls at least one of the vehicle propulsion system or the braking system to stop the autonomous vehicle for passenger pickup. Further, the computing system controls the notification system to output the indicator; a characteristic of the indicator outputted by the notification system is controlled based on the identity of the passenger to be picked up and whether the autonomous vehicle is stopped for passenger pickup.

A method for assisting in turning a vehicle, the method may include detecting or estimating that the vehicle is about to turn to a certain direction or is turning to the certain direction; sensing a relevant portion of an environment of the vehicle to provide sensed information, wherein the relevant portion of the environment is positioned at a side of the vehicle that corresponds with the certain direction; applying an artificial intelligence process on the sensed information to (i) detect objects within the relevant portion of the environment and (ii) estimate expected movement patterns of the objects within a time frame that ends with an expected completion of the turn of the vehicle; determining, given an expected trajectory of the vehicle during the turn and the expected movement patterns of the objects, whether at least one of the objects is expected to cross the trajectory of the vehicle during the turn; and responding to an outcome of the determining.

An autonomous vehicle (AV) maintenance system engages a user of an AV to assist in maintenance tasks. A sensor interface receives data captured by a sensor of the AV. An issue detector processes the sensor data to detect an issue in the AV. A user interface module instructs a user to perform a maintenance task addressing the detected issue. A verification module verifies that the user successfully completed the maintenance task.

In a method for moving a vehicle out of a parking area, the vehicle obtains map information of the parking area and determines a current parking space of the vehicle and an exit location of the parking area. The vehicle determines a plurality of target departure routes from the current parking space to the exit location, and identifies blocking vehicles on the target departure routes that blocks it from reaching the exit. The vehicle estimates the preferability of each of the target departure routes based on a number of blocking vehicles on the target departure route and a difficulty level of removing the blocking vehicles from the target departure route. The vehicle then selects from the target departure routes a preferred departure route, and transmits requests to remove the blocking vehicles off the preferred departure route.

A parking support device configured to support an automatic valet parking of a vehicle includes: an abnormality determiner configured to determine a presence or absence of an abnormality in an automatically driven vehicle when the automatically driven vehicle moves in a parking facility by automatic driving; and a notification instructor configured to issue, when determining an abnormality, a notification instruction for a portable terminal device held by a user of the automatically driven vehicle, notifying contents including (i) collection information indicating a collection position where the user should collect the automatically driven vehicle, and (ii) prompter information prompting that the user should go to the collection position.

Systems and methods automate the design and execution of randomized experiments. Portions of a field are planted using an agricultural vehicle configured to randomly vary planting parameters when planting a portion of the field. A resulting crop outcome across each portion or sub-portion of the field is observed. A training set of data is generated that includes the varied planting parameters and the associated crop outcomes for each portion of the field. A machine-learned model is trained using the training set of data and is configured to predict a crop outcome for a portion of the field based on historical and forecast conditions and a set of planting parameters applied to a portion of the field. For subsequent iterations, for a target portion of the field, the machine-learned model can be applied to identify a set of planting parameters for planting the target portion of the field to optimize a desired crop outcome.