Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

Systems, methods, and other embodiments for vehicle route scheduling and navigation with dynamic selection of turns across opposing traffic are presented herein. In one embodiment, a method includes during development of a vehicle route from an arrival link through a node of a graph representing a road network, determining, for a departure link, that a path of the vehicle from the arrival link to the departure link crosses oncoming traffic, and in response to determining that that the path of the vehicle crosses oncoming traffic, adding an additional delay for the departure link to a route objective function representing the vehicle route; selecting the route including the path that crosses oncoming traffic to be an optimum route between a first location and a second location; including the optimum route in the delivery schedule for the vehicle; and transmitting the delivery schedule for execution.

A system for instructing an Autonomous Vehicle (AV) to perform a minimal risk condition maneuver comprises a fleet of AVs and an oversight server. The oversight server receives macro information that applies to a plurality of AVs from the fleet. The oversight server generates a batch command based on the macro information. The batch command is associated with one or more conditions. The oversight server determines whether each AV meets the one or more conditions. If the oversight server determines that the AV meets the one or more conditions, the oversight server sends the batch command to the AV. The batch command includes instructions to perform a minimal risk condition maneuver.

Systems and methods are disclosed for generating a display of a navigation map. The system may comprise a historical data source device having, for example, a historical data source computer and a database storing historical data associated with one or more of vehicle accident data, traffic data, vehicle volume data, vehicle density data, road characteristic data, or weather data. The system may comprise a map data processing device having a map data processing computer and memory storing computer-executable instructions that, when executed by the map data processing computer, cause the map data processing device to, for example, determine, based on a location determining device, a location of a vehicle. The map data processing system may determine one or more historical factors based on the location of the vehicle. The map data processing system may receive, from the historical data source device and for the location, historical data associated with the one or more historical factors. Based on the location of the vehicle, one or more real time factors and real time data associated with the one or more real time factors may be calculated. The map data processing system may calculate, using the one or more historical factors and the one or more real time factors, a navigation score for each segment of a route from the location to a destination location. The map data processing system may determine one or more colors for each navigation score and/or generate a display of a navigation map comprising the one or more colors.

Methods and systems for autonomous and semi-autonomous vehicle control, routing, and automatic feature adjustment are disclosed. Sensors associated with autonomous operation features may be utilized to search an area for missing persons, stolen vehicles, or similar persons or items of interest. Sensor data associated with the features may be automatically collected and analyzed to passively search for missing persons or vehicles without vehicle operator involvement. Search criteria may be determined by a remote server and communicated to a plurality of vehicles within a search area. In response to which, sensor data may be collected and analyzed by the vehicles. When sensor data generated by a vehicle matches the search criteria, the vehicle may communicate the information to the remote server.

A system is disclosed for monitoring waste collected by a service vehicle. The system may include a lift actuator configured to cause lifting of the waste, a power takeoff driven by a powertrain of the service vehicle to power the lift actuator, and a sensor configured to generate a speed signal indicative of a speed of the powertrain. The system may also include an output device, and a controller in communication with the sensor and the output device. The controller may be configured to receive the speed signal from the sensor, determine an amount of waste lifted by the lift actuator based on the speed signal, and relay the amount of waste to the output device.

A control device in one aspect of the present disclosure includes a vehicle information acquisition unit, an obstacle information acquisition unit, and a sudden braking detection unit, and controls a warning information transmission unit to transmit, to an other vehicle, warning information including obstacle information when a sudden braking is performed by a subject vehicle. When receiving the warning information from the other vehicle, a target vehicle determination unit confirms that the other vehicle is a warning target vehicle, and a risk calculation unit calculates a collision risk of the subject vehicle to collide with an obstacle, and a collision avoidance unit performs a collision avoidance control according to the calculated collision risk.

A method of controlling movement of multi-vehicle includes acquiring a constraint condition under which vehicles move and a calculation cycle for calculating movement routes of the vehicles; acquiring a position of each vehicle; specifying a target position for each vehicle; calculating, based on the position of each vehicle, the target position, and the constraint condition, a movement route for prediction steps of each vehicle; determining, based on the movement routes of the vehicles, a driving condition of each vehicle from a current time to a unit time; and controlling movement of each vehicle. Calculating the movement route including performing optimization calculation based on an evaluation function, evaluation of which becomes higher as a deviation between the vehicle and the target position for each prediction step becomes smaller, and the constraint condition, to calculate the movement route.

A system for communicating fleet-specific features to one or more personal electronic devices includes one or more controllers in wireless communication with a centralized computer system including one or more databases for storing the fleet-specific features. The one or more controllers execute instructions to undergo a passive wireless interaction with the one or more personal electronic devices. The passive wireless interaction involves determining the one or more personal electronic devices are located within a predefined proximity around a vehicle without human interaction. In response to undergoing the passive wireless interaction, the one or more controllers transmit one or more fleet-specific features to the one or more personal electronic devices, wherein the one or more fleet-specific features are shared by a fleet of vehicles, where the fleet of vehicles include an immediate vehicle and a group of vehicles that share one or more common attributes.

A method of causing car sharing platform user to perform vehicle actions includes training a model by analyzing historical data; analyzing a first data set to determine vehicle requirements comprising respective actions that include respective action values; displaying the actions; receiving user acceptance of the actions; analyzing a second data set to identify changes to the requirements indicating completed actions; and releasing the respective generated action value for the completed actions. A non-transitory computer readable medium containing program instructions that when executed, cause a computer system to: train a model by analyzing historical data; analyze a first data set to determine vehicle requirements comprising respective actions that include respective action values; display the actions; receive user acceptance of the actions; analyze a second data set to identify changes to the requirements indicating completed actions; and release the respective generated action value for the completed actions.