Disclosed in the present disclosure are a method and an apparatus for determining a vehicle speed control model training sample. The method includes: a lane in map data is divided into a first lane area and a second lane area, and to-be-measured vehicle speed control features indicated by the two lane areas are different; the to-be-measured vehicle speed control features are determined as target vehicle speed control feature when a difference between a first empirical highest vehicle speed distribution and a second empirical highest vehicle speed distribution is greater than or equal to a preset difference threshold; and starting coordinates and ending coordinates of each preset lane section in the map data, and the target vehicle speed control features and a vehicle speed control label in the preset lane section are taken as a vehicle speed control model training sample.

Disclosed is an electronic device for a vehicle, including a processor receiving first image data from a first camera, receiving second image data from a second camera, receiving first sensing data from a first lidar, generating a depth image based on the first image data and the second image data, and fusing the first sensing data for each of divided regions in the depth image.

A method for fusing state data via a control unit. State data of a first mobile unit and of an object ascertained via a sensor system of the first mobile unit are received. State data of an object ascertained via a sensor system of a second mobile unit and/or state data of the second mobile unit, transmitted via a communication link from the second mobile unit to the first mobile unit, are received. A node is created in a time-position diagram for each set of received state data of the first mobile unit, the second mobile unit, and the objects. A data optimization of the state data ascertained by the first mobile unit and/or by the second mobile unit is carried out. An optimization problem is created based on the optimized state data ascertained by the first mobile unit and the optimized state data received from the second mobile unit.

A path providing device configured to provide a path information to a vehicle includes: a communication unit configured to receive, from a server, map information including a plurality of layers of data, an interface unit configured to receive sensing information from one or more sensors disposed at the vehicle, a processor, and an event data recorder (EDR) configured to store vehicle status information including first sensor data sensed by a first sensor associated with an operation of the vehicle, and second sensor data sensed by a second sensor associated with surrounding information of the vehicle. The processor is configured to determine an optimal path for guiding the vehicle from an identified lane, generate autonomous driving visibility information, update the optimal path based on dynamic information and the autonomous driving visibility information, and include the vehicle status information stored in the EDR in the autonomous driving visibility information.

Autonomous driving of a vehicle in which computerized perception by the vehicle, including of its environment and of itself (e.g., its egomotion), is used to autonomously drive the vehicle and, additionally, can also be used to provide feedback to enhance performance, safety, and/or other attributes of autonomous driving of the vehicle (e.g., when certain conditions affecting the vehicle are determined to exist by detecting patterns in or otherwise analyzing what is perceived by the vehicle), such as by adjusting autonomous driving of the vehicle, conveying messages regarding the vehicle, and/or performing other actions concerning the vehicle.

Techniques relating to monitoring map consistency are described. In an example, a monitoring component associated with a vehicle can receive sensor data associated with an environment in which the vehicle is positioned. The monitoring component can generate, based at least in part on the sensor data, an estimated map of the environment, wherein the estimated map is encoded with policy information for driving within the environment. The monitoring component can then compare first information associated with a stored map of the environment with second information associated with the estimated map to determine whether the estimated map and the stored map are consistent. Component(s) associated with the vehicle can then control the object based at least in part on results of the comparing.

A method for the control of a vehicle by an operator. The method includes: using a predictive map to control the vehicle by: detecting a situation and/or location reference of the vehicle, transmitting data of a defined set of sensors, fusing and processing the data of the defined set of sensors; displaying the fused and processed data for the operator; creating/updating the predictive map by: recognizing a problematic situation and/or a problematic location by observation of the operator and/or marking by the operator, storing the problematic situation and/or the problematic location in a first database for storing problematic situations and locations, and training a model for selecting the defined set of sensors and fusing the data of the defined set of sensors by machine learning.

Methods and systems are provided for controlling an autonomous vehicle. In one embodiment, a method includes: A method of controlling an autonomous vehicle, comprising: receiving, by a processor, a first set of data obtained from an inertial measurement unit of the vehicle; receiving, by the processor, a second set of data obtained from a global positioning system of the vehicle; receiving, by the processor, a third set of data obtained from a camera of the vehicle; determining, by the processor, at least two vehicle states relative to markings of a lane by processing the first set of data, the second set of data, and the third set of data as measurement with an extended Kalman filter; and controlling, by the processor, the vehicle based on the at least two vehicle states.

A vehicle sensor data processing method and system are provided. The method includes: a vehicle sensor data processing system processes and fuses, by using a plurality of levels of control units, a signal sensed by a sensor, and a higher-level control unit makes a control decision based on received data of a plurality of types or a plurality of processing levels. In addition, a priority of a sensor may be further configured based on a vehicle function that needs to be implemented by the system, thereby implementing more stable and reliable vehicle control and ensuring safe driving while satisfying a delay requirement.

A navigation system includes: a control circuit configured to: generate a video clip by parsing an interval of a sensor data stream for a region of travel; analyze the video clip submitted to a deep learning model, already trained, including identifying a traffic flow estimate; access a position coordinate for calculating a distance to intersection; generate a traffic flow state by fusing a corrected speed, the traffic flow estimate, and the distance to intersection; merge a vehicle maneuvering instruction into the traffic flow state for maneuvering through the region of travel; and a communication circuit, coupled to the control circuit, configured to: communicate the traffic flow state for displaying on a device.