Abstract: A control signal related to a road segment is received by a processor of a vehicle from a remote server. Using at least a portion of the control signal, a cruise control parameter for controlling the vehicle is obtained. Responsive to determining that a cruise control module of the vehicle is enabled, the cruise control module is configured to use the cruise control parameter. The cruise control module operates to maintain the cruise control parameter for the vehicle.

Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.

Abstract: A server accesses vehicle data from each connected vehicle (CV) of a subset of a plurality of CVs on a roadway portion, the vehicle data comprising at least one of: a position, a velocity, or a headway. The server generates, based on the accessed vehicle data, a long-term shared world model. The server generates, using the long-term shared world model, a data structure representing predicted future velocities on the roadway portion by position and time by applying a traffic flow model to the long-term shared world model. The server transmits, to a connected autonomous vehicle (CAV), a control signal for controlling operation of the CAV based on the generated data structure.

Abstract: A server accesses vehicle data from each connected vehicle (CV) of a subset of a plurality of CVs on a roadway portion, the vehicle data comprising at least one of: a position, a velocity, or a headway. The server generates, based on the accessed vehicle data, a long-term shared world model. The server generates, using the long-term shared world model, a data structure representing predicted future velocities on the roadway portion by position and time by applying a traffic flow model to the long-term shared world model. The server transmits, to a connected autonomous vehicle (CAV), a control signal for controlling operation of the CAV based on the generated data structure.

Abstract: A server accesses vehicle data from each connected vehicle (CV) of a subset of a plurality of CVs on a roadway portion, the vehicle data comprising at least one of: a position, a velocity, or a headway. The server generates, based on the accessed vehicle data, a long-term shared world model. The server generates, using the long-term shared world model, a data structure representing predicted future velocities on the roadway portion by position and time by applying a traffic flow model to the long-term shared world model. The server transmits, to a connected autonomous vehicle (CAV), a control signal for controlling operation of the CAV based on the generated data structure.

Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.

Abstract: An intersection collision avoidance system determines, for an ego vehicle, a direction indicated by its turn signal, its destination setting, or both, generates, where the direction is determined, a possible intended path relative to an intersection using a high-definition (HD) map and the direction, and generates, where the destination setting is determined, a possible intended path for using the HD map and the destination setting. Where the direction and the destination setting are both determined, the direction indicated by the turn signal is compared to the possible intended path generated using the destination setting, and one of the possible intended paths is selected based on the comparison. The system transmits, to a conflict detection module, a set of drive goals for the ego vehicle relative to the intersection that conforms to the intended path. The module can determine a possible collision with another road user using the drive goals.

Abstract: Intersection collision avoidance may use a cellular transceiver for a cellular network and a processor located at a cellular access point for multi-access edge computing. The processor includes a shared world model and a conflict detection module. The shared world model is configured to receive, by the cellular transceiver, signals relating to at least two road users in proximity to an intersection within a vehicle transportation network, wherein the at least two road users include an ego vehicle, and the signals conform to a standards-based communication protocol. The conflict detection module is configured to receive object information from the shared world model, determine a potential future collision between the ego vehicle and an other road user of the at least two road users, and transmit a notification of the potential future collision to the ego vehicle over the cellular network.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with the motion prediction and operation of a device including a vehicle are provided. For example, a vehicle computing system can access state data including information associated with locations and characteristics of objects over a plurality of time intervals. Trajectories of the objects at subsequent time intervals following the plurality of time intervals can be determined based on the state data and a machine-learned tracking and kinematics model. The trajectories of the objects can include predicted locations of the objects at subsequent time intervals that follow the plurality of time intervals. Further, the predicted locations of the objects can be based on physical constraints of the objects. Furthermore, indications, which can include visual indications, can be generated based on the predicted locations of the objects at the subsequent time intervals.

Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.

Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.

Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.

Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.

Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with the motion prediction and operation of a device including a vehicle are provided. For example, a vehicle computing system can access state data including information associated with locations and characteristics of objects over a plurality of time intervals. Trajectories of the objects at subsequent time intervals following the plurality of time intervals can be determined based on the state data and a machine-learned tracking and kinematics model. The trajectories of the objects can include predicted locations of the objects at subsequent time intervals that follow the plurality of time intervals. Further, the predicted locations of the objects can be based on physical constraints of the objects. Furthermore, indications, which can include visual indications, can be generated based on the predicted locations of the objects at the subsequent time intervals.

Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.