The described technology is generally directed towards digital map truth maintenance. Map inputs shared among multiple users of a shared overlay map service can have a range of credibility, from not credible to highly credible. The disclosed digital map truth maintenance technologies can be used to enhance credibility of shared map inputs. Credibility values can be calculated for map inputs, based on any of multiple factors. Map inputs having sufficiently high credibility, such as a credibility value determined to be above a threshold value, can be shared among multiple mobile devices.

A driving control device including a processor. The processor detects that a vehicle has encroached into an area configured for car-washing by a carwash machine, switches a travel mode of the vehicle to autonomous driving, and controls the vehicle so as to stop at a carwash position for the carwash machine under autonomous driving.

A method for data management for an autonomous vehicle may include transmitting a polling request to a first server to obtain a task. The task may be a remote task request, and the task may be associated with obtaining, from the autonomous vehicle, data related to one or more subjects via a mobile network. The method may also include receiving the task from the first server based on the polling request. The method may also include obtaining the data based on the task. The method may also include transmitting the data to a second server via the mobile network.

An autonomous vehicle is provided with a touch panel that enables an operator to input vehicle speed control instructions during an automatic driving mode and a mechanical operation unit for inputting driving control instructions. When the driving mode of the autonomous vehicle is the automatic driving mode or a semi-automatic driving mode, a driving control unit of the autonomous vehicle prioritizes a vehicle speed control instruction input from the touch panel over a vehicle speed control instruction input from the mechanical operation unit and executes vehicle speed control for the autonomous vehicle based on the prioritized instruction.

A vehicle controller includes a first detector that detects a traveling state of a host vehicle, a second detector that detects a traveling state of an other vehicle that travels along a main lane when the host vehicle is traveling along a merging road, a marking line recognizer that recognizes a marking line of the main lane, and a merging controller that performs merging control of the host vehicle into the main lane based on a transverse moving situation of the other vehicle detected by the second detector, wherein, when a marking line of the main lane is unable to be recognized by the marking line recognizer, the merging controller delays starting of the merging control in comparison with a case in which the marking line of the main lane is able to be recognized by the marking line recognizer.

Systems and methods for parallel autonomy of a vehicle are disclosed herein. One embodiment receives input data, the input data including at least one of sensor data and structured input data; encodes the input data into an intermediate embedding space using a first neural network; inputs the intermediate embedding space to a first behavior model and a second behavior model, the first behavior model producing a first behavior output, the second behavior model producing a second behavior output; combines the first behavior output and the second behavior output using an ideal-behavior model to produce an ideal behavior for the vehicle; and controls one or more aspects of operation of the vehicle based, at least in part, on the ideal behavior.

A method includes determining a target specification map that is associated with a task and that indicates, for each respective region of a plurality of regions around a vehicle equipped with a sensor, a target value of a parameter of the sensor. The method also includes determining a capability specification map that indicates, for each respective region, an attained value of the parameter that the sensor is configured to provide. The method additionally includes comparing the capability specification map to the target specification map to determine, for each respective region, a disparity between the target value and the attained value. The method further includes, based on the comparing, identifying one or more of: a first subset of the plurality of regions where the target value exceeds the attained value or a second subset of the plurality of regions where the attained value meets or exceeds the target value.

The present disclosure provides a method and a device for autonomous driving control, a vehicle, a storage medium and an electronic device. The method includes: obtaining first actual position data of a first vehicle body; obtaining relative position data between a second vehicle body and the first vehicle body; determining second actual position data of the second vehicle body according to the first actual position data and the relative position data, so that the vehicle performs autonomous driving control according to the first and second actual position data. The method can obtain the relative position between two vehicle bodies connected in the non-rigid manner and the real-time positions of the two vehicle bodies under different driving conditions in real time during the driving, can accurately depict the dynamic characteristics of two vehicle bodies, so that the vehicle performs autonomous driving control according to the first and second actual position data.

A system and method for providing an interpretable and unified representation for trajectory prediction that includes receiving birds-eye image data associated with travel of at least one agent within a roadway environment. The system and method also include analyzing the birds-eye image data to determine a potential field associated with the roadway environment and analyzing the birds-eye image data to determine a potential field associated with a past trajectory of the at least one agent. The system and method further include predicting a future trajectory of the at least one agent based on analysis of the potential fields.

A method includes encapsulating a current state of a road portion into a voxel grid, a first dimension of the voxel grid being associated with a first spatial dimension of the road portion, a second dimension of the voxel grid being associated with a second spatial dimension of the road portion, and a third dimension of the voxel grid comprising a plurality of feature layers, wherein each feature layer is associated with a feature of the road portion. The voxel grid may be input into a trained neural network and a future state of the road portion may be predicted based on an output of the neural network.