Operation data from one or more vehicle subsystems are input to a vehicle dynamics model. Predicted operation data of the one or more vehicle subsystems are output from the vehicle dynamics model. The operation data and the predicted operation data are input to an optimization program that is programmed to output control directives for the one or more vehicle subsystems. One or more vehicle subsystems are operated according to the output control directives.

A driver command predictor includes a controller, multiple sensors, and a command prediction unit. The controller is configured to command an adjustment of multiple motion vectors of a vehicle relative to a roadway in response to multiple actual driver commands and multiple future driver commands. The actual driver commands are received at a current time. The future driver commands are received at multiple update times. The update times range from the current time to a future time. The sensors are configured to generate sensor data that determines multiple actual states of the vehicle in response to the motion vectors as commanded. The command prediction unit is configured to generate the future driver commands at the update times in response to a driver model. The driver model operates on the actual driver commands and the actual states to predict the future driver commands at the update times.

A driver command predictor includes a controller, multiple sensors, and a command prediction unit. The controller is configured to command an adjustment of multiple motion vectors of a vehicle relative to a roadway in response to multiple actual driver commands and multiple future driver commands. The actual driver commands are received at a current time. The future driver commands are received at multiple update times. The update times range from the current time to a future time. The sensors are configured to generate sensor data that determines multiple actual states of the vehicle in response to the motion vectors as commanded. The command prediction unit is configured to generate the future driver commands at the update times in response to a driver model. The driver model operates on the actual driver commands and the actual states to predict the future driver commands at the update times.

A system includes a powertrain controller operatively coupled with and configured to control operation of a powertrain of a vehicle and for bidirectional communication via a wireless communication path. An optimization engine is configured to determine optimized powertrain operation parameters for the powertrain controller and for bidirectional communication via a second communication path. A channel management engine is configured for bidirectional communication with the powertrain controller via the wireless communication path and for bidirectional communication with the optimization engine via the second communication path, the channel management engine configured to dynamically update a plurality of data channels including a first data channel storing a non-transitory dynamically-updated instance of powertrain operation data received from the powertrain controller, and a second data channel storing a non-transitory dynamically-updated instance of optimized powertrain operation parameters received from the optimization engine.

A system includes a powertrain controller operatively coupled with and configured to control operation of a powertrain of a vehicle and for bidirectional communication via a wireless communication path. An optimization engine is configured to determine optimized powertrain operation parameters for the powertrain controller and for bidirectional communication via a second communication path. A channel management engine is configured for bidirectional communication with the powertrain controller via the wireless communication path and for bidirectional communication with the optimization engine via the second communication path, the channel management engine configured to dynamically update a plurality of data channels including a first data channel storing a non-transitory dynamically-updated instance of powertrain operation data received from the powertrain controller, and a second data channel storing a non-transitory dynamically-updated instance of optimized powertrain operation parameters received from the optimization engine.

A method for scenario-based event triggers is described. The method includes generating, by a first machine-learning (ML) model, feature vectors encoding driving scenarios surrounding an ego vehicle. The method also includes detecting, by a second machine-learning (ML) model, a unique driving scenario outside of pre-programmed event triggers corresponding to one of the feature vectors encoding driving scenarios surrounding the ego vehicle. The method further includes triggering uploading of the unique driving scenario outside of pre-programmed event triggers to a central scenario-based event control server.

A method for scenario-based event triggers is described. The method includes generating, by a first machine-learning (ML) model, feature vectors encoding driving scenarios surrounding an ego vehicle. The method also includes detecting, by a second machine-learning (ML) model, a unique driving scenario outside of pre-programmed event triggers corresponding to one of the feature vectors encoding driving scenarios surrounding the ego vehicle. The method further includes triggering uploading of the unique driving scenario outside of pre-programmed event triggers to a central scenario-based event control server.

A method may include determining time-variable risk profiles for plural separate vehicle systems that are remotely controlled by operators that are located off-board the separate vehicle systems. The time-variable risk profiles represent one or more risks to travel of the separate vehicle systems. The method may include assigning the operators to remotely monitor or control the separate vehicle systems during the trips based on the time-variable risk profiles. The operator assigned changes with respect to time while the one or more separate vehicle systems is moving along one or more routes during the trip. A system may include one or more processors that may determine time-variable risk profiles for plural separate vehicle systems that are remotely controlled and assign the operators to remotely monitor or control the separate vehicle systems during the trips based on the time-variable risk profiles.

A method may include determining time-variable risk profiles for plural separate vehicle systems that are remotely controlled by operators that are located off-board the separate vehicle systems. The time-variable risk profiles represent one or more risks to travel of the separate vehicle systems. The method may include assigning the operators to remotely monitor or control the separate vehicle systems during the trips based on the time-variable risk profiles. The operator assigned changes with respect to time while the one or more separate vehicle systems is moving along one or more routes during the trip. A system may include one or more processors that may determine time-variable risk profiles for plural separate vehicle systems that are remotely controlled and assign the operators to remotely monitor or control the separate vehicle systems during the trips based on the time-variable risk profiles.

A method for combating a stop-and-go wave problem using deep reinforcement learning based autonomous vehicles includes selecting one of a plurality of deep reinforcement learning algorithms for training an autonomous vehicle and a reward function in a roundabout environment in which autonomous vehicles and non-autonomous vehicles are driving, determining a deep neural network architecture according to the selected deep reinforcement learning algorithm, learning a policy which enables the autonomous vehicle to drive at a closest velocity to a constant velocity based on state information including a velocity of the autonomous vehicle and a relative velocity and a relative position between the autonomous vehicle and an observable vehicle by the autonomous vehicle at a preset time interval and reward information, using the selected deep reinforcement learning algorithm, and driving the autonomous vehicle based on the learned policy to determine an action of the autonomous vehicle.