A drive assistance system includes an onboard device that is mounted on a vehicle performing automatic driving based on sensing information detected by a sensor of the vehicle, and a center that communicates with the onboard device. The onboard device includes a sensing information acquisition portion that acquires the sensing information. Either the onboard device or the center includes an evaluation portion that evaluates a detection performance of the sensor based on the sensing information. The center includes a region specification portion that specifies a decrease region where the detection performance of the sensor decreases, the decrease region specified by the detection performance, based on the sensing information, and the decrease region specified by a position at which the sensing information has been detected. The onboard device stops the automatic driving when the vehicle is located in the decrease region.

An on-vehicle control apparatus (130) switches an operating state of an on-vehicle control system (100) from a regular state to a partially checking state in a case where a cyber-attack has been detected in a part of a plurality of driving control apparatuses (110 and 120). The regular state is an operating state in which autonomous driving is performed by using at least one of the plurality of driving control apparatuses. The partially checking state is an operating state in which the autonomous driving is performed by using at least one of normal driving control apparatuses where the cyber-attack has not been detected, and security of each of the driving control apparatuses where the cyber-attack has been detected is checked.

A transporter vehicle includes: a traveling device changing a traveling direction so that one state of a linear movement state and a non-linear movement state changes to the other state thereof; a setting unit setting a determination value related to a change amount in the traveling direction from the linear movement state; a collision prevention system including an object detection device detecting an object in front of the vehicle and a collision determination unit determining a possibility of a collision with the object based on a detection result of the object detection device, the collision prevention system performing a process for reducing damage caused by the collision with the object; and an invalidation unit invalidating at least a part of a process of the collision prevention system based on the determination value and a detection value of the change amount in the traveling direction from the linear movement state.

Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about a state of the object in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about a current state of the object in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the state of the object to corresponding control actions that are not applied to the object.

Methods and systems for evaluating the effectiveness of autonomous operation features of autonomous vehicles using an accident risk model are provided. According to certain aspects, an accident risk model may be determined using effectiveness information regarding autonomous operation features associated with a vehicle. The effectiveness information may indicate a likelihood of an accident for the vehicle and may include test data or actual loss data. Determining the likelihood of an accident may include determining risk factors for the features related to the ability of the features to make control decisions that successfully avoid accidents. The accident risk model may further include information regarding effectiveness of the features relative to location or operating conditions, as well as types and severity of accidents. The accident risk model may further be used to determine or adjust aspects of an insurance policy associated with an autonomous vehicle.

A method for operating a navigation system for a motor vehicle with autopilot is disclosed, wherein the autopilot is designed to automatically carry out longitudinal and lateral guidance of the motor vehicle in the activated state during a piloted journey without assistance from a driver. The navigation system determines, for a destination prescribed by the user, a route to the destination on the basis of navigation data. The roads on which the activation of the autopilot is likely to be possible is determined using traffic data and on the basis of a predetermined activation condition for the autopilot.

A computer in a vehicle is configured to operate the vehicle in at least one of an autonomous and a semi-autonomous mode. The computer is further configured to detect at least one condition of a roadway being traveled by the vehicle, the condition comprising at least one of a restricted lane, a restricted zone, a construction zone, and accident area, an incline, a hazardous road surface. The computer is further configured to determine at least one autonomous action based on the condition, the at least one autonomous action including at least one of altering a speed of the vehicle, controlling vehicle steering, controlling vehicle lighting, transitioning the vehicle to manual control, and controlling a distance of the vehicle from an object.

A state predicting circuitry predicts a route showing a future change in the vehicle state from among a plurality of routes from a first node to a second node. The first node corresponds to the current vehicle state. The second node corresponds to the vehicle state after having transitioned a predetermined number of times from the first node. The state predicting circuitry predicts a route in which at least one of an accumulated value of the node that exists in the routes and an accumulated value of the link that exists in the routes is greatest, from among the plurality of routes.

Models can be generated of a vehicle's view of its environment and used to maneuver the vehicle. This view need not include what objects or features the vehicle is actually seeing, but rather those areas that the vehicle is able to observe using its sensors if the sensors were completely un-occluded. For example, for each of a plurality of sensors of the object detection component, a computer may generate an individual 3D model of that sensor's field of view. Weather information is received and used to adjust one or more of the models. After this adjusting, the models may be aggregated into a comprehensive 3D model. The comprehensive model may be combined with detailed map information indicating the probability of detecting objects at different locations. The model of the vehicle's environment may be computed based on the combined comprehensive 3D model and detailed map information.

A driving control system includes an automatic driving control device and a driver monitoring device. The automatic driving control device includes a driver state determining unit, an override detector, a retreat mode controller, and a retreat mode canceler. During traveling under an automatic driving mode, when the driver state determining unit determines from a driver state detected by the driver monitoring device that the driver is not in a state capable of driving normally, the retreat mode controller sets a retreat mode in which an override operation is disabled and an own vehicle is caused to travel for retreat. When the driver state determining unit determines, during traveling for retreat, that the driver has returned to the state capable of driving normally, the retreat mode canceler cancels the retreat mode, and enables detection of the override operation of the driver by the override detector.