A vehicle speed control device 1 mounted in a vehicle comprises: a forward detection unit 121 that obtains the amount of time until a vehicle V.sub.b to be overtaken that is traveling to the side of a host vehicle V.sub.a, in which the vehicle speed device 1 is mounted, is overtaken; a rearward detection unit 122 that obtains the amount of time until the distance between the host vehicle V.sub.a and a following vehicle V.sub.c traveling rearward of the host vehicle V.sub.a reaches a prescribed rearward distance; and a speed control unit 123 that increases the speed of the host vehicle V.sub.a when the time until overtaking occurs is greater than the time until the prescribed rearward distance is reached.

Techniques are discussed for generating and optimizing a trajectory using closed-form numerical integration in route-relative coordinates. A decision planner component of an autonomous vehicle, for example, can receive or generate a reference trajectory, which may correspond to an ideal route for an autonomous vehicle to traverse through an environment, such as a center of a road segment. Lateral dynamics (e.g., steering angles, curvature values of trajectory segments) and longitudinal dynamics (e.g., velocity and acceleration) can be represented in a single algorithm such that optimizing the reference trajectory (e.g., based on loss functions or costs) can substantially simultaneously optimize the lateral dynamics and longitudinal dynamics in a single convergence operation. In some cases, the trajectory can be used to control the autonomous vehicle to traverse an environment.

A method for controlling operation of a motor vehicle includes an electronic controller receiving, e.g., from a vehicle-mounted sensor array, sensor data with dynamics information for a target vehicle and, using the received sensor data, predicting a lane assignment for the target vehicle on a road segment proximate the host vehicle. The electronic controller also receives map data with roadway information for the road segment; the controller fuses the sensor and map data to construct a polynomial overlay for a host lane of the road segment across which travels the host vehicle. A piecewise linearized road map of the host lane is constructed and combined with the predicted lane assignment and polynomial overlay to calculate a lane assignment for the target vehicle. The controller then transmits one or more command signals to a resident vehicle system to execute one or more control operations using the target vehicle's calculated lane assignment.

A method includes identifying a desired path for an ego vehicle. The method also includes determining how to apply steering control and torque vectoring control to cause the ego vehicle to follow the desired path. The determination is based on actuator delays associated with the steering control and the torque vectoring control and one or more limits of the ego vehicle. The method further includes applying at least one of the steering control and the torque vectoring control to create lateral movement of the ego vehicle during travel. Determining how to apply the steering control and the torque vectoring control may include using a state-space model that incorporates first-order time delays associated with the steering control and the torque vectoring control and using a linear quadratic regulator to determine how to control the ego vehicle based on the state-space model and the one or more limits of the ego vehicle.

Among other things, techniques are described for screening and monitoring the health of a vehicle user including receiving sensor data produced by a sensor at the vehicle, processing the sensor data to determine at least one health condition of the user of the vehicle, and in response to determining the at least one health condition, executing a vehicle function selected from a plurality of vehicle functions based on the at least one health condition.

Performance anomalies in autonomous vehicle can be difficult to identify, and the impact of such anomalies on systems within the autonomous vehicle may be difficult to understand. In examples, systems of the autonomous vehicle are modeled as nodes in a probabilistic graphical network. Probabilities of data generated at each of the nodes is determined. The probabilities are used to determine capabilities associated with higher level functions of the autonomous vehicle.

An apparatus for controlling a direction and speed of travel an autonomous vehicle or driver assisted autonomous vehicle (AV). A GPS and map module receive a start location and a destination location for the AV. A plurality of sensors identify a current and a proposed lane for the AV. A database of AV baseline maneuver profiles used to control one or more of direction and speed of travel of the AV is provided. A trajectory profile generator module generates a planned path for the AV with lateral acceleration less than 2 Hz, based on the start location, the destination location, the current and proposed lane for the AV, and a selected AV baseline maneuver profile from the database. A steering control module controls the direction of travel of the AV based on the generated AV planned path, and a supervisory control module controls the speed of the AV based on the generated AV planned path and inner ear constraints.

A travel assistance method is executed by a processor and comprises: acquiring, from a device for storing map information, information on static traveling path boundaries between a traveling path of a subject vehicle and other than the traveling path; acquiring, from a sensor for detecting surrounding environment of the subject vehicle, information on dynamic traveling path boundaries different from the static traveling path boundaries; generating, based on the information on the static traveling path boundaries, a static traveling path on which the subject vehicle can travel; generating, based on the information on the static traveling path and the dynamic traveling path boundaries, a dynamic traveling path which is shorter than the static traveling path and corresponds to the surrounding environment; and controlling the subject to travel along a traveling path including the static traveling path and the dynamic traveling path.

Techniques to generate driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. Nodes of the path are assigned a time for action to avoid collision from the node. The generated scenarios may be simulated in a computer.

The technology provides a sign detection and classification methodology. A unified pipeline approach incorporates generic sign detection with a robust parallel classification strategy. Sensor information such as camera imagery and lidar depth, intensity and height (elevation) information are applied to a sign detector module. This enables the system to detect the presence of a sign in a vehicle's externa environment. A modular classification approach is applied to the detected sign. This includes selective application of one or more trained machine learning classifiers, as well as a text and symbol detector. Annotations help to tie the classification information together and to address any conflicts with different the outputs from different classifiers. Identification of where the sign is in the vehicle's surrounding environment can provide contextual details. Identified signage can be associated with other objects in the vehicle's driving environment, which can be used to aid the vehicle in autonomous driving.