A method for checking an effect chain, which includes multiple components, for an infrastructure-based, at least semiautomated control of a motor vehicle within an infrastructure. The method includes: receiving state signals which represent a state of the effect chain, setting up at least one digital twin of the components of the effect chain based on the state signals, checking the effect chain with the aid of the at least one digital twin to determine whether the effect chain is suitable for an infrastructure-based, at least semiautomated control of a motor vehicle, determining whether the effect chain is suitable for an infrastructure-based, at least semiautomated control of a motor vehicle within the infrastructure based on the check.

A method for generating the at least one highway exit indicator, the method may include receiving video information and location information obtained during driving sessions of the plurality of vehicles; determining, based on the location information, multiple suspected highway exit events; selecting video information segments, wherein each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event; and applying a machine learning process on at least some of the selected video information segments to find the at least one highway exit indicator.

A method for generating the at least one highway exit indicator, the method may include receiving video information and location information obtained during driving sessions of the plurality of vehicles; determining, based on the location information, multiple suspected highway exit events; selecting video information segments, wherein each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event; and applying a machine learning process on at least some of the selected video information segments to find the at least one highway exit indicator.

Provided are a method and apparatus for controlling a vehicle, the method including receiving traffic signal information, determining whether or not a vehicle passes through a crosswalk, on the basis of the traffic signal information and driving information of the vehicle, in response to determining that the vehicle does not pass through the crosswalk, generating a virtual stop line, and controlling the vehicle not to cross the virtual stop line.

Systems and techniques are described for securely managing maneuver identifications (IDs) for vehicle-based communications. For example, a method may include transmitting a message associated with a potential maneuver by the vehicle, determining a maneuver identification (ID) for the potential maneuver based on the message, and transmitting a first maneuver message (including the maneuver ID) for the potential maneuver. In another example, a method may include receiving a first maneuver message including a maneuver ID, determining that the first maneuver ID is a new maneuver ID, and determining, based on the first maneuver ID being a new maneuver ID, whether the first maneuver ID matches a second maneuver ID determined based on a previously-received message. In another example, a method may include receiving maneuver messages that include a same maneuver identification (ID) and one or more source IDs and determining whether the source ID(s) of the maneuver messages match.

According to various embodiments, systems, methods, and mediums for operating an autonomous driving vehicles (ADV) are described. The embodiments use a number of machine learning models to extract features individually from audio data and visual data captured by sensors mounted on the ADV, and then to fuse these extracted features to create a concatenated feature vectors. The concatenated feature vector is provided to a multiplayer perceptron (MLP) as input to generate a detection result related to the presence of an emergency vehicle in the surrounding environment. The detection result can be used by the ADV to take appropriate actions to comply with the local traffic rules.

A vehicular collision mitigation method includes disposing at a vehicle a plurality of cameras, at least two non-camera sensors, and a control that processes data captured by the cameras and non-camera sensors. When the equipped vehicle is traveling forward, and via processing at the control of provided data captured by the forward viewing camera and the at least two non-camera sensors, it is determined if the vehicle is approaching a pedestrian or other vehicle forward of the vehicle. Responsive to such determination, braking by an automatic emergency braking system is controlled to mitigate collision with the pedestrian or other vehicle. Responsive to determination that a following vehicle is following the vehicle within a threshold distance from the vehicle and is approaching the vehicle above a threshold rate of approach, braking by the automatic emergency braking system is adjusted to mitigate collision at the rear of the vehicle by the following vehicle.

A method for detecting and modelling of an object on a surface of a road by first scanning the road and generating a 3D model of the scanned road (which 3D model of the scanned road contains a description of a 3D surface of the road) and then creating a top-view image of the road. The object is detected on the surface of the road by evaluating the top-view image of the road. The detected object is projected on the surface of the road in the 3D model of the scanned road. The object projected on the surface of the road in the 3D model of the scanned road is modelled.

Devices, systems and methods for causing light (visible or invisible) or other forms of energy to be emitted from traffic cones or other traffic channelizing or marking devices such as barrels, tubes, some buoys, some types of signs, etc.

A method for detecting and modelling of an object on a surface of a road by first scanning the road and generating a 3D model of the scanned road (which 3D model of the scanned road contains a description of a 3D surface of the road) and then creating a top-view image of the road. The object is detected on the surface of the road by evaluating the top-view image of the road. The detected object is projected on the surface of the road in the 3D model of the scanned road. The object projected on the surface of the road in the 3D model of the scanned road is modelled.