A driving assist device includes a driving assist controller. The driving assist controller includes an oncoming vehicle detection unit, a prediction determination unit, a predicted travel region setting unit and a stop controller. The oncoming vehicle detection unit is configured to, when a vehicle enters an intersection, determine whether an oncoming vehicle going to enter the intersection is present. The prediction determination unit is configured to, when the oncoming vehicle detection unit determines that the oncoming vehicle is going to enter the intersection, determine whether a course of the oncoming vehicle is predictable based on vehicle behavior of the oncoming vehicle. The predicted travel region setting unit is configured to set a predicted travel region of the oncoming vehicle based on the vehicle behavior. The stopping controller is configured to cause the vehicle to stop outside of the predicted travel region set by the predicted travel region setting unit.

The control device, which operates due to a processor executing an object-oriented program, backs-up, to a storing section, respective first combinations of elements of a first object in which class structure relating to an application program is defined, and respective second combinations of elements of a second object in which class structure relating to a storage region used by an application program is defined. In a case in which generation of an object is necessary when the program is started, for the first object, the control device reads-out the respective first combinations from the storing section and generates the first object, and, for the second object, the control device reads-out the respective second combinations from the storing section and generates the second object.

The control device, which operates due to a processor executing an object-oriented program, backs-up, to a storing section, respective first combinations of elements of a first object in which class structure relating to an application program is defined, and respective second combinations of elements of a second object in which class structure relating to a storage region used by an application program is defined. In a case in which generation of an object is necessary when the program is started, for the first object, the control device reads-out the respective first combinations from the storing section and generates the first object, and, for the second object, the control device reads-out the respective second combinations from the storing section and generates the second object.

Techniques for improving the performance of an autonomous vehicle (AV) are described herein. A system can determine a plan for the AV in a driving scenario that optimizes an initial cost function of a control algorithm of the AV. The system can obtain data describing an observed human driving path in the driving scenario. Additionally, the system can determine for each cost dimension in the plurality of cost dimensions, a quantity that compares the estimated cost to the observed cost of the observed human driving path. Moreover, the system can determine a function of a sum of the quantities determined for each cost dimension in the plurality of cost dimensions. Subsequently, the system can use an optimization algorithm to adjust one or more weights of the plurality of weights applied to the plurality of cost dimensions to optimize the function of the sum of the quantities.

Techniques for improving the performance of an autonomous vehicle (AV) are described herein. A system can determine a plan for the AV in a driving scenario that optimizes an initial cost function of a control algorithm of the AV. The system can obtain data describing an observed human driving path in the driving scenario. Additionally, the system can determine for each cost dimension in the plurality of cost dimensions, a quantity that compares the estimated cost to the observed cost of the observed human driving path. Moreover, the system can determine a function of a sum of the quantities determined for each cost dimension in the plurality of cost dimensions. Subsequently, the system can use an optimization algorithm to adjust one or more weights of the plurality of weights applied to the plurality of cost dimensions to optimize the function of the sum of the quantities.

Aspects of the disclosure relate to methods for controlling a vehicle having an autonomous driving mode. For instance, sensor data may be received from one or more sensors of the perception system of the vehicle, the sensor data identifying characteristics of an object perceived by the perception system. When it is determined that the object is no longer being perceived by the one or more sensors of the perception system, predicted characteristics for the object may be generated based on one or more of the identified characteristics. The predicted characteristics of the object may be used to control the vehicle in the autonomous driving mode such that the vehicle is able to respond to the object when it is determined that the object is no longer being perceived by the one or more sensors of the perception system.

A drive mode switch control device acquires operation information. The drive mode switch control device switches a drive state among at least an autonomous drive state, a manual drive state, and a coordination drive state. The operation detection unit detects a first operation and a second operation based on the operation information when the drive state is not in the manual drive state. The second operation is the drive operation different from the first operation and input after the input of the first operation. The drive mode switch control device switches the drive state from the autonomous drive state to the coordination drive state based on a detection determination of the first operation. The drive mode switch control device switches the drive state from the coordination drive state to the manual drive state based on a detection determination of the first operation.

A method performed by an electronic device is described. The method includes obtaining sensor data corresponding to multiple occupants from an interior of a vehicle. The method also includes obtaining, by a processor, at least one occupant status for at least one of the occupants based on a first portion of the sensor data. The method further includes identifying, by the processor, at least one vehicle operation in response to the at least one occupant status. The method additionally includes determining, by the processor, based at least on a second portion of the sensor data, whether to perform the at least one vehicle operation. The method also includes performing the at least one vehicle operation in a case that it is determined to perform the at least one vehicle operation.

Particular embodiments may enable configuring settings of a vehicle in a designated mode. A signal to place the vehicle in a designated mode may be received. A roll angle and a pitch angle of the vehicle as parked may be assessed based on data received from a position sensor built into the vehicle. Signals to adjust an electronically controlled suspension of the vehicle to reduce the roll angle or the pitch angle so that the vehicle is level as parked may be sent based on the assessed roll angle and pitch angle exceeding a threshold value. One or more settings of the vehicle to change default operating characteristics by the vehicle while in the designated mode may be modified.

Determination of a trajectory for a first vehicle (1) by model predictive control (MPC) is provided. Trajectory information about a second vehicle (18) traveling in the area ahead of the first vehicle (1) is utilized. In particular, discretization points (P.sub.1, P.sub.2, P.sub.3) and arrival times of the vehicles (1, 18) at the discretization points (P.sub.1, P.sub.2, P.sub.3) are utilized to generate constraints for the model predictive control of the first vehicle (1).