Abstract: Vehicles and related systems and methods are provided for predicting a future maneuver expected to be executed by a driver. One method involves determining a combined probability for a potential maneuver based on constituent probabilities corresponding to different vehicle state variables, and environmental conditions using one or more tuning parameters specific to the respective combination of maneuver and vehicle state variable, determining an adjusted probability for the potential maneuver based at least in part on the combined probability and one or more contextual state variables corresponding to a current operating context for the vehicle, adapted to driver behavior and driving style, identifying the potential maneuver as an expected maneuver to be executed by a driver of the vehicle based on the adjusted probability, and automatically initiating one or more actions in a manner that is influenced by the expected maneuver.

Abstract: A vehicle system includes a control module configured to receive data from a sensor indicative of a torque applied to the steering wheel, calculate a torque rate based on the applied torque, calculate a left evasive steering probability of the driver intending to steer the vehicle to the left and a right evasive steering probability of the driver intending to steer the vehicle to the right based on the torque, the torque rate, and a modeled relationship between the torque and the torque rate, compare the left evasive steering probability and the right evasive steering probability to determine a directional steering intent of the driver, and transmit a signal to a threat avoidance steering control module for controlling the vehicle. Other example vehicle systems and methods for predicting driver intent in evasive steering maneuvers are also disclosed.

Abstract: Vehicles and related systems and methods are provided for predicting a future maneuver expected to be executed by a driver. One method involves determining a combined probability for a potential maneuver based on constituent probabilities corresponding to different vehicle state variables, and environmental conditions using one or more tuning parameters specific to the respective combination of maneuver and vehicle state variable, determining an adjusted probability for the potential maneuver based at least in part on the combined probability and one or more contextual state variables corresponding to a current operating context for the vehicle, adapted to driver behavior and driving style, identifying the potential maneuver as an expected maneuver to be executed by a driver of the vehicle based on the adjusted probability, and automatically initiating one or more actions in a manner that is influenced by the expected maneuver.

Abstract: A system and method are provided for controlling a vehicle. In one embodiment, a system includes: a sensor system configured to generate sensor data sensed from an environment of the vehicle; and a control module configured to, by a processor, based on the sensor data, identify a gap in a lane line on a roadway in front of the vehicle, determine at least two points within the gap, determine a curve between the at least two points, compute a correlation measure based on the curve, generate lane stitching data based on data based on the curve and an evaluation of the correlation measure, and controlling one or more components of the vehicle based on the stitching data.

Abstract: A RLP system for a host vehicle includes a memory and levels. The memory stores a RLP algorithm, which is a multi-agent collaborative DQN with PER algorithm. A first level includes a data processing module that provides sensor data, object location data, and state information of the host vehicle and other vehicles. A second level includes a coordinate location module that, based on the sensor data, the object location data, the state information, and a refined policy provided by the third level, generates an updated policy and a set of future coordinate locations implemented via the first level. A third level includes evaluation and target neural networks and a processor that executes instructions of the RLP algorithm for collaborative action planning between the host and other vehicles based on outputs of the evaluation and target networks and to generate the refined policy based on reward values associated with events.