A computer-implemented method of evaluating the performance of a full or partial autonomous vehicle (AV) stack in simulation, the method comprising: applying an optimization algorithm to a numerical performance function defined over a scenario space, wherein the numerical performance function quantifies the extent of success or failure of the AV stack as a numerical score, and the optimization algorithm searches the scenario space for a driving scenario in which the extent of failure of the AV stack is substantially maximized, wherein the optimization algorithm evaluates multiple driving scenarios in the search space over multiple iterations, by running a simulation of each driving scenario in a simulator, in order to provide perception inputs to the AV stack, and thereby generate at least one simulated agent trace and a simulated ego trace reflecting autonomous decisions taken in the AV stack in response to the simulated perception inputs, wherein later iterations of the multiple iterations are guided by the results of previous iterations of the multiple iterations, with the objective of finding the driving scenario for which the extent of failure of the AV stack is maximized.

Systems and methods are provided for predicting blind spot incursions for a host vehicle. In one implementation, a navigation system for a host vehicle may comprise a processor. The processor may be programmed to receive, from an image capture device located on a rear of the host vehicle, at least one image representative of an environment of the host vehicle. The processor may be programmed to analyze the at least one image to identify an object in the environment of the host vehicle and to determine kinematic information associated with the object. The processor may further be programmed to predict, based on the kinematic information, that the object will travel in a region outside of a field of view of the image capture device and perform a control action based on the prediction.

A deceleration support device in which an electronic control unit controls a speed reduction device to execute automatic deceleration control when an object that requires deceleration of a vehicle is detected and a braking/driving operation is not detected, and interrupt the automatic deceleration control when a driving operation is detected in a situation where the automatic deceleration control is being executed, and with an object that requires deceleration of the vehicle and does not prevent the vehicle from passing through a position of the object being defined as a specific object, the electronic control unit resumes the automatic deceleration control if it is determined that the object is not a specific object, but does not resume the automatic deceleration control if it is determined that the object is a specific object, when the driving operation is not detected in a situation where the automatic deceleration control is interrupted.

Disclosed herein is a vehicle predictive control method that includes determining a driving prediction horizon in front of a vehicle, dividing the driving prediction horizon into a plurality of steps, at least some of the steps corresponding to a sloped section being integrated into one step according to slopes, and applying a driving prediction model based on a relationship between states of vehicle speed, traction force, and braking force for each step and collectively computing the driving prediction model over the entire prediction horizon to calculate a control value for the vehicle.

An object detection device includes first and second detectors each configured to detect an object by transmitting an ultrasonic wave in a moving direction of the moving object and receiving a reflected wave of the ultrasonic wave, a second detector, a memory, and a hardware processor coupled to the memory, and configured to: determine that an obstacle is present in the moving direction of the moving object, based on object detection results by the first and second detectors; determine crossing of the obstacle based on object detection results by the first and second detectors in a state in which it is being determined that the obstacle is present; and cause a driving controller mounted on the moving object, to release driving restriction control of restricting movement of the moving object when determining the crossing, or prohibit the driving controller from releasing the driving restriction control under a predetermined condition.

A control device mounted on a mobile object acquires surrounding situation information indicating a surrounding situation of a mobile object recognized by an object recognition device mounted on the mobile object, detects a predetermined reference object present in a traveling direction of the mobile object on the basis of the surrounding situation information, identifies a travelable area of the mobile object on the basis of the surrounding situation information, controls traveling of the mobile object such that the mobile object travels in the travelable area, causes the mobile object to move closer to the reference object when the reference object is detected, and detects an accompanying object accompanying the reference object on the basis of the surrounding situation information recognized by the object recognition device after the mobile object moves closer to the reference object, and identifying the travelable area by excluding the reference object and the accompanying object.

A vehicle driving assist device includes a traveling environment recognizer, an obstacle recognizer, an emergency collision, an oncoming moving body recognizer, a lateral position calculator, a risk degree calculator, and a preliminary collision avoidance controller. The obstacle recognizer recognizes, based on information recognized by a traveling environment recognizer, an obstacle on a vehicle's traveling path. An emergency collision avoidance controller performs emergency collision avoidance control for avoiding a collision with the obstacle. An oncoming moving body recognizer recognizes, an oncoming moving body in an oncoming lane. A lateral position calculator calculates a distance from a lane marker defining the oncoming lane to a reference position of the oncoming moving body. A risk degree calculator calculates a risk degree for the oncoming moving body. A preliminary collision avoidance controller recognizes the oncoming moving body as the obstacle, and performs preliminary control before the emergency collision avoidance control.

A vehicle driving assist device includes an oncoming moving body recognizer configured to recognize an oncoming moving body; a lateral position distribution characteristics acquisition unit configured to acquire distribution characteristics of a lateral position of the oncoming moving body; a risk determination region setting unit configured to set, based on the distribution characteristics, a risk determination region for calculating a risk degree; a risk degree calculator configured to calculate the risk degree for the oncoming moving body; and a preliminary collision avoidance controller configured to recognize the oncoming moving body as the obstacle in accordance with the risk degree, and perform preliminary collision avoidance control in response to the oncoming moving body prior to the emergency collision avoidance control. The risk determination region setting unit is further configured to variably set the risk determination region so that the risk degree relatively increases as the distribution characteristics tend to disperse.

A vehicle driving assist device includes a processor that functions as a receiver, an emergency collision avoidance controller, and a preliminary collision avoidance controller. The receiver receives, in relation to an oncoming moving body moving in an oncoming lane adjacent to a traveling lane of a vehicle and having a velocity component in a direction opposite to a traveling direction of the vehicle, a risk degree calculated based on a history of a distance from a lane marker defining the oncoming lane to the oncoming moving body, by communication with a device outside the vehicle. Upon determination that the vehicle is highly likely to collide with an obstacle, the emergency collision avoidance controller performs emergency collision avoidance control. The preliminary collision avoidance controller recognizes the oncoming moving body as the obstacle in accordance with the risk degree, and performs preliminary control prior to the emergency collision avoidance control.

A driver assistance system include a camera mounted on a host vehicle and having an external field of view of the host vehicle and a controller configured to process image data captured by the camera. The controller may analyze the image data to determine whether a lane splitting vehicle approaching or close to the host vehicle is present and control a steering device of the host vehicle so that the host vehicle laterally moves away from a lane line close to the lane splitting vehicle when the lane splitting vehicle is present.