Techniques for accurately predicting and avoiding collisions with objects detected in an environment of a vehicle are discussed herein. A vehicle computing device can implement a model to output data indicating costs for potential intersection points between the object and the vehicle in the future. The model may employ a control policy and a time-step integrator to determine whether an object may intersect with the vehicle, in which case the techniques may include predicting vehicle actions by the vehicle computing device to control the vehicle.

A device according to one aspect of the present disclosure is an on-vehicle control device configured to control a traveling speed of a vehicle including the on-vehicle control device. The on-vehicle control device includes: an acquisition unit configured to acquire a present light color of a traffic light unit installed at an intersection; a calculation unit configured to calculate an avoidance position and an avoidance speed with respect to a dilemma zone at a time when yellow light starts; and a control unit configured to execute a first deceleration process of reducing the traveling speed of the vehicle at the avoidance position to a speed equal to or lower than the avoidance speed, in a case where a present position of the vehicle is on an upstream side relative to the avoidance position and the present light color is green.

In some aspects, a safety system may be configured to receive vehicle position data indicating a position of a vehicle, determine a first lane segment in a lane coordinate system based on the vehicle position data, the first lane segment being a lane segment in which the vehicle is located, determine a relevant set of lane segments based on a safety-range from the first lane segment, determine or receive obstacle position data indicating a second lane segment in the lane coordinate system, the second lane segment being a lane segment in which an obstacle is located, and classify the obstacle either as a non-relevant obstacle in the case that the second lane segment is not included in the relevant set of lane segments, or as a relevant obstacle in the case that the second lane segment is included in the relevant set of lane segments.

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection.

Provided is An apparatus for assisting driving of a host vehicle, the apparatus comprising: a camera mounted to the host vehicle and having a field of view in front of the host vehicle, the camera configured to acquire image data; and a controller including a processor configured to process the image data, and configured to receive a map on which the host vehicle travels from a server, compare a speed limit included in the map with a speed limit included in the image data, and control a display of the host vehicle so as to display the speed limit based on the image data.

A method and an apparatus for controlling personal mobility device (PMD) depending on congestion includes identifying a target area according to an expected route of the PMD, acquiring a degree of congestion of the target area based on at least one of a type of objects, a movement of the objects, a distance between objects, the number of objects that is expected, and a speed limit of the target area, and controlling speed of the PMD according to the degree of congestion.

An adaptive cruise control for a motor vehicle includes a detection module for detecting a vehicle ahead, a production module capable of producing a setpoint, a storage module configured to store a value corresponding to the setpoint, a chronometer configured to be initialized and activated at a moment when the vehicle stops, and a reinitialization module for reinitializing the storage module. This cruise control includes a setup module capable of determining a limit according to the environment of the vehicle. The reinitialization module reinitializes the value stored by the storage module if the chronometer provides a duration greater than the limit.

A method for automatically reactivating a lane departure warning and/or lane keeping driver assistance system of a vehicle, comprising deactivating the system at a deactivation time point; identifying a first road condition which is associated with the deactivation time point when the system is being deactivated, wherein the first road condition is indicative of a driving situation when the driver wants the system to be deactivated; setting a reactivation threshold value, wherein the reactivation threshold value is set based on the identified first road condition and defines a limit for when the first road condition no longer applies; and automatically reactivating the system when it is determined that the reactivation threshold value is reached. The invention also relates to a vehicle control unit and to a vehicle.

The use of predefined (pre-built) graphical representations of roads for autonomous driving of vehicles and display of route planning.

The present invention relates to a method of generating and using a new data set for a novel technique of autonomous vehicle driving and route planning display using a predefined graphic representation/definition/illustration of the vehicle surroundings, in combination with the actual view sighted and captured by video cameras from the vehicle (for example, a dashboard camera). This method is primarily based on the use of the predefined graphic representation of the actual visual scene that is sighted from a host vehicle on roads at known GPS locations.

The main feature of this disclosure is the use of a predefined and simplified graphic illustration of the actual view experienced from vehicles on roads. This data is prepared in advance, stored in a cloud-based facility, and can be accessed by any vehicle.

The method comprises at least one video camera mounted in the vehicle, a module for accessing the predefined graphic visualization of the road and its surroundings, a module for defining the exact position and direction of the host vehicle on the predefined graphic view of the road, based on the use of GPS in combination with the identification of the surrounding characteristics of the road, a module continuously aligning the graphic view with the real view filmed by the video camera and for displaying the graphic visualization of the real view filmed by a forward facing camera.

The present invention relates to a new method for generating data that can be used in the vehicle's autopilot and for displaying route planning.

Numerous variations and modifications of the invention may be considered other than those described herein without departing from the spirit and scope of the present invention. This invention should not be limited by the specific details described herein.

A lane-borrowing vehicle driving method includes generating, by a control center, a first lane-borrowing driving policy of the vehicle based on a lane-borrowing requirement, a moving trend of the vehicle, and a preset traffic rule, where the lane-borrowing requirement includes a lane-borrowing driving reason, and the first lane-borrowing driving policy includes an instruction for controlling lane-borrowing driving of the vehicle, and sending, by the control center, the first lane-borrowing driving policy to the vehicle. The embodiments of this application are used for temporary lane-borrowing driving and lane-borrowing driving on a tidal lane.